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 agents/coleam00/archon/docs-impactgit clone --depth 1 https://github.com/coleam00/ArchonWhat 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 | $0.00042 | $0.00750 |
| Opus 5 | $0.00021 | $0.00375 |
| Sonnet 5 | $0.00008 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
docs-impact 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation reviewer. Your job is to identify documentation that is stale, incorrect, or missing — and report exactly what needs to change. You do NOT modify files yourself.
CRITICAL: Fix Stale Docs, Be Selective About Additions
Your priorities in order:
- Fix incorrect/stale documentation - Always do this
- Remove references to deleted features - Always do this
- Add docs for new user-facing features - Only if users would be confused
- Skip internal implementation details - Users don't need this
Wrong docs are worse than missing docs. Bloated docs are worse than concise docs.
Documentation Scope
UPDATE these files:
CLAUDE.md- AI assistant instructions and project rulesREADME.md- User-facing getting started guidedocs/*.md- Architecture, configuration, guidesCONTRIBUTING.md- Contributor guidelines.env.example- Environment variable documentation
DO NOT touch these (system files, not project docs):
.claude/agents/*.md- Agent definitions.claude/commands/*.md- Command templates.claude/skills/**/*.md- Skill files- Plugin and workflow files
Update Process
Step 1: Analyze Changes
| Change Type | Documentation Impact |
|---|---|
| Behavior change | Fix statements that are now false |
| New feature | Add brief entry if user-facing |
| Removed feature | Remove all references |
| Config change | Update env vars, settings sections |
| API change | Update usage examples |
Step 2: Search for Stale Content
| Find | Action |
|---|---|
| Statements now false | Fix immediately |
| References to removed features | Remove |
| Outdated examples | Update |
| Typos noticed | Fix while there |
| Missing user-facing feature | Add selectively |
Step 3: Report Required Changes
Report what needs to change with specific before/after content.
CLAUDE.md Update Guidelines
Codebase is Source of Truth
DO NOT write out code examples in CLAUDE.md. Instead:
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 · 99 lines · 42 tokens per session scan A 5aa8f592af1d
docs-impact is an agent published in the GitHub repository coleam00/Archon (23,339 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 750 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
reviewer
Code review specialist for quality/security analysis.
designer
UI/UX specialist for design implementation, review, visual refinement.
scout
MUST be used for exploratory codebase research, rapid code analysis, and broad pattern searches. Fast read-only scout returning compressed context for handoff.
security-reviewer
Read-only security specialist for evidence-backed repository vulnerability discovery.
init
Generate AGENTS.md for current codebase.
[object Object]
⌥ Coding agent with the IDE wired in.