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/axiomantic/spellbook/docs-plangit clone --depth 1 https://github.com/axiomantic/spellbookWhat 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 | $0.00034 | $0.03272 |
| Opus 5 | $0.00017 | $0.01636 |
| Sonnet 5 | $0.00007 | $0.00654 |
| Haiku 4.5 | $0.00003 | $0.00327 |
Grade A, and why
docs-plan 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MISSION
Generate a documentation plan: table of contents with Diataxis type and tone profile per section, MkDocs build configuration, README section plan, and optional hosting config. Transform audit gaps into actionable TOC entries with output paths, priority tiers, and source hints. Present the complete plan for user approval before proceeding.
Invariant Principles
- One Diataxis type per section: Every TOC entry maps to exactly one type. Mode mixing is a defect caught in review, but prevented here by correct assignment.
- Tone follows type mapping: Default tone profiles are assigned by Diataxis type. Users CAN override during the interview step. Overrides are respected by all downstream phases.
- User approves TOC before generation proceeds: Present the full TOC table. Iterate on changes until the user confirms. Never skip this gate.
- Re-run policy: Check for existing
doc-state/plan.json. If found, present option to reuse or regenerate. Do not silently overwrite. - Source citations must be source-verified: Any symbol, function, method, class, file path, or Redis/database key namespace that appears in
source_hints,cross_cutting_tasks, or any prose field of the plan MUST be verified to exist in the project source before being recorded. Usegrep -r '<symbol>' src/(or the project's equivalent) and confirm at least one match. Plausible-sounding LLM-generated names are the failure mode this rule prevents: writers downstream treat plan output as authoritative and will apply unverified names verbatim. If the audit flags "replace line numbers with symbol names" as a cross-cutting task, the planner is responsible for deriving and verifying each replacement name, not for asserting candidates that the writer must somehow validate.
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 · 324 lines · 34 tokens per session scan A 850f97941839
docs-plan is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 3,272 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 2026-08-31.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
audit-whitepapers
Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.
audit-repo-docs
Audit repository documentation against 85+ best practices from claude-code-ultimate-guide.
boldguy-linkedin-answer
Draft a LinkedIn comment on a post, referencing the guide's relevant section, in Flow style with AI markers removed.
methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
release
Release guide version (CHANGELOG + VERSION + README + landing sync + commit + push).