Skip to content

refactor(skills): consolidate code verification skills into one#4854

Merged
teknium1 merged 2 commits into
mainfrom
hermes/hermes-1e1d81f5
Apr 3, 2026
Merged

refactor(skills): consolidate code verification skills into one#4854
teknium1 merged 2 commits into
mainfrom
hermes/hermes-1e1d81f5

Conversation

@teknium1

@teknium1 teknium1 commented Apr 3, 2026

Copy link
Copy Markdown
Contributor

Summary

Consolidates three overlapping code review/verification skills into one clear skill:

  • Deleted: code-review (passive checklist — absorbed)
  • Enhanced: requesting-code-review (now a full automated pipeline)
  • Closes PR feat(skills): add verify-code-changes skill #4459 by @MorAlekss (verify-code-changes) — their static scan, baseline gates, and auto-fix loop patterns are incorporated with credit

Why

Three skills (code-review, requesting-code-review, and the proposed verify-code-changes) all trigger on "review code" — the model can't reliably distinguish them. One consolidated skill with a clear pipeline eliminates the ambiguity.

What the enhanced skill now includes

  1. Static security scan (grep on diff lines)
  2. Baseline-aware quality gates (only flag NEW failures)
  3. Multi-language tool detection (Python, Node, Rust, Go)
  4. Independent reviewer subagent with fail-closed JSON verdict
  5. Auto-fix loop with separate fixer agent (max 2 attempts)
  6. Git checkpoint and [verified] commit convention
  7. Self-review checklist (from deleted code-review)
  8. Common vulnerability patterns reference

Software-development skills after this change

Skill Trigger Purpose
requesting-code-review "verify", "commit", "push", "review before merge" Full pre-commit verification pipeline
github-code-review "review this PR", "check PR #N" Review others' PRs on GitHub with inline comments
test-driven-development "implement this", "fix this bug" TDD red-green-refactor
subagent-driven-development "execute this plan" Multi-task subagent dispatch
systematic-debugging "this is broken" Root cause investigation
writing-plans "plan this feature" Spec → implementation plan

Closes #406

teknium1 added 2 commits April 3, 2026 11:14
168 merged PRs, 223 commits, 46 resolved issues, 40+ contributors.

Highlights: pluggable memory providers, credential pools, Camofox browser,
inline diff previews, API server session continuity, ACP MCP registration,
gateway hardening, secret exfiltration blocking.
…requesting-code-review

Merge the passive code-review checklist and the automated verification
pipeline (from PR #4459 by @MorAlekss) into a single requesting-code-review
skill. This eliminates model confusion between three overlapping skills.

Now includes:
- Static security scan (grep on diff lines)
- Baseline-aware quality gates (only flag NEW failures)
- Multi-language tool detection (Python, Node, Rust, Go)
- Independent reviewer subagent with fail-closed JSON verdict
- Auto-fix loop with separate fixer agent (max 2 attempts)
- Git checkpoint and [verified] commit convention

Deletes: skills/software-development/code-review/ (absorbed)
Closes: #406 (independent code verification)
@github-actions

github-actions Bot commented Apr 3, 2026

Copy link
Copy Markdown
Contributor

⚠️ Supply Chain Risk Detected

This PR contains patterns commonly associated with supply chain attacks. This does not mean the PR is malicious — but these patterns require careful human review before merging.

⚠️ WARNING: exec() or eval() usage

Dynamic code execution can hide malicious behavior, especially when combined with base64 or network fetches.

Matches (first 20):

607:+shell injection, SQL injection, path traversal, eval()/exec() with user input,

⚠️ WARNING: marshal/pickle/compile usage

These can deserialize or construct executable code objects.

Matches:

608:+pickle.loads(), obfuscated commands.

Automated scan triggered by supply-chain-audit. If this is a false positive, a maintainer can approve after manual review.

@teknium1 teknium1 merged commit 52ddd6b into main Apr 3, 2026
5 of 6 checks passed
Tommyeds pushed a commit to Tommyeds/hermes-agent that referenced this pull request Apr 12, 2026
…Research#4854)

* chore: release v0.7.0 (2026.4.3)

168 merged PRs, 223 commits, 46 resolved issues, 40+ contributors.

Highlights: pluggable memory providers, credential pools, Camofox browser,
inline diff previews, API server session continuity, ACP MCP registration,
gateway hardening, secret exfiltration blocking.

* refactor(skills): consolidate code-review + verify-code-changes into requesting-code-review

Merge the passive code-review checklist and the automated verification
pipeline (from PR NousResearch#4459 by @MorAlekss) into a single requesting-code-review
skill. This eliminates model confusion between three overlapping skills.

Now includes:
- Static security scan (grep on diff lines)
- Baseline-aware quality gates (only flag NEW failures)
- Multi-language tool detection (Python, Node, Rust, Go)
- Independent reviewer subagent with fail-closed JSON verdict
- Auto-fix loop with separate fixer agent (max 2 attempts)
- Git checkpoint and [verified] commit convention

Deletes: skills/software-development/code-review/ (absorbed)
Closes: NousResearch#406 (independent code verification)
angelburgosrosado pushed a commit to angelburgosrosado/hermes-agent that referenced this pull request Apr 27, 2026
…Research#4854)

* chore: release v0.7.0 (2026.4.3)

168 merged PRs, 223 commits, 46 resolved issues, 40+ contributors.

Highlights: pluggable memory providers, credential pools, Camofox browser,
inline diff previews, API server session continuity, ACP MCP registration,
gateway hardening, secret exfiltration blocking.

* refactor(skills): consolidate code-review + verify-code-changes into requesting-code-review

Merge the passive code-review checklist and the automated verification
pipeline (from PR NousResearch#4459 by @MorAlekss) into a single requesting-code-review
skill. This eliminates model confusion between three overlapping skills.

Now includes:
- Static security scan (grep on diff lines)
- Baseline-aware quality gates (only flag NEW failures)
- Multi-language tool detection (Python, Node, Rust, Go)
- Independent reviewer subagent with fail-closed JSON verdict
- Auto-fix loop with separate fixer agent (max 2 attempts)
- Git checkpoint and [verified] commit convention

Deletes: skills/software-development/code-review/ (absorbed)
Closes: NousResearch#406 (independent code verification)
02356abc pushed a commit to 02356abc/hermes-agent that referenced this pull request May 14, 2026
…Research#4854)

* chore: release v0.7.0 (2026.4.3)

168 merged PRs, 223 commits, 46 resolved issues, 40+ contributors.

Highlights: pluggable memory providers, credential pools, Camofox browser,
inline diff previews, API server session continuity, ACP MCP registration,
gateway hardening, secret exfiltration blocking.

* refactor(skills): consolidate code-review + verify-code-changes into requesting-code-review

Merge the passive code-review checklist and the automated verification
pipeline (from PR NousResearch#4459 by @MorAlekss) into a single requesting-code-review
skill. This eliminates model confusion between three overlapping skills.

Now includes:
- Static security scan (grep on diff lines)
- Baseline-aware quality gates (only flag NEW failures)
- Multi-language tool detection (Python, Node, Rust, Go)
- Independent reviewer subagent with fail-closed JSON verdict
- Auto-fix loop with separate fixer agent (max 2 attempts)
- Git checkpoint and [verified] commit convention

Deletes: skills/software-development/code-review/ (absorbed)
Closes: NousResearch#406 (independent code verification)
olympus-terminal pushed a commit to olympus-terminal/hermes-agent that referenced this pull request May 16, 2026
…Research#4854)

* chore: release v0.7.0 (2026.4.3)

168 merged PRs, 223 commits, 46 resolved issues, 40+ contributors.

Highlights: pluggable memory providers, credential pools, Camofox browser,
inline diff previews, API server session continuity, ACP MCP registration,
gateway hardening, secret exfiltration blocking.

* refactor(skills): consolidate code-review + verify-code-changes into requesting-code-review

Merge the passive code-review checklist and the automated verification
pipeline (from PR NousResearch#4459 by @MorAlekss) into a single requesting-code-review
skill. This eliminates model confusion between three overlapping skills.

Now includes:
- Static security scan (grep on diff lines)
- Baseline-aware quality gates (only flag NEW failures)
- Multi-language tool detection (Python, Node, Rust, Go)
- Independent reviewer subagent with fail-closed JSON verdict
- Auto-fix loop with separate fixer agent (max 2 attempts)
- Git checkpoint and [verified] commit convention

Deletes: skills/software-development/code-review/ (absorbed)
Closes: NousResearch#406 (independent code verification)
gweeteve pushed a commit to gweeteve/hermes-agent that referenced this pull request Jun 2, 2026
…Research#4854)

* chore: release v0.7.0 (2026.4.3)

168 merged PRs, 223 commits, 46 resolved issues, 40+ contributors.

Highlights: pluggable memory providers, credential pools, Camofox browser,
inline diff previews, API server session continuity, ACP MCP registration,
gateway hardening, secret exfiltration blocking.

* refactor(skills): consolidate code-review + verify-code-changes into requesting-code-review

Merge the passive code-review checklist and the automated verification
pipeline (from PR NousResearch#4459 by @MorAlekss) into a single requesting-code-review
skill. This eliminates model confusion between three overlapping skills.

Now includes:
- Static security scan (grep on diff lines)
- Baseline-aware quality gates (only flag NEW failures)
- Multi-language tool detection (Python, Node, Rust, Go)
- Independent reviewer subagent with fail-closed JSON verdict
- Auto-fix loop with separate fixer agent (max 2 attempts)
- Git checkpoint and [verified] commit convention

Deletes: skills/software-development/code-review/ (absorbed)
Closes: NousResearch#406 (independent code verification)
Egavasyug pushed a commit to Egavasyug/hermes-agent that referenced this pull request Jun 10, 2026
…Research#4854)

* chore: release v0.7.0 (2026.4.3)

168 merged PRs, 223 commits, 46 resolved issues, 40+ contributors.

Highlights: pluggable memory providers, credential pools, Camofox browser,
inline diff previews, API server session continuity, ACP MCP registration,
gateway hardening, secret exfiltration blocking.

* refactor(skills): consolidate code-review + verify-code-changes into requesting-code-review

Merge the passive code-review checklist and the automated verification
pipeline (from PR NousResearch#4459 by @MorAlekss) into a single requesting-code-review
skill. This eliminates model confusion between three overlapping skills.

Now includes:
- Static security scan (grep on diff lines)
- Baseline-aware quality gates (only flag NEW failures)
- Multi-language tool detection (Python, Node, Rust, Go)
- Independent reviewer subagent with fail-closed JSON verdict
- Auto-fix loop with separate fixer agent (max 2 attempts)
- Git checkpoint and [verified] commit convention

Deletes: skills/software-development/code-review/ (absorbed)
Closes: NousResearch#406 (independent code verification)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Feature: Independent Code Verification & Quality Gates — Fail-Closed Review, Baseline Regression Detection, and Auto-Fix Loop (inspired by Nightwire)

1 participant