Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/quangphu1912/codebase-analyzer/claude-mdgit clone --depth 1 https://github.com/quangphu1912/codebase-analyzerWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00515 | $0.00515 |
| Opus 5 | $0.00258 | $0.00258 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
codebase-analyzer CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codebase-analyzer Plugin
Architecture
- 32 skills + 3 agents
- Track A (reconnaissance) -> Track B (deep dive) -> System Intent
- Orchestration skills cloned from superpowers (vendor/superpowers/) for development workflows
- Standard output contract in
docs/analysis/
Three Depths Model
- Surface (Track A): Fast structural scans, architecture maps
- Deep (Track B Phases 1-3): Git archaeology, gate extraction, behavior simulation
- Intent (Track B Phase 4): Reconstruct what the system was built to do
Skill Standards
- Description field: starts with "Use when...", triggers only, no workflow summary
- Every skill writes to
docs/analysis/using standard contract - Trigger signals include: priority (high/med/low), confidence (high/med/low), evidence (file:line)
Behavioral Engineering
- Skills are behavioral software, not reference documentation
- Every skill includes: announce line, red flags, output contract
- Critical skills include: Iron Law, rationalization table, HARD-GATE
- Description field: trigger-only (CSO rule), never summarize workflow
File Naming
- Skills:
skills/<verb>-<noun>/SKILL.md - References:
skills/<verb>-<noun>/references/<topic>.md - Agents:
agents/<noun>.md
Testing
- RED-GREEN-REFACTOR for each skill
- Test against diverse repo types (web app, library, IaC, monorepo)
Multi-Platform Support
- Claude Code: Primary target. SessionStart hook, plugin manifests, Skill tool, full agent dispatch.
- OpenCode: ESM plugin at
.opencode/plugins/codebase-analyzer.js. Config hook + message transform. No agent dispatch (degraded mode). - Codex: Symlink-based skill discovery (
~/.agents/skills/). AGENTS.md symlink. Sandbox fallback mode. No agent dispatch (degraded mode). - Platform capabilities: Defined in
skills/using-codebase-analyzer/PLATFORM-NOTES.md(single source of truth). - Validation:
scripts/validate.shchecks all skills, agents, hooks, and plugin health. - Upstream sync:
scripts/sync-upstream.shpulls upstream superpowers via git subtree + rebuilds skills.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 41 lines · 515 tokens per session scan A f674ade78d20
codebase-analyzer CLAUDE.md is an instructions file published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 515 tokens to every session, about $0.0026 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.