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/drobins25/craft/craft-update-docsgit clone --depth 1 https://github.com/drobins25/craftWrote 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/commands/drobins25/craft/craft-update-docs)<a href="https://agentmods.dev/commands/drobins25/craft/craft-update-docs"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-update-docs.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.01591 |
| Opus 5 | $0.00013 | $0.00796 |
| Sonnet 5 | $0.00005 | $0.00318 |
| Haiku 4.5 | $0.00003 | $0.00159 |
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 3d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Documentation
Re-scan the project to update .craft/project.md and .craft/design/locked.md as the codebase evolves.
When to Use
- After major refactors or architectural changes
- After adding new dependencies or frameworks
- When you notice documentation is stale
- Periodically (check
last_updatedin frontmatter) - Before starting a significant new initiative
Flow
Step 1: Check Current State
Read existing documentation to understand what we have:
Use Read to read .craft/project.md (with limit: 20) and .craft/design/locked.md (with limit: 20) to check last_updated timestamps in frontmatter.
"Your project documentation was last updated on [date].
Let me scan for changes..."
Step 2: Run Project Scanner
INVOKE the project-scanner agent using the Task tool:
Task tool:
subagent_type: "craft:project-scanner"
description: "Re-scan project for documentation update"
prompt: "Scan this project comprehensively for a documentation update.
**Project root:** [current working directory]
**Context:** This is a re-scan, not initial setup. Focus on:
- New patterns that have emerged
- Changed conventions
- New dependencies or tools
- Architecture evolution
- Files/directories that have been added or reorganized
Follow your full analysis checklist (P1-P9). Be thorough.
Return findings in your structured output format."
Extract confidence signals:
If the agent's output contains a ## Confidence Signals (YAML) section:
- Extract the YAML content from the fenced code block in that section
- Write it to
.craft/design/.confidence-signals.yamlat the project root - This file is consumed by craft-init for project-state matrix branching.
If the section is missing (agent failed, non-UI project), skip this step.
Step 3: Compare Findings
Read current documentation:
.craft/project.md.craft/design/locked.md.craft/design/tokens.yaml(for CLI: conventions).craft/design/schemas.md(if exists)
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.
- 3d ago First seen · 288 lines · 26 tokens per session scan A 82d69c4dbaf2
update-docs is a command published in the GitHub repository drobins25/craft (53 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 1,591 once invoked, about $0.0001 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 commands, from other repositories
claudehut-learning-report
Show the ClaudeHut learning scoreboard — measured memory health (store size, reinforcement, effectiveness/recurrence, quality) so you can tell whether the agent is actually getting smarter across sessions. One-shot, read-only.
implement
Execute phased implementation with validation gates.
review
Code review with security and @MX tag compliance check.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".