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 commands/agoldian/claudenv/update-docsgit clone --depth 1 https://github.com/AGoldian/claudenvWhat 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 | $0.00006 | $0.00518 |
| Opus 5 | $0.00003 | $0.00259 |
| Sonnet 5 | $0.00001 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
update-docs 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.
What it actually says
Update Project Documentation
You are updating the existing Claude Code documentation for this project.
Step 1: Read Current Documentation
Read the existing documentation files:
- @CLAUDE.md
- Read any files referenced by @imports in CLAUDE.md
Step 2: Scan Current State
Detect the current tech stack:
Package managers:
!find . -maxdepth 3 \( -name "package.json" -o -name "pyproject.toml" -o -name "go.mod" -o -name "Cargo.toml" -o -name "Gemfile" \) -not -path "*/node_modules/*" 2>/dev/null | head -20
Framework configs:
!find . -maxdepth 2 \( -name "tsconfig.json" -o -name "next.config.*" -o -name "vite.config.*" -o -name "manage.py" -o -name "docker-compose.*" \) -not -path "*/node_modules/*" 2>/dev/null | head -20
Read the manifest files to check for new dependencies, scripts, or configuration changes since the documentation was last generated.
Step 3: Identify Changes
Compare the current state against the existing documentation:
- New dependencies or tools not mentioned in CLAUDE.md
- Changed scripts (renamed, added, or removed)
- New directories not covered in Architecture section
- Stale references to files or directories that no longer exist
- Missing conventions based on new config files (e.g., new linter added)
- Missing or outdated
.mcp.json— if.mcp.jsondoesn't exist, or if new technologies have been added that could benefit from MCP servers, suggest running/setup-mcp
Step 4: Propose Updates
Present a diff-style summary of proposed changes to each documentation file. For each change:
- Show what currently exists
- Show what should be updated
- Explain why the change is needed
Wait for user approval before writing any changes.
Step 5: Apply Updates
After user approval, update the documentation files. Preserve any user-written content that was manually added — only update sections that correspond to detected/generated content.
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 · 51 lines · 6 tokens per session scan A fce6b5496794
update-docs is a command published in the GitHub repository AGoldian/claudenv (10 stars, last pushed 2mo ago), licensed MIT. It adds 6 tokens to every session and 518 once invoked, about $0.0000 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.