feat(agents): add RAI Planner, enhance SSSC Planner, and redesign Security Planner#979
Conversation
- add RAI Planner agent with responsible-AI instructions - redesign Security Planner with STRIDE risk-surface analysis - rename threat-model concept to risk-surface across security domain - integrate RAI into data-science and project-planning collections - flag all new D+E artifacts as experimental maturity 🔒 - Generated by Copilot
- add security-planning docs with phase reference, entry modes, and handoff pipeline - add rai-planning docs with phase reference, entry modes, and handoff pipeline - add RAI planner sample prompts for capture, from-prd, and from-security-plan modes - update Agent Systems Catalog with Security Planning and RAI Planning entries 📝 - Generated by Copilot
- fix 12 doc files using * instead of - for YAML list items in keywords/tags - regenerate plugins to include 3 missing RAI planning prompt entries - apply markdown table formatting from format:tables pipeline 🔧 - Generated by Copilot
Dependency Review✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.Scanned FilesNone |
|
@WilliamBerryiii I know this is a draft one, but wanted to highlight we have a backlog item to rename |
- add dedicated RAI Planner agent with capture, plan-from-prd, and plan-from-security-plan entry modes - create 7 RAI planning instruction files covering standards, sensitive uses, threat model, impact, backlog, identity, and capture coaching - update Security Planner with RAI awareness, OWASP 2025 + LLM Top 10 standards, AI/ML operational bucket, and AI-specific STRIDE extensions - add rai-planning collection manifest with experimental maturity - rename risk surface terminology to security model across all files 🤖 - Generated by Copilot
raymond-nassar
left a comment
There was a problem hiding this comment.
RAI Table-Stakes Checklist review. These comments are framed as questions to the author for consideration. Items are mapped from a vendor-neutral Responsible AI checklist evaluation.
|
@chaosdinosaur - do you have similar thoughts on the security side of this as @raymond-nassar? I'm also thinking that this PR needs a "secure software supply chain"(SSSC) agent that does all the same things but for build/CI systems. @raymond-nassar - this feedback is incredible .. I'm pulling it all into some research docs to make updates on both the RAI and security side ... and will use that to inform the SSSC agent build out. |
Glad that this helped! I made a Responsible AI "Table-Stakes" Checklist that didn't include things that only applied within Microsoft. This included a lot of items that I'm learned from reviewing a few dozen Impact Assessments. I then used that checklist with the Here is a copy of the checklist I created: Responsible AI Table‑Stakes Checklist (Vendor‑Neutral)1. Purpose & Scope Definition
2. Risk & Impact Screening
3. Input Guardrails
4. Output Guardrails
5. Human Oversight & Control
6. Transparency to Users
7. Transparency Documentation (e.g., FAQ or Model Card)
8. Appropriate Reliance Guidance
9. Data Considerations
10. Evaluation & Monitoring
11. Accountability & Documentation
|
…ner-redesign # Conflicts: # .github/CUSTOM-AGENTS.md # .github/agents/security/security-plan-creator.agent.md # .github/agents/security/security-planner.agent.md # .github/plugin/marketplace.json # .github/prompts/security/security-capture.prompt.md # .github/prompts/security/security-plan-from-prd.prompt.md # collections/hve-core-all.collection.yml # collections/project-planning.collection.yml # collections/security-planning.collection.md # collections/security-planning.collection.yml # docs/README.md # docs/agents/README.md # docs/architecture/ai-artifacts.md # docs/hve-guide/roles/security-architect.md # docs/security/sbom-verification.md # plugins/hve-core-all/README.md # plugins/hve-core-all/agents/security-plan-creator.md # plugins/project-planning/README.md # plugins/security/instructions/backlog-handoff.md # plugins/security/instructions/identity.md # plugins/security/instructions/operational-buckets.md # plugins/security/instructions/security-model.md # plugins/security/instructions/standards-mapping.md
- add RAI Planner agent with responsible-AI instructions - redesign Security Planner with STRIDE risk-surface analysis - rename threat-model concept to risk-surface across security domain - integrate RAI into data-science and project-planning collections - flag all new D+E artifacts as experimental maturity 🔒 - Generated by Copilot
- add security-planning docs with phase reference, entry modes, and handoff pipeline - add rai-planning docs with phase reference, entry modes, and handoff pipeline - add RAI planner sample prompts for capture, from-prd, and from-security-plan modes - update Agent Systems Catalog with Security Planning and RAI Planning entries 📝 - Generated by Copilot
- fix 12 doc files using * instead of - for YAML list items in keywords/tags - regenerate plugins to include 3 missing RAI planning prompt entries - apply markdown table formatting from format:tables pipeline 🔧 - Generated by Copilot
- add dedicated RAI Planner agent with capture, plan-from-prd, and plan-from-security-plan entry modes - create 7 RAI planning instruction files covering standards, sensitive uses, threat model, impact, backlog, identity, and capture coaching - update Security Planner with RAI awareness, OWASP 2025 + LLM Top 10 standards, AI/ML operational bucket, and AI-specific STRIDE extensions - add rai-planning collection manifest with experimental maturity - rename risk surface terminology to security model across all files 🤖 - Generated by Copilot
- add sssc-planner.agent.md with 6-phase supply chain assessment workflow - add 6 SSSC instruction files for identity, assessment, standards, gap analysis, backlog, and handoff - add 4 SSSC prompt files for capture, from-prd, from-brd, and from-security-plan entry modes - update security-planning and hve-core-all collection manifests with SSSC entries 🔗 - Generated by Copilot
fea5107 to
98087a5
Compare
…urity Planner - add guardrail verification and appropriate reliance to impact assessment - expand RAI identity with autonomous boundaries and data topics - add transparency category, optional artifacts, and handoffs frontmatter - fix security-planner autonomyTier and update collection metadata ✨ - Generated by Copilot
…n' into feature/security-planner-redesign # Conflicts: # .github/CUSTOM-AGENTS.md # .github/agents/rai-planning/rai-planner.agent.md # .github/agents/security/security-planner.agent.md # .github/instructions/rai-planning/rai-backlog-handoff.instructions.md # .github/instructions/rai-planning/rai-identity.instructions.md # .github/instructions/rai-planning/rai-impact-assessment.instructions.md # .github/instructions/rai-planning/rai-sensitive-uses.instructions.md # .github/instructions/security-planning/identity.instructions.md # collections/experimental.collection.yml # collections/hve-core-all.collection.yml # collections/project-planning.collection.md # collections/project-planning.collection.yml # docs/agents/README.md # docs/agents/rai-planning/why-rai-planning.md # plugins/data-science/README.md # plugins/experimental/README.md # plugins/hve-core-all/README.md # plugins/project-planning/README.md
…cabulary - resolve post-merge maturity conflicts across collection manifests - align RAI autonomy tier vocabulary to codebase standard (Full/Partial/Manual) - add .hypothesis to .gitignore and regenerate plugins 🔧 - Generated by Copilot
Review Comment Resolution SummaryWe addressed every substantive review comment in this PR. Here is the consolidated status. raymond-nassar (12 threads, all addressed)
auyidi1 (7 threads, all addressed)
General Comments
All 19 review threads have individual replies with specific file and line references. Each thread should be resolvable. |
raymond-nassar
left a comment
There was a problem hiding this comment.
PR-OBS-03 (Low): Phase 1 Question Template Wording Inconsistency
The Phase-Specific Question Templates section here still uses intended and unintended use contexts for Phase 1, while rai-identity.instructions.md (the authoritative instruction file) correctly uses intended use contexts, out-of-scope and prohibited use contexts, autonomous decision boundaries and human-only decision requirements.
Since the instruction file is the primary reference and was updated per RI-01/RI-05, this agent-level shorthand should be updated to match — or at minimum use intended and out-of-scope use contexts to avoid re-introducing the conflation between "unintended" and "out-of-scope" that RI-01 addressed.
raymond-nassar
left a comment
There was a problem hiding this comment.
I left one additional comment addressing a minor inconsistency that was discovered during my last review. Besides that, I am really excited to see this go live.
- add name frontmatter and Subagent Delegation sections to all three planners - add Phase-Specific Delegation with anti-hallucination guards - update CUSTOM-AGENTS registry and security-plan-from-prd prompt 🔧 - Generated by Copilot
…instructions - add fallback clauses, output contracts, and anti-hallucination guards - expand SSSC identity scope to include supply chain standards - harmonize backlog handoff and planning instructions across domains 📋 - Generated by Copilot
- move RAI and security planner artifacts from experimental to dedicated collections - add SSSC Planner artifacts to security collection - add researcher-subagent to data-science and rai-planning collections 📦 - Generated by Copilot
- add complete SSSC planning Docusaurus section with 7 pages - add RAI and SSSC plan templates - update security planning, RAI planning, and HVE guide references - update security architect and SRE operations role guides 📚 - Generated by Copilot
- move security and RAI planner plugins from experimental to dedicated collections - add SSSC planner plugin artifacts to security collection - add researcher-subagent plugins to data-science and rai-planning 🔄 - Generated by Copilot
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #979 +/- ##
==========================================
- Coverage 86.90% 86.88% -0.02%
==========================================
Files 59 59
Lines 8774 8770 -4
==========================================
- Hits 7625 7620 -5
- Misses 1149 1150 +1
Flags with carried forward coverage won't be shown. Click here to find out more. 🚀 New features to boost your workflow:
|
+ Fulcio + gitsign + Rekor + sscp + unforgeable + NTIA + ntia + DSPM + dspm 🔤 - Generated by Copilot
- update `sscpPlanFile` to `ssscPlanFile` in state schema - change `sscpEnabled` to `ssscEnabled` for consistency - revise documentation to reflect the updated agent name and functionality 🔧 - Generated by Copilot
|
@WilliLam I've done merge conflict resolution and gave a check to valid references. Did a few doc updates, and small changes to some wording, hope those are OK - Updated SSSC references in state schema and documentation and in the agents:
We should be good to merge. This is in |
🔒 - Generated by Copilot
🤖 I have created a release *beep* *boop* --- ## [3.2.0](hve-core-v3.1.46...hve-core-v3.2.0) (2026-03-20) ### ✨ Features * add -OutputPath parameter to Validate-MarkdownFrontmatter.ps1 ([#1134](#1134)) ([fdf1bcf](fdf1bcf)), closes [#1006](#1006) * add action version consistency scan workflow ([#1127](#1127)) ([4229df1](4229df1)) * **agent:** MVE Experiment Designer ([#976](#976)) ([70f86ca](70f86ca)) * **agents:** add ADO Backlog Manager orchestrator agent ([#800](#800)) ([fae3987](fae3987)) * **agents:** add meeting analyst agent for transcript analysis using work-iq ([#502](#502)) ([5345b5b](5345b5b)) * **agents:** add quick-reference line to RPI Phase 5 suggestions ([#897](#897)) ([9a90f39](9a90f39)) * **agents:** add RAI Planner, enhance SSSC Planner, and redesign Security Planner ([#979](#979)) ([06f826c](06f826c)) * **agents:** add symmetric cross-system handoff to GitHub Backlog Manager ([#952](#952)) ([ba34a35](ba34a35)) * **agents:** Functional Code Review Agent — pre-PR functional correctness reviewer ([#733](#733)) ([9cf63b7](9cf63b7)) * **build:** add Python extensions and uv 0.10.8 to devcontainer ([#920](#920)) ([9ca0579](9ca0579)) * **build:** add uv ecosystem to Dependabot configuration ([#913](#913)) ([2a4bd39](2a4bd39)) * **build:** enable npm pinning enforcement in dependency scan ([#838](#838)) ([4e9e31f](4e9e31f)) * **build:** migrate attestation actions to v4.1.0 and add SBOM verification docs ([#841](#841)) ([ca1e65b](ca1e65b)) * **collections:** add four new validator checks (orphan, duplicate, companion, coverage) ([#869](#869)) ([1a96b73](1a96b73)) * **devcontainer,security:** add enterprise artifact hub configuration ([#1032](#1032)) ([1d56d25](1d56d25)) * **docs:** add Rust coding standards and guidelines ([#809](#809)) ([d4c4899](d4c4899)) * **extension:** add Microsoft logo icon to VS Code Marketplace listings ([#906](#906)) ([82aca41](82aca41)) * **github:** add declarative label management ([#953](#953)) ([a1a6845](a1a6845)) * **instructions:** add ADO backlog shared infrastructure ([#786](#786)) ([1914078](1914078)) * **instructions:** add ADO backlog sprint planning and capacity tracking ([#788](#788)) ([d6fb77d](d6fb77d)) * **instructions:** add ADO triage workflow and prompt ([#787](#787)) ([cde0190](cde0190)) * **instructions:** add shared story quality conventions and sprint planning ([#803](#803)) ([a2f18e3](a2f18e3)) * **prompts:** add ADO discovery and work item prompts with agent routing ([#790](#790)) ([7e74523](7e74523)) * **prompts:** add security review prompts ([#1118](#1118)) ([ad30967](ad30967)) * **scripts:** add dynamic Python skill discovery for lint/test ([#957](#957)) ([0a90f57](0a90f57)) * **scripts:** add Get-StandardTimestamp utility to CIHelpers module ([#1126](#1126)) ([b273a4b](b273a4b)) * **scripts:** add Python copyright header validation ([#905](#905)) ([67df902](67df902)) * **scripts:** add Python skill support to Validate-SkillStructure ([#903](#903)) ([68479d9](68479d9)) * **scripts:** add workflow npm command scanning to dependency pinning ([#837](#837)) ([6b5ae06](6b5ae06)) * **security:** add basic security reviewer agent with owasp skills ([#1008](#1008)) ([cb1fd05](cb1fd05)) * **security:** add sigstore attestation bundles and fix component-detection action ([#1148](#1148)) ([f79c272](f79c272)) * **skills:** add Atheris fuzz harness with CI workflow integration ([#1102](#1102)) ([d337e1d](d337e1d)) * **skills:** add PowerPoint automation skill with YAML-driven deck generation ([#868](#868)) ([00465cd](00465cd)) * **skills:** convert hve-core-installer agent to self-contained skill ([#846](#846)) ([1d821fb](1d821fb)) * **skills:** enhance pr-reference skill with flexible filtering and base branch detection ([#1095](#1095)) ([26a32ea](26a32ea)) * **workflows:** add devcontainer infrastructure change log workflow ([#899](#899)) ([8aca446](8aca446)) * **workflows:** add milestone auto-close on stable and pre-release publishes ([#834](#834)) ([79362b1](79362b1)) * **workflows:** add ms.date documentation freshness checking ([#969](#969)) ([3ed441c](3ed441c)) * **workflows:** add Python linting CI workflow with Ruff ([#951](#951)) ([f89f0eb](f89f0eb)) * **workflows:** add Python testing CI workflow with pytest and Codecov ([#934](#934)) ([5e8306f](5e8306f)) * **workflows:** add uv and Python package sync to copilot-setup-steps ([#921](#921)) ([45d517d](45d517d)) ### 🐛 Bug Fixes * **build:** override Linguist vendored flag for Python skill files ([#1155](#1155)) ([0eee5b6](0eee5b6)) * **build:** override serialize-javascript to >=7.0.3 for RCE fix ([#876](#876)) ([e49039a](e49039a)) * **build:** resolve Pinned-Dependencies alerts for vsce npm commands in extension workflows ([#782](#782)) ([89dad9d](89dad9d)) * **build:** update undici and yauzl overrides for security audit ([#1030](#1030)) ([2c2f92f](2c2f92f)) * **docs:** add CLI Plugins to install.md navigation surfaces ([#902](#902)) ([79d6595](79d6595)) * **docs:** add sidebar ordering for Design Thinking documentation ([#832](#832)) ([551fddc](551fddc)), closes [#830](#830) * **docs:** graduate design-thinking to preview and correct stale collection references ([#831](#831)) ([5110e35](5110e35)) * **docs:** include project-planning in UX Designer install guidance ([#908](#908)) ([e7aa9bc](e7aa9bc)) * **docs:** remediate writing-style convention violations ([#865](#865)) ([68b04bc](68b04bc)) * **docs:** remove draft content announcement banner ([#825](#825)) ([b45de80](b45de80)) * **docs:** remove unbounded path-to-regexp override breaking SSG ([#1153](#1153)) ([d810018](d810018)) * **docs:** use actual clone paths instead of folder display names in multi-root workspace settings ([#984](#984)) ([5dbab82](5dbab82)) * **instructions:** replace black with ruff in uv-projects ([#898](#898)) ([b0c06d9](b0c06d9)) * **scripts:** cover .github/ skill files in copyright header validation ([#1055](#1055)) ([#1098](#1098)) ([27fbd33](27fbd33)) * **scripts:** eliminate phantom git changes from plugin generation ([#1035](#1035)) ([e49a1b5](e49a1b5)) * **scripts:** enable JSON log output for lint:version-consistency ([#1033](#1033)) ([52b0885](52b0885)) * **security:** calculate compliance score from total scanned dependencies ([#930](#930)) ([c112c3d](c112c3d)) * **skills:** add AST validation and namespace restriction for content-extra.py ([#1027](#1027)) ([c50c7a3](c50c7a3)) * **skills:** add depth limits to recursive PowerPoint processing functions ([#1028](#1028)) ([bf08994](bf08994)) * **skills:** harden XML parsing and blob writes in powerpoint extract ([#1053](#1053)) ([89d24b1](89d24b1)) * **skills:** resolve ruff lint and format violations in powerpoint skill ([#1048](#1048)) ([17bbe7a](17bbe7a)) * **workflows:** add uv.lock dependencies submission have fork-skip condition ([#1109](#1109)) ([dec56ac](dec56ac)) * **workflows:** automate weekly SHA staleness check with issue creation ([#975](#975)) ([1ea4caa](1ea4caa)) * **workflows:** close Codecov integration gaps for Pester and pytest flags ([#1106](#1106)) ([cca29b7](cca29b7)) * **workflows:** propagate uv sync errors in copilot-setup-steps ([#961](#961)) ([df88d7c](df88d7c)) * **workflows:** resolve release-please skip cascade and Python project discovery ([#1043](#1043)) ([79993e2](79993e2)) * **workflows:** scan only commit subjects for breaking change detection ([#1157](#1157)) ([a38a657](a38a657)) ### 📚 Documentation * clarify HVE Core Extension vs Installer messaging across documentation ([#965](#965)) ([0fceb8f](0fceb8f)) * **docs:** add ADO integration user documentation ([#935](#935)) ([ec89302](ec89302)) * **docs:** add Project Planning agent documentation ([#936](#936)) ([3a3a0fd](3a3a0fd)) * **onboarding:** overhaul marketplace onboarding and documentation site ([#982](#982)) ([4309e10](4309e10)) ### ♻️ Refactoring * **build:** merge code-review collection into coding-standards ([#863](#863)) ([8027e7b](8027e7b)) * **workflows:** rename release pipeline workflows and add marketplace automation triggers ([#829](#829)) ([b6397f4](b6397f4)) ### 🔧 Maintenance * **build:** add clean:logs npm script ([#1122](#1122)) ([f85fe02](f85fe02)), closes [#988](#988) * **build:** add JSON reporter for cspell ([#1123](#1123)) ([6d59f67](6d59f67)) * **ci:** add multi-arch support to copilot-setup-steps binary downloads ([#955](#955)) ([8d0c706](8d0c706)) * **deps-dev:** bump cspell from 9.6.4 to 9.7.0 in the npm-dependencies group ([#839](#839)) ([3fa16ff](3fa16ff)) * **deps:** bump actions/dependency-review-action from 4.8.3 to 4.9.0 in the github-actions group across 1 directory ([#942](#942)) ([1a9b858](1a9b858)) * **deps:** bump cairosvg from 2.8.2 to 2.9.0 in /.github/skills/experimental/powerpoint ([#1025](#1025)) ([f4deda7](f4deda7)) * **deps:** bump dompurify from 3.3.1 to 3.3.2 in /docs/docusaurus ([#924](#924)) ([d2060d6](d2060d6)) * **deps:** bump svgo from 3.3.2 to 3.3.3 in /docs/docusaurus ([#880](#880)) ([6dc2406](6dc2406)) * **deps:** bump the github-actions group across 1 directory with 4 updates ([#1100](#1100)) ([2290dc0](2290dc0)) * **deps:** bump the github-actions group with 6 updates ([#840](#840)) ([f57bc01](f57bc01)) * **docs:** correct New-MsDateReport table rendering and refresh stale docs ([#1114](#1114)) ([c2b806f](c2b806f)) * **settings:** remove orphaned Checkov config and stale gitignore entries ([#870](#870)) ([98fcd74](98fcd74)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: hve-core-release-please[bot] <254602402+hve-core-release-please[bot]@users.noreply.github.com> Co-authored-by: Bill Berry <wberry@microsoft.com>
…nd consolidate security collection (#1159) ## Description This PR addresses five issues discovered after the stable 3.2.0 release: pre-release pipeline failures, SBOM attestation errors, missing pre-release SBOM generation, an incorrectly re-created `security-planning` collection, and dependency review license false positives. ### Pre-release pipeline zero-diff force-push (#1160) Both `release-prerelease-pr.yml` and `release-stable.yml` used the GitHub API to force-push `prerelease/next` to the same SHA as `main`. GitHub detected 0-diff and auto-closed the open PR. The `reset-prerelease` job also ran git/gh commands without checkout. **Fix**: Replaced API-based force-push with atomic `git checkout -B` + `git push --force` to create a version-bump commit. Added `actions/checkout` with `fetch-depth: 0` to the `reset-prerelease` job. Added `-R` flag to `gh` CLI commands. Split the combined update step into separate reset and create-or-update PR steps. ### Stable release SBOM attestation failure (#1161) The dependency SBOM was downloaded to `./dist` alongside VSIX files, but attestation expected it at `./sbom/dependency-sbom.spdx.json`. **Fix**: Isolated dependency SBOM download to `./sbom` directory. Corrected `sbom-path` references. Added file-existence verification guards before all attestation steps. ### Pre-release pipeline missing SBOM (#1162) The pre-release pipeline had no dependency SBOM generation or attestation, unlike the stable pipeline. **Fix**: Added `generate-dependency-sbom` job using `anchore/sbom-action` with sparse checkout. Added per-VSIX SBOM generation, VSIX filename resolution, and SBOM attestation steps. Added `artifact-metadata: write` permission and expanded release asset uploads. ### security-planning collection consolidation (#1163) PR #980 renamed `security-planning` to `security`. PR #979 then incorrectly re-created `security-planning` as a separate collection for SSSC artifacts. **Fix**: Moved all files from `security-planning/` and `sssc-planning/` directories into `security/`. Updated all path references across collection YAMLs, agent files, marketplace.json, and documentation. Deleted `security-planning` collection manifests and plugin outputs. Regenerated all plugins. ### Dependency review license false positives (#1164) The `dependency-review.yml` workflow failed on PRs adding Python skill dependencies because `lxml` (BSD-3-Clause) and `typing-extensions` (PSF-2.0) were mis-labeled as GPL by the scanner due to compound SPDX expressions in their source distributions. **Fix**: Added per-package license exemptions via `allow-dependencies-licenses` for `pkg:pypi/lxml` and `pkg:pypi/typing-extensions`. Added missing license identifiers (`MIT-0`, `MIT-CMU`, `HPND`, `LicenseRef-scancode-secret-labs-2011`) to the global allow-list. Deduplicated `PRE_VERSION` calculation in `release-stable.yml` and added least-privilege comments to SBOM job permissions. ## Related Issue(s) Fixes #1160 Fixes #1161 Fixes #1162 Fixes #1163 Fixes #1164 ## Type of Change Select all that apply: **Code & Documentation:** * [x] Bug fix (non-breaking change fixing an issue) * [ ] New feature (non-breaking change adding functionality) * [x] Breaking change (fix or feature causing existing functionality to change) * [x] Documentation update **Infrastructure & Configuration:** * [x] GitHub Actions workflow * [ ] Linting configuration (markdown, PowerShell, etc.) * [x] Security configuration * [ ] DevContainer configuration * [ ] Dependency update **Other:** * [ ] Script/automation (`.ps1`, `.sh`, `.py`) * [ ] Other (please describe): ## Testing - YAML lint passed (43/43 workflow files) - Plugin generation: 12 collections, 0 errors - Plugin validation: 12 collections validated, 0 errors - Manual review of all workflow files for consistent atomic branch reset pattern - Verified all added action references use pinned 40-character commit SHAs with version comments - Grep validation: zero stale `security-planning/` or `sssc-planning/` references remain in live files ## Checklist ### Required Checks * [x] Documentation is updated (if applicable) * [x] Files follow existing naming conventions * [x] Changes are backwards compatible (if applicable) * [ ] Tests added for new functionality (if applicable) ### Required Automated Checks The following validation commands must pass before merging: * [x] Markdown linting: `npm run lint:md` * [x] Spell checking: `npm run spell-check` * [x] Frontmatter validation: `npm run lint:frontmatter` * [x] Skill structure validation: `npm run validate:skills` * [ ] Link validation: `npm run lint:md-links` * [x] PowerShell analysis: `npm run lint:ps` * [x] Plugin freshness: `npm run plugin:generate` ## Security Considerations * [x] This PR does not contain any sensitive or NDA information * [x] Any new dependencies have been reviewed for security issues * [x] Security-related scripts follow the principle of least privilege All new action references use fully pinned SHA references. Defensive `test -f` guards gate SBOM attestation steps. Sparse checkout limits clone surface. SBOM attestation uses `actions/attest` for supply chain integrity. The `security-planning` marketplace extension entry has been removed. Dependency review license exemptions use per-package `allow-dependencies-licenses` rather than adding GPL to the global allow-list. ## Additional Notes **Breaking change**: The `security-planning` collection and its marketplace extension no longer exist. All artifacts are now in the `security` collection. Consumers of the `security-planning` extension should switch to the `security` extension.
Pull Request
Description
Added a new RAI Planner agent, enhanced the SSSC Planner agent, and redesigned the existing Security Planner agent. All three agents follow a 6-phase orchestration pattern with dedicated instruction files, prompt entry points, and dual-format backlog handoff (ADO and GitHub). Namespaced work item IDs prevent collisions across planners.
What Changed
Agents: Added rai-planner.agent.md and security-planner.agent.md. Enhanced sssc-planner.agent.md with handoff buttons, web tool access, flattened state schema, and entry mode documentation. Deleted the previous security-plan-creator.agent.md and renamed the agent to Security Planner with a redesigned 6-phase STRIDE risk-surface analysis workflow. The RAI Planner implements a 6-phase RAI risk assessment workflow referencing Microsoft RAI Standard v2 and NIST AI RMF 1.0. Updated cross-references in implementation-validator.agent.md and system-architecture-reviewer.agent.md.
Instructions: Added 11 instruction files — 6 for RAI planning (identity, sensitive uses, standards mapping, security model, impact assessment, backlog handoff) and 5 for security planning (identity, operational buckets, standards mapping, security model, backlog handoff). Enhanced 6 SSSC instruction files (identity, assessment, standards, gap analysis, backlog, handoff) with flattened state schema, entry mode documentation, namespaced IDs, and explicit state transition rules. All files use proper YAML frontmatter with
applyTopatterns targeting.copilot-tracking/session paths.Prompts: Added 5 prompt files — 3 for RAI planning (rai-capture, rai-plan-from-prd, rai-plan-from-security-plan) and 2 for security planning (security-capture, security-plan-from-prd). All prompts use the
${input:project-slug}variable.Collections: Updated 8 collection manifests (experimental, project-planning, hve-core-all, data-science, security-planning, security) to include the new artifacts. Added SSSC and RAI planners to the security collection for comprehensive security coverage. Added caution notices for RAI and security collections. All new entries tagged
maturity: experimental.Documentation: Added 13 new Docusaurus pages across
docs/agents/rai-planning/anddocs/agents/security-planning/, covering agent overviews, phase references, entry modes, handoff pipelines, and motivation. Updated 19 existing documentation files to reference the new agents and align terminology.Infrastructure: Updated general-technical.txt with new terminology, refreshed CUSTOM-AGENTS.md with agent listings, and updated SECURITY.md references.
Plugins: Regenerated plugin symlinks and READMEs across 5 plugin directories. Security and security-planning plugins now list SSSC and RAI planners with full agent, command, and instruction tables.
Cross-Cutting Patterns
.copilot-tracking/paths for session state managementraiEnabledflag for RAI Planner integrationWI-SEC-{NNN}/{{SEC-TEMP-N}}(Security),WI-SSSC-{NNN}/{{SSSC-TEMP-N}}(SSSC),WI-RAI-{NNN}/{{RAI-TEMP-N}}(RAI)partialin all planneruserPreferencesRelated Issue(s)
No linked issues.
Type of Change
Select all that apply:
Code & Documentation:
Infrastructure & Configuration:
scripts/security/changed)AI Artifacts:
prompt-builderagent and addressed all feedback.github/instructions/*.instructions.md).github/prompts/*.prompt.md).github/agents/*.agent.md).github/skills/*/SKILL.md)Other:
.ps1,.sh,.py) (N/A — no script files changed)Sample Prompts (for AI Artifact Contributions)
RAI Planner
User Request:
Execution Flow:
.copilot-tracking/rai-plans/{slug}/.Researcher Subagentfor NIST AI RMF and Microsoft RAI Standard v2 framework lookups.Output Artifacts:
.copilot-tracking/rai-plans/{slug}/phase-01-identity.md— System identification.copilot-tracking/rai-plans/{slug}/phase-02-sensitive-uses.md— Sensitive uses assessment.copilot-tracking/rai-plans/{slug}/phase-03-standards.md— Standards mapping.copilot-tracking/rai-plans/{slug}/phase-04-security-model.md— Security model analysis.copilot-tracking/rai-plans/{slug}/phase-05-impact.md— Impact assessment.copilot-tracking/rai-plans/{slug}/phase-06-backlog.md— Dual-format backlog (ADO + GitHub)Success Indicators:
Security Planner
User Request:
Execution Flow:
.copilot-tracking/security-plans/{slug}/.raiEnabled: trueand recommends follow-up with the RAI Planner.Output Artifacts:
.copilot-tracking/security-plans/{slug}/phase-01-discovery.md— Component discovery.copilot-tracking/security-plans/{slug}/phase-02-buckets.md— Operational bucket classification.copilot-tracking/security-plans/{slug}/phase-03-standards.md— Standards mapping.copilot-tracking/security-plans/{slug}/phase-04-security-model.md— STRIDE security model.copilot-tracking/security-plans/{slug}/phase-05-impact.md— Impact assessment.copilot-tracking/security-plans/{slug}/phase-06-backlog.md— Dual-format backlog (ADO + GitHub)Success Indicators:
raiEnabledflag is set and RAI Planner handoff recommendedSSSC Planner
User Request:
Execution Flow:
.copilot-tracking/sssc-plans/{slug}/.Output Artifacts:
.copilot-tracking/sssc-plans/{slug}/state.json— Session state.copilot-tracking/sssc-plans/{slug}/sssc-plan.md— Comprehensive SSSC planSuccess Indicators:
Testing
npm run lint:mdnpm run spell-checknpm run lint:frontmatternpm run validate:skillsnpm run lint:md-linksnpm run lint:psnpm run plugin:generateRemediation Applied: Frontmatter validation initially found 12 errors in documentation files under
docs/agents/rai-planning/anddocs/agents/security-planning/— YAML list items used*instead of-. Fixed all 12 files and regenerated plugins. Manual testing was not performed. All validation is automated via npm scripts.Checklist
Required Checks
AI Artifact Contributions
/prompt-analyzeto review contributionprompt-builderreviewRequired Automated Checks
The following validation commands must pass before merging:
npm run lint:mdnpm run spell-checknpm run lint:frontmatternpm run validate:skillsnpm run lint:md-linksnpm run lint:psnpm run plugin:generateGHCP Artifact Maturity
Warning
This PR includes experimental GHCP artifacts that may have breaking changes.
.github/agents/rai-planning/rai-planner.agent.md.github/agents/security-planning/sssc-planner.agent.md.github/agents/security/security-planner.agent.md.github/instructions/rai-planning/rai-identity.instructions.md.github/instructions/rai-planning/rai-sensitive-uses.instructions.md.github/instructions/rai-planning/rai-standards.instructions.md.github/instructions/rai-planning/rai-security-model.instructions.md.github/instructions/rai-planning/rai-impact-assessment.instructions.md.github/instructions/rai-planning/rai-backlog-handoff.instructions.md.github/instructions/rai-planning/rai-capture-coaching.instructions.md.github/instructions/security-planning/identity.instructions.md.github/instructions/security-planning/operational-buckets.instructions.md.github/instructions/security-planning/standards-mapping.instructions.md.github/instructions/security-planning/security-model.instructions.md.github/instructions/security-planning/backlog-handoff.instructions.md.github/instructions/sssc-planning/sssc-identity.instructions.md.github/instructions/sssc-planning/sssc-assessment.instructions.md.github/instructions/sssc-planning/sssc-standards.instructions.md.github/instructions/sssc-planning/sssc-gap-analysis.instructions.md.github/instructions/sssc-planning/sssc-backlog.instructions.md.github/instructions/sssc-planning/sssc-handoff.instructions.md.github/prompts/rai-planning/rai-capture.prompt.md.github/prompts/rai-planning/rai-plan-from-prd.prompt.md.github/prompts/rai-planning/rai-plan-from-security-plan.prompt.md.github/prompts/security/security-capture.prompt.md.github/prompts/security/security-plan-from-prd.prompt.md.github/prompts/security-planning/sssc-capture.prompt.md.github/prompts/security-planning/sssc-from-prd.prompt.md.github/prompts/security-planning/sssc-from-brd.prompt.md.github/prompts/security-planning/sssc-from-security-plan.prompt.md.github/agents/rai-planning/rai-planner.agent.md.github/agents/security-planning/sssc-planner.agent.md.github/agents/security/security-planner.agent.md.github/agents/hve-core/subagents/implementation-validator.agent.md.github/agents/project-planning/system-architecture-reviewer.agent.md.github/instructions/rai-planning/rai-identity.instructions.md.github/instructions/rai-planning/rai-sensitive-uses.instructions.md.github/instructions/rai-planning/rai-standards.instructions.md.github/instructions/rai-planning/rai-security-model.instructions.md.github/instructions/rai-planning/rai-impact-assessment.instructions.md.github/instructions/rai-planning/rai-backlog-handoff.instructions.md.github/instructions/rai-planning/rai-capture-coaching.instructions.md.github/instructions/security-planning/identity.instructions.md.github/instructions/security-planning/operational-buckets.instructions.md.github/instructions/security-planning/standards-mapping.instructions.md.github/instructions/security-planning/security-model.instructions.md.github/instructions/security-planning/backlog-handoff.instructions.md.github/instructions/sssc-planning/sssc-identity.instructions.md.github/instructions/sssc-planning/sssc-assessment.instructions.md.github/instructions/sssc-planning/sssc-standards.instructions.md.github/instructions/sssc-planning/sssc-gap-analysis.instructions.md.github/instructions/sssc-planning/sssc-backlog.instructions.md.github/instructions/sssc-planning/sssc-handoff.instructions.md.github/prompts/rai-planning/rai-capture.prompt.md.github/prompts/rai-planning/rai-plan-from-prd.prompt.md.github/prompts/rai-planning/rai-plan-from-security-plan.prompt.md.github/prompts/security/security-capture.prompt.md.github/prompts/security/security-plan-from-prd.prompt.md.github/prompts/security-planning/sssc-capture.prompt.md.github/prompts/security-planning/sssc-from-prd.prompt.md.github/prompts/security-planning/sssc-from-brd.prompt.md.github/prompts/security-planning/sssc-from-security-plan.prompt.md.github/skills/installer/hve-core-installer/SKILL.mdGHCP Maturity Acknowledgment