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/theshadow27/mcp-cli/documentation-reviewgit clone --depth 1 https://github.com/theshadow27/mcp-cliWrote 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/theshadow27/mcp-cli/documentation-review)<a href="https://agentmods.dev/commands/theshadow27/mcp-cli/documentation-review"><img src="https://agentmods.dev/badge/commands/theshadow27/mcp-cli/documentation-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 | $0.00000 | $0.00867 |
| Opus 5 | $0.00000 | $0.00434 |
| Sonnet 5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
documentation-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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Review
Review project documentation for consistency with recent code changes. Docs are part of the product — if a feature was added but not documented, or an old pattern was removed but still referenced, that's a bug.
Input
One or more PR numbers (merged or open) to review against. Parse from: $ARGUMENTS
Example: /documentation-review 123 124 125 126
Workflow
1. Gather Context
For each PR number, fetch the diff and summary:
gh pr view <number> --json title,body,files
Build a list of what changed: new commands, renamed files, changed APIs, removed features, updated patterns.
2. Review Each Document
Check every document below against the changes. For each, ask: "Does this document accurately describe the project as it exists right now?"
Documents to review
| Document | Why it matters |
|---|---|
CLAUDE.md |
The primary instruction set for every Claude session. Outdated paths, missing commands, or stale patterns here cause repeated mistakes across all sessions. |
README.md |
First thing a new session (or human) reads. Installation, usage examples, and feature lists must reflect reality. |
test/CLAUDE.md |
Test conventions guide. If new test patterns were established or old ones deprecated, this needs updating so future test writers follow current practice. |
.claude/commands/*.md |
Slash commands reference specific file paths, CLI flags, and workflows. A renamed file or new flag can silently break a command's instructions. |
.claude/skills/*/SKILL.md |
Skills orchestrate multi-step workflows. Changed tool names, new pipeline steps, or updated conventions need to flow through here. |
CLI help text (in packages/command/src/commands/) |
The --help output users actually see. New flags, changed defaults, or removed options must be reflected in the help strings. |
What good looks like
- File paths in docs point to files that actually exist
- Command examples use current flag names and syntax
- Architecture descriptions match the actual package structure
- Feature lists include recently added capabilities
- Removed or renamed items are cleaned up, not left as stale references
- Code examples compile and run correctly
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 · 103 lines · 0 tokens per session scan A c414d6de6cb8
documentation-review is a command published in the GitHub repository theshadow27/mcp-cli (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 867 tokens. 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.