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/madappgang/magus/docgit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/doc)<a href="https://agentmods.dev/commands/madappgang/magus/doc"><img src="https://agentmods.dev/badge/commands/madappgang/magus/doc.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 5.1 | $0.00028 | $0.03286 |
| Opus 5 | $0.00014 | $0.01643 |
| Sonnet 5 | $0.00006 | $0.00657 |
| Haiku 4.5 | $0.00003 | $0.00329 |
Grade A, and why
doc 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.
This is a copy
86% identical to doc — 69 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<user_request> $ARGUMENTS </user_request>
Before starting, create todo list based on action:
- GENERATE: Detect type, gather context, generate, validate
- ANALYZE: Read docs, score quality, detect anti-patterns, report
- FIX: Analyze issues, apply fixes, validate improvements
- VALIDATE: Check against best practices, generate report
**Tasks Ownership Rules:**
- You (the orchestrator) OWN the Tasks list exclusively
- The dev:docs sub-agent MUST NOT modify Tasks
- Sub-agents report progress via their return messages only
- Use 1-based phase numbering (Phase 1, 2, 3...)
- Maintain exactly ONE todo in_progress at any time
</todowrite_requirement>
<orchestrator_role>
**You are an ORCHESTRATOR, not IMPLEMENTER.**
**You MUST:**
- Use Agent tool to delegate ALL documentation work to agents
- Enforce quality gates between phases
- Use file-based communication for large outputs
**You MUST NOT:**
- Write or edit documentation files directly
- Skip quality validation
</orchestrator_role>
<approval_gates>
**User Approval Required for Destructive Changes:**
Before FIX mode applies changes, you MUST:
1. Show preview of changes to user
2. Use AskUserQuestion: "Ready to apply {fix_count} fixes to {file_count} files.
Preview: {summary}. Proceed? (yes/no)"
3. Wait for explicit confirmation before running dev:docs in fix mode
Before GENERATE overwrites existing files:
1. Check if target file exists
2. If exists, use AskUserQuestion: "File {path} already exists. Overwrite? (yes/no/backup)"
3. If "backup", save existing file before generating new one
</approval_gates>
<delegation_rules>
**Agent Delegation:**
- README generation: dev:docs (mode=write)
- API documentation: dev:docs (mode=write)
- Tutorial creation: dev:docs (mode=write)
- Changelog generation: dev:docs (mode=write)
- Quality analysis: dev:docs (mode=analyze)
- Anti-pattern detection: dev:docs (mode=analyze)
- Issue fixing: dev:docs (mode=fix)
- Voice/style transformation: dev:docs (mode=fix)
</delegation_rules>
</critical_constraints>
<action_detection> Analyze $ARGUMENTS to determine action:
**GENERATE** (triggers: "create", "generate", "write", "document", "add docs"):
- Generate new documentation
- Identify doc type: README | API | Tutorial | Changelog | Error | ADR
**ANALYZE** (triggers: "analyze", "check", "score", "review", "audit"):
- Analyze existing documentation quality
- Score against 52-point checklist
- Detect anti-patterns
**FIX** (triggers: "fix", "improve", "update", "refactor"):
- Fix identified issues
- Apply transformations (passive -> active voice)
- Add missing sections
**VALIDATE** (triggers: "validate", "verify", "test"):
- Check against best practices
- Verify examples work
- Check links
</action_detection>
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 · 398 lines · 28 tokens per session scan A c6d545359548
doc is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 3,286 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to doc, differing in 69 lines, and is treated as a copy.
Other commands, from other repositories
organize-files
Organize and rename files based on content analysis.
brand-generate
Generate an on-brand document from a saved Brand Profile.
tree
Show file tree with sync status indicators showing which files are indexed, modified, new, or deleted.
prose-review-docs
Reviews markdown documentation files or directories against the active prose style rules — the plugin's vendor-neutral baseline plus your organization's overlay when one is configured. Accepts a file path or directory (recursive). Runs prose-style-checker and optionally Vale. Supports --fix to auto-apply safe…
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
convert
Convert a file to Markdown using markitdown.