Add design specification, license, and project setup by Aureliolo · Pull Request #2 · Aureliolo/synthorg

Aureliolo · 2026-02-27T09:48:44Z

Summary

Design Specification (DESIGN_SPEC.md) — comprehensive 18-section high-level design for the AI Company framework covering agent system, company structure, communication architecture, task engine, memory, HR, model providers, budget management, tools, security, human interaction, templates, technical architecture, research/prior art, open questions, and backlog
BSL 1.1 License — Business Source License with non-commercial use grant, converting to Apache 2.0 on February 27, 2030
README — updated with project concept, planned features, tech stack, and documentation links
Claude Code skill — aurelio-review-pr PR review pipeline for future use

All technology choices in the design spec are marked as candidates/TBD pending further research. No final decisions on frameworks, libraries, or specific models.

Test plan

Review DESIGN_SPEC.md for completeness and internal consistency
Verify LICENSE parameters (change date, use grant, change license)
Confirm README accurately reflects current project status
Validate all 18 sections are properly cross-referenced in table of contents

🤖 Generated with Claude Code

Comprehensive design spec covering: - Agent identity system with roles, personalities, skills, seniority - Company structure templates (solo founder to full enterprise) - Communication architecture (event-driven bus, hierarchical, meetings, hybrid) - Task/workflow engine with multiple execution patterns - Memory system (working, episodic, semantic, procedural, social) - Multi-provider LLM layer via LiteLLM (Claude, OpenRouter, Ollama) - Budget management with CFO agent and cost optimization - Tool/capability system with progressive trust - Security operations agent and configurable autonomy levels - API-first architecture (FastAPI + WebSocket) with web UI - Template system and company builder - Research analysis of MetaGPT, ChatDev, CrewAI, AutoGen, LangGraph - Build-from-scratch recommendation leveraging LiteLLM, Mem0, MCP, A2A - Open questions, risks, backlog, and scaling path

Business Source License 1.1 with parameters: - Non-commercial use only (personal, education, research, evaluation) - Commercial/production use requires separate license - Converts to Apache 2.0 after 4 years per version

- Fix LICENSE Change Date to explicit "February 27, 2030" - Extract HR into its own section (Section 8), renumber all sections - Reconcile budget hierarchy to include QA department - Correct A2A/MCP governance attribution to Linux Foundation - Keep SecOps agent active in locked autonomy mode for audit logging - Consolidate terminology on "Agent" (remove "Employee" as separate concept) - Add communication loop prevention mechanism (Section 5.5) - Mark model pricing and provider configs as illustrative examples - Soften specific technology commitments to "candidates - TBD after research" - Add language spec to workflow diagram code blocks - Add aurelio-review-pr skill for Claude Code

coderabbitai · 2026-02-27T09:48:54Z

Caution

Review failed

The pull request is closed.

ℹ️ Recent review info

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between eeaec53 and dfa99f3.

📒 Files selected for processing (2)

.claude/skills/aurelio-review-pr/skill.md
DESIGN_SPEC.md

📝 Walkthrough

Summary by CodeRabbit

Documentation
- Added a comprehensive design spec describing architecture, agent framework, communication, persistence, governance, and implementation guidance.
- Added a detailed PR review workflow document outlining a multi-phase review, feedback consolidation, and approval/implementation steps.
- Expanded README with project concept, planned features, status, tech stack, and docs references.
Chores
- Added Business Source License 1.1; production/commercial use requires a separate commercial license.

Walkthrough

Adds foundational documentation and a PR review workflow: a 10-phase PR review pipeline spec, a comprehensive design specification for multi-agent orchestration, a Business Source License 1.1, and an expanded README.

Changes

Cohort / File(s)	Summary
Workflow Documentation `.claude/skills/aurelio-review-pr/skill.md`	New markdown describing a 10-phase PR review pipeline: identify PR/branch, fetch issue context, run local review agents in parallel, fetch external reviewer feedback, consolidate/triage with deduplication/conflict detection, AskUserQuestion approval step, implement approved fixes grouped by file, commit/push safeguards, post-push verification, and final summary. Specifies control flow rules, retry semantics, error signaling, and user prompts.
Design & Architecture `DESIGN_SPEC.md`	New comprehensive design spec for a config-driven autonomous-agent "AI Company" framework: architecture, agent system, company structure, communication patterns, workflow engine, memory/persistence, HR/security/approval, model providers, cost/budgeting, templates, technical stack candidates, research notes, risks, and backlog.
Project Foundation `LICENSE`, `README.md`	Adds Business Source License 1.1 (Change Date Feb 27, 2030 → Apache 2.0) and expands README with formal project title, concept, planned features, status, tech stack, and documentation references.

Sequence Diagram(s)

mermaid
sequenceDiagram
participant User
participant LocalAgents as Local Review Agents
participant GH as GitHub API
participant Ext as External Reviewers
participant Repo
User->>GH: Identify PR / branch
GH-->>User: Return PR & issue context
User->>LocalAgents: Run local review agents (parallel)
LocalAgents-->>User: Local findings
User->>GH: Fetch external reviewer feedback (retry semantics)
GH-->>Ext: Request external comments
Ext-->>GH: External feedback (may include outside-diff comments)
GH-->>User: External feedback delivered
User->>User: Consolidate & triage feedback (dedupe, detect conflicts)
User->>User: AskUserQuestion (approve all / selective)
User->>LocalAgents: Implement approved fixes (grouped by file)
LocalAgents->>Repo: Create commits (lint/tests considerations)
Repo-->>User: Push/commit result (safeguards)
User->>GH: Verify external reviewer status post-push
GH-->>User: Final summary & report

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Possibly related PRs

Add design specification, license, and project setup #2: Modifies the same new files (DESIGN_SPEC.md, LICENSE, README.md, .claude/skills/aurelio-review-pr/skill.md) with overlapping content and intent.

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately summarizes the main changes: adding a design specification, license, and project setup files to establish the project foundation.
Description check	✅ Passed	The description is well-structured and directly related to the changeset, covering all major file additions (DESIGN_SPEC.md, LICENSE, README updates) and the PR review skill with clear context.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment
Commit unit tests in branch feat/design-spec

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

gemini-code-assist · 2026-02-27T09:49:06Z

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request establishes the foundational elements for the "AI Company" project by introducing its core design principles, licensing, and initial development tooling. It provides a detailed high-level design specification outlining the architecture and components of the AI agent orchestration framework, defines the project's open-source license, updates the main project README with key information, and adds a sophisticated PR review automation skill.

Highlights

Design Specification: A comprehensive 18-section high-level design for the AI Company framework has been added, covering agent system, company structure, communication, task engine, memory, HR, model providers, budget, tools, security, human interaction, templates, technical architecture, research, open questions, and backlog.
Licensing: The project now includes a Business Source License (BSL 1.1) with a non-commercial use grant, which will convert to Apache 2.0 on February 27, 2030.
Project Setup & Documentation: The README has been updated to include the project concept, planned features, tech stack, and links to documentation, reflecting the current project status.
Claude Code Skill: A new Claude Code skill, 'aurelio-review-pr', has been introduced to define a full PR review pipeline for future use, integrating local agents, external feedback, triage, and fix implementation.

Changelog

.claude/skills/aurelio-review-pr/skill.md
- Added a new Claude skill for a comprehensive PR review pipeline.
- Defined 10 phases for the PR review process, from finding the PR to implementing fixes and verifying external reviewer status.
- Specified tools allowed for the skill, including Bash, Read, Edit, Write, Grep, Glob, Task, and AskUserQuestion.
- Included detailed logic for issue linkage, context fetching, parallel local agent execution, external feedback collection, and triage.
- Outlined rules for fix implementation, commit procedures, and loop prevention.
DESIGN_SPEC.md
- Added a detailed 18-section high-level design specification for the AI Company framework.
- Included sections on vision, core concepts, agent system, company structure, communication, task engine, memory, HR, model providers, cost management, tools, security, human interaction, templates, technical architecture, research, open questions, and future vision.
- Provided detailed YAML/JSON examples for agent identity, department configuration, communication settings, task definition, memory levels, budget controls, tool access, autonomy levels, and company templates.
- Compared the proposed architecture with existing AI agent frameworks and justified a build-from-scratch approach leveraging key libraries.
LICENSE
- Added the Business Source License 1.1.
- Specified "Aurelio" as the Licensor and "AI Company" as the Licensed Work.
- Included an Additional Use Grant for non-production use (personal, educational, research, evaluation).
- Set the Change Date to February 27, 2030, and the Change License to Apache License, Version 2.0.
README.md
- Updated the project title to "AI Company".
- Added a concept section explaining the framework for orchestrating autonomous AI agents.
- Listed key planned features such as configurable company structure, deep agent identity, multi-provider support, smart cost management, configurable autonomy, persistent memory, HR system, real tool access, API-first design, and templates.
- Updated the status to "Design phase" and linked to DESIGN_SPEC.md.
- Included a planned tech stack section with Python, FastAPI, LiteLLM, Mem0, MCP, Vue 3, and SQLite/PostgreSQL.
- Added a documentation section linking to the Design Specification.

Activity

No human activity has been recorded on this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request introduces foundational documents for the project, including a detailed design specification for an AI Company framework, a BSL 1.1 license, and an updated project README. While I've noted minor inconsistencies within the design specification and the aurelio-review-pr skill definition, a critical concern is that the aurelio-review-pr skill contains instructions that could lead to security vulnerabilities. Specifically, it lacks explicit validation for untrusted input extracted from PR bodies, potentially leading to command injection, and does not include safeguards against prompt injection when passing GitHub issue context to review agents. Addressing these inconsistencies and, more importantly, refining the skill definition to mitigate these security risks is crucial for clarity and project security.

gemini-code-assist · 2026-02-27T09:51:16Z

.claude/skills/aurelio-review-pr/skill.md

+**Fetch issue context.** If an issue reference was found (regardless of warnings), fetch the issue for review context. If the PR body used a full URL (`https://github.com/OWNER/REPO/issues/N`), extract both `OWNER/REPO` and `N` and pass `--repo OWNER/REPO` to query the correct repository:
+
+```bash
+gh issue view N --repo OWNER/REPO --json title,body,labels,comments --jq '{title: .title, body: .body, labels: [.labels[].name], comments: [.comments[] | {author: .author.login, body: .body}]}'


The skill instructions direct the agent to extract OWNER/REPO and N from a URL provided in the PR body and use them in a shell command (gh issue view N --repo OWNER/REPO). Since the PR body is untrusted input, an attacker could provide a malicious URL (e.g., https://github.com/owner/repo;injection/issues/1) to perform command injection. The instructions should explicitly require the agent to validate that OWNER/REPO matches the expected repository format and that N is a numeric value before using them in any shell command.

gemini-code-assist · 2026-02-27T09:51:16Z

.claude/skills/aurelio-review-pr/skill.md

+| **comment-analyzer** | Comments or docstrings changed | `pr-review-toolkit:comment-analyzer` |
+| **type-design-analyzer** | Type annotations or classes added/modified | `pr-review-toolkit:type-design-analyzer` |
+
+Each agent should receive the list of changed files and focus on reviewing them. **If issue context was collected in Phase 2, include the issue title, body, and key comments in each agent's prompt** so they can verify the PR addresses the issue's requirements.


The skill instructions specify that untrusted data from GitHub (issue title, body, and comments) should be included in the prompts for review agents. This data is not sanitized or wrapped in delimiters, making the agents vulnerable to prompt injection attacks. An attacker could use malicious issue comments to manipulate the behavior of the review agents. The instructions should be updated to require the use of clear delimiters (e.g., XML tags) and to explicitly instruct the sub-agents to treat this content as untrusted data.

gemini-code-assist · 2026-02-27T09:51:16Z

.claude/skills/aurelio-review-pr/skill.md

+   ```bash
+   gh api repos/OWNER/REPO/pulls/NUMBER/comments --paginate
+   ```
+   Extract: author, file path, line number, body, subject_type.


In the list of fields to extract for inline review comments, subject_type is mentioned. However, according to the GitHub API documentation, this field is not present in the response for listing PR review comments (/repos/OWNER/REPO/pulls/NUMBER/comments). This field is associated with commit comments. To ensure the implementation is based on the correct API schema, I suggest removing subject_type from this list.

gemini-code-assist · 2026-02-27T09:51:17Z

DESIGN_SPEC.md

+```yaml
+memory:
+  level: "full"                 # none, session, project, full
+  backend: "sqlite"             # sqlite, postgresql, mem0, file


There appears to be an inconsistency in how Mem0 is defined as part of the memory architecture.

Here in Section 7.3, mem0 is listed as a value for the backend configuration, suggesting it's a standalone storage option.

However, Section 15.2 describes the stack as Mem0 + SQLite and states Mem0 is for semantic/episodic memory while SQLite is for structured data. This implies Mem0 is a layer that works with a database, not as an alternative to it.

To avoid confusion during implementation, it would be helpful to clarify the relationship. Is Mem0 a memory system that can be configured with different storage backends (like SQLite), or is it a backend itself? The configuration schema should reflect this relationship clearly.

gemini-code-assist · 2026-02-27T09:51:17Z

DESIGN_SPEC.md

+    - role_level: "c_suite"
+      preferred_model: "opus"
+      fallback: "sonnet"
+    - role_level: "senior"
+      preferred_model: "sonnet"
+      fallback: "haiku"
+    - role_level: "junior"
+      preferred_model: "haiku"
+      fallback: "local-small"


There's an inconsistency in the casing of agent seniority levels across the design document.

Section 3.1 (level) and 3.2 (Level) use capitalized values (e.g., Senior, C-Suite).

The routing rules here in Section 9.4 use lowercase values (e.g., c_suite, senior, junior).

This could lead to bugs where routing rules don't match agent levels. It would be beneficial to standardize on a single casing convention (e.g., all lowercase) for these values throughout the specification.

Copilot

Pull request overview

This PR establishes the foundational documentation and legal framework for the AI Company project, a framework for orchestrating autonomous AI agents within a virtual company structure. The PR transitions the repository from a minimal placeholder to a fully specified design-phase project with clear licensing, technical vision, and development tooling.

Changes:

Added comprehensive 18-section design specification covering agent system, company structure, communication, tasks, memory, HR, providers, budget, tools, security, human interaction, templates, and technical architecture
Implemented Business Source License 1.1 with 4-year conversion to Apache 2.0
Updated README with project concept, key features, tech stack, and documentation links
Added Claude Code PR review skill for automated review workflow

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.

File	Description
DESIGN_SPEC.md	Comprehensive high-level design covering all major system components, with technology choices marked as candidates pending research
LICENSE	Business Source License 1.1 with non-production use grant, converting to Apache 2.0 on February 27, 2030
README.md	Project overview with concept description, planned features, tech stack, and documentation links
.claude/skills/aurelio-review-pr/skill.md	PR review pipeline skill with 10-phase workflow for local agents, external feedback, triage, and fixes

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Aureliolo · 2026-02-27T12:02:57Z

@coderabbitai review

coderabbitai · 2026-02-27T12:03:07Z

✅ Actions performed

Review triggered.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

coderabbitai

Actionable comments posted: 2

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In @.claude/skills/aurelio-review-pr/skill.md:
- Around line 32-34: Several fenced code blocks (e.g., the block containing "gh
repo view --json nameWithOwner -q .nameWithOwner") lack surrounding blank lines
and nearby sentences lack terminal punctuation; update each affected fenced
block by inserting a blank line before and after the triple-backtick fence and
ensure the sentence immediately preceding or following each fence ends with
proper punctuation (period, question mark, or exclamation). Apply the same fixes
to the other similar fences called out (the blocks around the other listed
snippets) so all fenced code blocks have blank lines around them and all nearby
sentences end with punctuation for MD lint stability.

In `@DESIGN_SPEC.md`:
- Around line 76-97: The fenced block showing the company org tree (the
triple-backtick block starting with "Company ├── Departments[] ...") and
multiple other fenced blocks lack a language identifier and several headings
(e.g., "#### C-Suite / Executive") are missing surrounding blank lines; to fix,
add an appropriate fence language token (e.g., ```text, ```yaml, ```json, or
```bash) to every fenced code block such as the "Company" tree and the other
blocks listed, and ensure each heading has a blank line above and below it (for
example insert a blank line before "#### C-Suite / Executive" and a blank line
after the heading), applying this pattern across the noted ranges (lines with
MD040/MD022 warnings) so markdownlint MD040 and MD022 are resolved.

ℹ️ Review info

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 6e040da and eeaec53.

📒 Files selected for processing (4)

.claude/skills/aurelio-review-pr/skill.md
DESIGN_SPEC.md
LICENSE
README.md

📜 Review details

🧰 Additional context used

🧠 Learnings (7)

📚 Learning: 2026-01-24T16:33:29.354Z

Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: .github/copilot-instructions.md:0-0
Timestamp: 2026-01-24T16:33:29.354Z
Learning: Applies to README.md : Update README.md for significant feature changes

Applied to files:

README.md

📚 Learning: 2026-02-26T17:43:50.902Z

Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-02-26T17:43:50.902Z
Learning: When making changes that affect architecture, services, key files, settings, or workflows, update the relevant sections of existing documentation (CLAUDE.md, README.md, etc.) to reflect those changes.

Applied to files:

.claude/skills/aurelio-review-pr/skill.md

📚 Learning: 2026-01-24T09:54:45.426Z

Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: .github/instructions/agents.instructions.md:0-0
Timestamp: 2026-01-24T09:54:45.426Z
Learning: Applies to agents/*.py : Use structured prompts with clear instructions including role definition, constraints, output format (JSON when needed), and context from story state

Applied to files:

.claude/skills/aurelio-review-pr/skill.md

📚 Learning: 2026-02-26T17:43:50.902Z

Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-02-26T17:43:50.902Z
Learning: Never defer work—do not suggest "this can be done later" or "consider for a future PR". Complete all requested changes fully.

Applied to files:

.claude/skills/aurelio-review-pr/skill.md

📚 Learning: 2026-01-26T08:59:32.818Z

Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: .github/copilot-instructions.md:0-0
Timestamp: 2026-01-26T08:59:32.818Z
Learning: Never defer work. Do not suggest 'this can be done later' or 'consider for a future PR'. Complete all requested changes fully.

Applied to files:

.claude/skills/aurelio-review-pr/skill.md

📚 Learning: 2026-01-26T08:59:32.818Z

Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: .github/copilot-instructions.md:0-0
Timestamp: 2026-01-26T08:59:32.818Z
Learning: After every push, you MUST check that CI passes. If CI fails, fix the issue immediately and push again until all checks are green. Never walk away from a failing CI pipeline.

Applied to files:

.claude/skills/aurelio-review-pr/skill.md

📚 Learning: 2026-02-26T17:43:50.902Z

Learnt from: CR
Repo: Aureliolo/story-factory PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-02-26T17:43:50.902Z
Learning: Always create a PR for issue work. When implementing changes for a GitHub issue, create a branch and open a pull request. Do not wait to be asked.

Applied to files:

.claude/skills/aurelio-review-pr/skill.md

🪛 LanguageTool

DESIGN_SPEC.md

[typographical] ~1-~1: To join two clauses or introduce examples, consider using an em dash.
Context: # AI Company - High-Level Design Specification > A fra...

(DASH_RULE)

[typographical] ~193-~193: To join two clauses or introduce examples, consider using an em dash.
Context: ...### Engineering - Software Architect - System design, technology decisions, pat...

(DASH_RULE)

[typographical] ~194-~194: To join two clauses or introduce examples, consider using an em dash.
Context: ...Frontend Developer** (Junior/Mid/Senior) - UI implementation, components, state man...

(DASH_RULE)

[typographical] ~195-~195: To join two clauses or introduce examples, consider using an em dash.
Context: ...Backend Developer* (Junior/Mid/Senior) - APIs, business logic, databases - **Full...

(DASH_RULE)

[typographical] ~196-~196: To join two clauses or introduce examples, consider using an em dash.
Context: ...ll-Stack Developer** (Junior/Mid/Senior) - End-to-end implementation - **DevOps/SRE...

(DASH_RULE)

[typographical] ~197-~197: To join two clauses or introduce examples, consider using an em dash.
Context: ...implementation - DevOps/SRE Engineer - Infrastructure, CI/CD, monitoring, deplo...

(DASH_RULE)

[typographical] ~198-~198: To join two clauses or introduce examples, consider using an em dash.
Context: ...ring, deployment - Database Engineer - Schema design, query optimization, migra...

(DASH_RULE)

[typographical] ~199-~199: To join two clauses or introduce examples, consider using an em dash.
Context: ...tion, migrations - Security Engineer - Security audits, vulnerability assessmen...

(DASH_RULE)

[style] ~383-~383: Consider using a different adjective to strengthen your wording.
Context: ...#### Pattern 4: Hybrid (Recommended for Full Company) Combines all three: - **Messa...

(FULL_ENTIRE)

[style] ~654-~654: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...onality would complement the team? - What model/provider fits the budget? 3. Cand...

(ENGLISH_WORD_REPEAT_BEGINNING_RULE)

[style] ~664-~664: You have used the passive voice repeatedly in nearby sentences. To make your writing clearer and easier to read, consider using active voice.
Context: ... 3. Active tasks are reassigned 4. Team is notified ### 8.3 Performance Tracking ```yaml ...

(REP_PASSIVE_VOICE)

[grammar] ~682-~682: Use a hyphen to join words.
Context: ...ce: - Promotion criteria: sustained high quality scores, task complexity handled,...

(QB_NEW_EN_HYPHEN)

[typographical] ~1377-~1377: In American English, use a period after an abbreviation.
Context: ...pid prototyping | ### 16.2 What Exists vs What We Need | Feature | MetaGPT | Cha...

(MISSING_PERIOD_AFTER_ABBREVIATION)

(DASH_RULE)

(DASH_RULE)

(DASH_RULE)

(DASH_RULE)

(DASH_RULE)

[typographical] ~1390-~1390: To join two clauses or introduce examples, consider using an em dash.
Context: ...rs | Partial | Partial | Partial | **Yes - unified abstraction (LiteLLM candidate)*...

(DASH_RULE)

[typographical] ~1391-~1391: To join two clauses or introduce examples, consider using an em dash.
Context: ...racking per agent | No | No | No | Yes - full budget system | | Progressive tru...

(DASH_RULE)

[typographical] ~1398-~1398: In American English, use a period after an abbreviation.
Context: ...Planned (backlog) | ### 16.3 Build vs Fork Decision **Recommendation: Build ...

(MISSING_PERIOD_AFTER_ABBREVIATION)

[style] ~1432-~1432: Consider using the typographical ellipsis character here instead.
Context: ... | Agent A asks Agent B who asks Agent A... | | 8 | Optimal message bus for local-f...

(ELLIPSIS)

(MISSING_PERIOD_AFTER_ABBREVIATION)

(MISSING_PERIOD_AFTER_ABBREVIATION)

(MISSING_PERIOD_AFTER_ABBREVIATION)

[typographical] ~1434-~1434: In American English, use a period after an abbreviation.
Context: ...h | Sandboxing strategy, Docker vs WASM vs subprocess | | 10 | What's the minimum ...

(MISSING_PERIOD_AFTER_ABBREVIATION)

[style] ~1509-~1509: To make your text as clear as possible to all readers, do not use this foreign term. Possible alternatives are ‘in fact’ or ‘in reality’.
Context: ...rop | | OpenAI API format | OpenAI (de facto standard) | LLM API interface | Via pro...

(DE_FACTO)

[style] ~1509-~1509: This phrase is redundant (‘I’ stands for ‘interface’). Use simply “API”.
Context: ...at** | OpenAI (de facto standard) | LLM API interface | Via provider abstraction layer (LiteL...

(ACRONYM_TAUTOLOGY)

[typographical] ~1513-~1513: To join two clauses or introduce examples, consider using an em dash.
Context: ...s://github.com/FoundationAgents/MetaGPT) - Multi-agent SOP framework (64.5k stars) ...

(DASH_RULE)

[typographical] ~1514-~1514: To join two clauses or introduce examples, consider using an em dash.
Context: ...2.0](https://github.com/openbmb/ChatDev) - Zero-code multi-agent platform (31.2k st...

(DASH_RULE)

[typographical] ~1515-~1515: To join two clauses or introduce examples, consider using an em dash.
Context: ...AI](https://github.com/crewAIInc/crewAI) - Role-based agent collaboration framework...

(DASH_RULE)

[typographical] ~1516-~1516: To join two clauses or introduce examples, consider using an em dash.
Context: ...n](https://github.com/microsoft/autogen) - Microsoft async multi-agent framework - ...

(DASH_RULE)

[typographical] ~1517-~1517: To join two clauses or introduce examples, consider using an em dash.
Context: ...LLM](https://github.com/BerriAI/litellm) - Unified LLM API gateway (100+ providers)...

(DASH_RULE)

[typographical] ~1518-~1518: To join two clauses or introduce examples, consider using an em dash.
Context: ...- Mem0 - Universal memory layer for AI agents - [...

(DASH_RULE)

[typographical] ~1519-~1519: To join two clauses or introduce examples, consider using an em dash.
Context: ...ocol](https://github.com/a2aproject/A2A) - Agent-to-Agent protocol (Linux Foundatio...

(DASH_RULE)

[typographical] ~1520-~1520: To join two clauses or introduce examples, consider using an em dash.
Context: ...extprotocol.io/specification/2025-11-25) - Model Context Protocol - [Langfuse Agent...

(DASH_RULE)

[typographical] ~1521-~1521: To join two clauses or introduce examples, consider using an em dash.
Context: ...com/blog/2025-03-19-ai-agent-comparison) - Framework comparison - [Confluent Event-...

(DASH_RULE)

[typographical] ~1522-~1522: To join two clauses or introduce examples, consider using an em dash.
Context: .../blog/event-driven-multi-agent-systems/) - Multi-agent architecture patterns - [Mic...

(DASH_RULE)

[typographical] ~1523-~1523: To join two clauses or introduce examples, consider using an em dash.
Context: ....io/multi-agent-reference-architecture/) - Enterprise patterns - [OpenRouter](https...

(DASH_RULE)

[typographical] ~1524-~1524: To join two clauses or introduce examples, consider using an em dash.
Context: ...s - OpenRouter - Multi-model API gateway

(DASH_RULE)

README.md

[typographical] ~11-~11: To join two clauses or introduce examples, consider using an em dash.
Context: ...s (Planned) - Any Company Structure - From a 2-person startup to a 50+ enterpr...

(DASH_RULE)

[typographical] ~12-~12: To join two clauses or introduce examples, consider using an em dash.
Context: ...nfig/templates - Deep Agent Identity - Names, personalities, skills, seniority ...

(DASH_RULE)

[typographical] ~13-~13: To join two clauses or introduce examples, consider using an em dash.
Context: ...erformance tracking - Multi-Provider - Anthropic Claude, OpenRouter (400+ model...

(DASH_RULE)

[typographical] ~14-~14: To join two clauses or introduce examples, consider using an em dash.
Context: ... via LiteLLM - Smart Cost Management - Per-agent budget tracking, auto model ro...

(DASH_RULE)

[typographical] ~15-~15: To join two clauses or introduce examples, consider using an em dash.
Context: ...optimization - Configurable Autonomy - From fully autonomous to human-approves-...

(DASH_RULE)

[typographical] ~16-~16: To join two clauses or introduce examples, consider using an em dash.
Context: ...agent in between - Persistent Memory - Agents remember past decisions, code, re...

(DASH_RULE)

[typographical] ~17-~17: To join two clauses or introduce examples, consider using an em dash.
Context: ...relationships (via Mem0) - HR System - Hire, fire, promote agents. HR agent ana...

(DASH_RULE)

[typographical] ~18-~18: To join two clauses or introduce examples, consider using an em dash.
Context: ...tem, git, code execution, web, databases - role-based and sandboxed - API-First...

(DASH_RULE)

[grammar] ~20-~20: Please add a punctuation mark at the end of paragraph.
Context: ...built company templates and interactive builder ## Status Design phase. See [DESI...

(PUNCTUATION_PARAGRAPH_END)

[typographical] ~37-~37: To join two clauses or introduce examples, consider using an em dash.
Context: ...- Design Specification - Full high-level design

(DASH_RULE)

.claude/skills/aurelio-review-pr/skill.md

[style] ~107-~107: The phrase ‘Look for patterns’ is used very frequently. Consider using a less frequent alternative to set your writing apart from others.
Context: ... lines are outside the PR's diff range. Look for patterns like "Outside diff range comments (N)" ...

(LOOK_FOR_STYLE)

[style] ~121-~121: This word has been used in one of the immediately preceding sentences. Using a synonym could make your text more interesting to read, unless the repetition is intentional.
Context: ...tionable items, not just summaries). Important: Use gh api with --jq for filteri...

(EN_REPEATEDWORDS_IMPORTANT)

[style] ~123-~123: This word has been used in one of the immediately preceding sentences. Using a synonym could make your text more interesting to read, unless the repetition is intentional.
Context: ...omplex Python scripts to parse JSON. Important: When review bodies are large (e.g. C...

(EN_REPEATEDWORDS_IMPORTANT)

[grammar] ~139-~139: Please add a punctuation mark at the end of paragraph.
Context: ...heck against CLAUDE.md rules and actual code Deduplication: If multiple sources...

(PUNCTUATION_PARAGRAPH_END)

[grammar] ~172-~172: Please add a punctuation mark at the end of paragraph.
Context: ... rely on pre-push hooks and CI for full coverage ## Phase 8: Commit and push After all...

(PUNCTUATION_PARAGRAPH_END)

[style] ~181-~181: Consider using a different verb for a more formal wording.
Context: .... If commit or push fails due to hooks, fix the actual issue and create a NEW commi...

(FIX_RESOLVE)

🪛 markdownlint-cli2 (0.21.0)

DESIGN_SPEC.md

[warning] 76-76: Fenced code blocks should have a language specified

(MD040, fenced-code-language)

[warning] 178-178: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below