Harness Agent Team Designer
revfactory/harness
Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.
Run a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs.
Install Analyze Codebase
$ npx skills add divar-ir/ai-doc-gen --skill analyze-codebase -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install divar-ir/ai-doc-gen analyze-codebase --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/divar-ir/ai-doc-gen.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/analyze-codebase .claude/skills/analyze-codebase && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "analyze-codebase" agent skill from https://github.com/divar-ir/ai-doc-gen/tree/main/skills/analyze-codebase into .claude/skills/analyze-codebase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-codebase", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/divar-ir/ai-doc-gen/tree/main/skills/analyze-codebaseType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add divar-ir/ai-doc-gen --skill analyze-codebase -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install divar-ir/ai-doc-gen analyze-codebase --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/divar-ir/ai-doc-gen.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/analyze-codebase .agents/skills/analyze-codebase && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "analyze-codebase" agent skill from https://github.com/divar-ir/ai-doc-gen/tree/main/skills/analyze-codebase into .agents/skills/analyze-codebase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-codebase", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add divar-ir/ai-doc-gen --skill analyze-codebase -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install divar-ir/ai-doc-gen analyze-codebase --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/divar-ir/ai-doc-gen.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/analyze-codebase .cursor/skills/analyze-codebase && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "analyze-codebase" agent skill from https://github.com/divar-ir/ai-doc-gen/tree/main/skills/analyze-codebase into .cursor/skills/analyze-codebase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-codebase", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/divar-ir/ai-doc-gen.git --path skills/analyze-codebase--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add divar-ir/ai-doc-gen --skill analyze-codebase -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install divar-ir/ai-doc-gen analyze-codebase --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/divar-ir/ai-doc-gen.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/analyze-codebase .gemini/skills/analyze-codebase && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "analyze-codebase" agent skill from https://github.com/divar-ir/ai-doc-gen/tree/main/skills/analyze-codebase into .gemini/skills/analyze-codebase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-codebase", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install divar-ir/ai-doc-gen analyze-codebaseInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add divar-ir/ai-doc-gen --skill analyze-codebase -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/divar-ir/ai-doc-gen.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/analyze-codebase .github/skills/analyze-codebase && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "analyze-codebase" agent skill from https://github.com/divar-ir/ai-doc-gen/tree/main/skills/analyze-codebase into .github/skills/analyze-codebase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-codebase", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add divar-ir/ai-doc-gen --skill analyze-codebase -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install divar-ir/ai-doc-gen analyze-codebase --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/divar-ir/ai-doc-gen.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/analyze-codebase .opencode/skills/analyze-codebase && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "analyze-codebase" agent skill from https://github.com/divar-ir/ai-doc-gen/tree/main/skills/analyze-codebase into .opencode/skills/analyze-codebase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-codebase", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
analyze-codebase- GitHub stars
- 765
- Token cost
- ~899 tokens
- SKILL.md length
- 396 words
- Files
- 6 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
Run a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs.
- Works in 3 steps: Determine scope → Run the analyzers in parallel → Verify and report
- The user asks to analyze a repository
- SKILL.md covers Workflow and Notes
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Analyze Codebase is an agent skill from divar-ir/ai-doc-gen. Run a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs. Use whenever the user asks to analyze a repository, generate codebase analysis, understand an unfamiliar codebase in depth, or before generating documentation (README, CLAUDE.md, AGENTS.md) so the generators have analysis data to work from. Also use when the user mentions ".ai/docs", "ai analysis", or wants a structured architectural map of a…
Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/api-analyzer.md`, `references/data-flow-analyzer.md` and `references/dependency-analyzer.md`).
It sits in Agent Workflows, covering Agent instruction files, Codebase onboarding and Multi-agent orchestration. It works with Pydantic AI and Python. The repository describes itself as: AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple… The licence is MIT.
When your agent uses it
- The user asks to analyze a repository
- Generate codebase analysis
- Understand an unfamiliar codebase in depth
- Before generating documentation (README
Example prompts
- “.ai/docs”
- “ai analysis”
- “/analyze-codebase”
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit bd3aba7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Analyze Codebase loads about 899 tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 135 tokens; SKILL.md has 396 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from divar-ir/ai-doc-gen at commit bd3aba7, republished under its MIT licence (© divar-ir). 396 words, ~899 tokens.
Download SKILL.mdSave it as
.claude/skills/analyze-codebase/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- analyze-codebase
- description
- Run a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs. Use whenever the user asks to analyze a repository, generate codebase analysis, understand an unfamiliar codebase in depth, or before generating documentation (README, CLAUDE.md, AGENTS.md) so the generators have analysis data to work from. Also use when the user mentions ".ai/docs", "ai analysis", or wants a structured architectural map of a project.
Analyze Codebase
Produce five AI-readable analysis documents by running specialized analyzers in parallel, each writing to .ai/docs/ in the target repository. These documents are the input for the generate-readme and generate-ai-rules skills, and are valuable on their own as machine-readable architecture maps.
Workflow
1. Determine scope
- Target repository: the current working directory unless the user names another path.
- Which analyses to run: all five by default. The user may exclude some (e.g., "skip the data flow analysis"). For projects with no meaningful API surface or request handling (pure libraries, simple scripts), suggest skipping the API and request-flow analyzers, but let the user decide.
| Analyzer | Reference file | Output file |
|---|---|---|
| Structure | references/structure-analyzer.md | .ai/docs/structure_analysis.md |
| Dependencies | references/dependency-analyzer.md | .ai/docs/dependency_analysis.md |
| Data flow | references/data-flow-analyzer.md | .ai/docs/data_flow_analysis.md |
| Request flow | references/request-flow-analyzer.md | .ai/docs/request_flow_analysis.md |
| API | references/api-analyzer.md | .ai/docs/api_analysis.md |
2. Run the analyzers in parallel
Create .ai/docs/ in the target repo if it doesn't exist. Then spawn one subagent per selected analyzer, all in a single message so they run concurrently. Each subagent prompt should say:
Read the instructions at
<absolute path to this skill's references/<analyzer>.md>and follow them exactly for the repository at<absolute repo path>. Explore the codebase with your file tools as needed. Write your complete analysis to<absolute repo path>/.ai/docs/<output file>, following the exact output format in the instructions. In the written file, refer to files by repo-relative paths (e.g.src/main.py, not absolute paths) so the document is portable. Return a one-paragraph summary of what you found.
Failures are isolated: if one analyzer fails, the others' results still count. Retry a failed analyzer once; if it fails again, note it in the final report and move on. Only treat the run as failed if every analyzer fails.
Show full SKILL.md (119 more words)Show less
3. Verify and report
After all subagents finish:
- Confirm each expected output file exists and is non-trivial (has content under its section headings, not just the skeleton).
- Check that no absolute local paths leaked into the documents; replace any with repo-relative paths.
- Report to the user: which analyses succeeded, where the files are, and a short synthesis of the most important findings. Suggest
generate-readmeorgenerate-ai-rulesas natural next steps.
Notes
- Analysis documents are optimized for AI consumption, not human reading — that's intentional. Human-facing output comes from the generator skills.
- Recommend adding
.ai/docs/to the repo (committed, not ignored) so future AI sessions and teammates benefit; but respect the project's existing convention if.ai/is gitignored.
© divar-ir, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in skills/analyze-codebase of divar-ir/ai-doc-gen.
- SKILL.md
- references/api-analyzer.md
- references/data-flow-analyzer.md
- references/dependency-analyzer.md
- references/request-flow-analyzer.md
- references/structure-analyzer.md
Open the folder on GitHubat commit bd3aba7
Compare with similar skills
Analyze Codebase next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Analyze Codebase this skilldivar-ir/ai-doc-gen | 765 | — | ~899 | Automated safety check: Pass | MIT | |
| Harness Agent Team Designerrevfactory/harness | 9.1k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Harness Evolution Feedback Looprevfactory/harness | 9.1k | — | ~855 | Automated safety check: Pass | Apache-2.0 | |
| Mspm0 Ccsmc3545dada/mspm0-skill | 374 | — | ~4.5k | Automated safety check: Pass | MIT | |
| Goal Prompt Builderwin4r/goal-prompt-builder | 228 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Adk Agent Buildergoogle/adk-python | 22k | — | ~879 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Harness Evolution Feedback Loop
revfactory/harness
Collects feedback on how an agent harness performed, generalizes it, and updates the harness agents, skills and orchestrator along with a change-history table.
Mspm0 Ccs
mc3545dada/mspm0-skill
Tool-neutral CLI agent rules for TI MSPM0 development with Code Composer Studio, Keil/uVision, CMake/GCC/OpenOCD, SysConfig, and DriverLib.
Goal Prompt Builder
win4r/goal-prompt-builder
Build high-quality /goal commands for OpenAI Codex CLI 0.128+ that maximize audit-friendliness and minimize false-completion.
- Official
Adk Agent Builder
google/adk-python
Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between…
Requirement Ledger CLI Workflow
adand-91/gpt-6-astra-skill
Runs an evidence-bound audit, daily or weekly review through the requirement-ledger CLI, binding scope and authority first and blocking the final report until a handoff check passes.
More from divar-ir/ai-doc-gen
Generate AI Rules
divar-ir/ai-doc-gen
Generate AI assistant configuration files for a repository — CLAUDE.md, AGENTS.md, and Cursor rules (.cursor/rules/.mdc) — from codebase analysis.
Generate Readme
divar-ir/ai-doc-gen
Generate or refresh a comprehensive, professional README.md for a repository, with architecture overview, mermaid and optional C4 diagrams, repository structure, dependencies, and API documentation.
Related
Works with
Categories
Questions about Analyze Codebase
What does Analyze Codebase do?
Run a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs. Analyze Codebase is an agent skill from divar-ir/ai-doc-gen.ai/docs/ covering structure, dependencies, data flow, request flow, and APIs.
When should I use Analyze Codebase?
Analyze Codebase fits situations like: the user asks to analyze a repository; generate codebase analysis; understand an unfamiliar codebase in depth; before generating documentation (README.
How do I install Analyze Codebase in Claude Code?
Run `npx skills add divar-ir/ai-doc-gen --skill analyze-codebase -a claude-code`. Or copy the skill folder (skills/analyze-codebase in divar-ir/ai-doc-gen) into .claude/skills/analyze-codebase in your project. Claude Code loads it when a task matches its description.
How do I install Analyze Codebase in Codex?
Run `npx skills add divar-ir/ai-doc-gen --skill analyze-codebase -a codex`. Or copy the skill folder (skills/analyze-codebase in divar-ir/ai-doc-gen) into .agents/skills/analyze-codebase in your project. Codex loads it when a task matches its description.
Can I use Analyze Codebase in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add divar-ir/ai-doc-gen --skill analyze-codebase -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/analyze-codebase, .gemini/skills/analyze-codebase, .github/skills/analyze-codebase and .opencode/skills/analyze-codebase in your project.
What does Analyze Codebase need to run?
SKILL.md names no scripts, command-line tools or credentials: Analyze Codebase is instructions for the agent only.
Does Analyze Codebase access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Analyze Codebase safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Analyze Codebase use?
Analyze Codebase is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Analyze Codebase use?
About 899 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.
What are the alternatives to Analyze Codebase?
Skills that share tags, products or a category with Analyze Codebase: Harness Agent Team Designer (revfactory/harness, 9.1k stars), Harness Evolution Feedback Loop (revfactory/harness, 9.1k stars), Mspm0 Ccs (mc3545dada/mspm0-skill, 374 stars) and Goal Prompt Builder (win4r/goal-prompt-builder, 228 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Analyze Codebase?
divar-ir (a GitHub organization) maintains it in divar-ir/ai-doc-gen, which has 765 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on July 21, 2026.
Source: divar-ir/ai-doc-gen on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.