Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Security-Phoenix-demo/security-skills-claude-codenpx agentmods add skills/security-phoenix-demo/security-skills-claude-code/project-documenterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/project-documenter)<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/project-documenter"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/project-documenter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/project-documenter"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/project-documenter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00236 | $0.04608 |
| Opus 5 | $0.00118 | $0.02304 |
| Sonnet 5 | $0.00047 | $0.00922 |
| Haiku 4.5 | $0.00024 | $0.00461 |
Grade A, and why
project-documenter 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 yesterday.
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 — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Documenter
Generates a three-layer, AI-native documentation hierarchy for any software repository.
Layer 1 DOC_INDEX.md — compressed routing layer (~1–2k tokens)
Layer 2 CLAUDE.md — engineering navigation map (150–300 lines)
Layer 3 /docs/** — authoritative domain sub-documents (all detail here)
Core law: Sub-documents hold all detail. CLAUDE.md routes to sub-docs. DOC_INDEX.md routes to CLAUDE.md. Nothing is ever duplicated across layers. Both CLAUDE.md and DOC_INDEX.md are generated LAST, synthesized from what was actually written.
EXECUTION SEQUENCE — mandatory order, no exceptions
1. INTAKE — Select mode, confirm existing-doc situation
2. AUDIT — Scan + triage every existing doc (skip only for Mode 0)
3. REPO SCAN — Build internal codebase model
4. SUB-DOCS — Generate all domain documents (depth first)
5. CLAUDE.md — Synthesize navigation index from sub-docs
6. DOC_INDEX.md — Synthesize compressed routing layer from CLAUDE.md
7. REPORT — Completion report + present_files
Step 1 — INTAKE
Ask two questions. Do not proceed until both are answered.
Q1 — Mode
How should I run this?
[0] Express — Brand new project, no existing docs.
Full pack in one run, no audit step, no questions mid-run.
[1] General — README, CONTRIBUTING, API_REFERENCE, MODULES, CHANGELOG, ADRs
[2] AI / LLM — PROMPTS, LLM_ARCHITECTURE, AGENT_WORKFLOWS, MODEL_GUARDRAILS,
AI_RUNBOOK, PROMPT_TESTS, LLM_COST_MODEL, AGENT_SAFETY_MODEL
[3] Architecture — SYSTEM_OVERVIEW, REPOSITORY_MAP, RUNTIME_FLOWS,
DEPENDENCY_MAP, DATA_CONTRACTS
[4] Full — All three domains + audit of any existing docs
[5] Self-Heal — Cursor .mdc rules + GitHub Actions CI + Python scripts
(drift detection, targeted updates, integrity verification)
Requires: CLAUDE.md and DOC_INDEX.md already exist.
Run Mode 0 or Mode 4 first if starting from scratch.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 440 lines · 236 tokens per session scan A d71480ccd4ac
project-documenter is a skill published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (70 stars, last pushed yesterday), licensed MIT. It adds 236 tokens to every session and 4,608 once invoked, about $0.0012 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 2026-09-11.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.