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-reviewgit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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/axiomantic/spellbook/docs-review)<a href="https://agentmods.dev/commands/axiomantic/spellbook/docs-review"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/docs-review.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 | $0.00033 | $0.04702 |
| Opus 5 | $0.00016 | $0.02351 |
| Sonnet 5 | $0.00007 | $0.00940 |
| Haiku 4.5 | $0.00003 | $0.00470 |
Grade A, and why
docs-review 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 4d 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MISSION
Apply 8 measurable quality criteria to all generated documentation files. Each criterion has a concrete pass condition and an automated or structured measurement method. Iterate on failures by re-dispatching /docs-write for failing sections only, up to 2 passes per section. Dispatch fact-checking for claim verification. Produce a structured review result that the orchestrator uses to decide whether to accept the docs or escalate to the user.
Invariant Principles
- All 8 criteria evaluated: No criterion is skipped, even if early criteria fail. The full picture matters for efficient iteration.
- Iteration limit enforced: Maximum 2 re-generation passes per section. After that, escalate to the user with specific failures rather than looping.
- Fact-checking dispatched: Claims about version numbers, API behaviors, command syntax, configuration options, and import paths are verified against source code.
- Structured results: Every finding is recorded per-criterion, per-file. The orchestrator needs granular data for targeted re-dispatch.
Inputs
| Source | Path | Tool |
|---|---|---|
| Written manifest | ~/.local/spellbook/docs/{project-encoded}/doc-state/written-manifest.json |
Read |
| Documentation plan | ~/.local/spellbook/docs/{project-encoded}/doc-state/plan.json |
Read |
| Writing guide rules | $SPELLBOOK_DIR/skills/documenting-projects/writing-guide.md |
Read |
| Previous review (optional) | ~/.local/spellbook/docs/{project-encoded}/doc-state/review-result.json |
Read |
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.
- 4d ago First seen · 396 lines · 33 tokens per session scan A d3e9d3f51647
docs-review is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 4,702 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.
boldguy-linkedin-answer
Draft a LinkedIn comment on a post, referencing the guide's relevant section, in Flow style with AI markers removed.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
sync
Check guide/landing synchronization status.
worktree
Create a git worktree for isolated feature/fix work.