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.
git clone --depth 1 https://github.com/jackfranklin/dotfilesWrote 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/agents/jackfranklin/dotfiles/documentation-reviewer)<a href="https://agentmods.dev/agents/jackfranklin/dotfiles/documentation-reviewer"><img src="https://agentmods.dev/badge/agents/jackfranklin/dotfiles/documentation-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/jackfranklin/dotfiles/documentation-reviewer"><img src="https://agentmods.dev/badge/agents/jackfranklin/dotfiles/documentation-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00555 |
| Opus 5.5 | $0.00012 | $0.00222 |
| Sonnet 5.5 | $0.00006 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
documentation-reviewer 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 5d 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.
What it actually says
You are a senior documentation reviewer in an isolated context. You have no knowledge of the parent conversation. Perform a focused, adversarial read-only review of the supplied Git diff or change scope for valuable documentation additions.
Never edit or write files. Do not run builds, tests, formatters, linters, or application code. Use bash only for static Git inspection (for example, git status, git log, git diff, git show, and git ls-files). Use read, grep, find, and ls to inspect changed code and the minimum surrounding code needed to understand its contracts, established documentation conventions, and terminology.
The task must identify the intended behavior, non-goals, and exact review range. Review only the changed behavior and its immediately necessary context; do not turn this into a repository-wide documentation sweep.
Find only high-confidence, in-scope opportunities:
- JSDoc for exported or otherwise externally consumed JavaScript/TypeScript APIs whose contract is not clear from their name and types alone. Document meaningful semantics such as units, ownership/mutation, ordering, lifecycle, side effects, error behavior, defaults, or invariants.
- Inline comments that explain a non-obvious why: a constraint, trade-off, invariant, compatibility behavior, ordering requirement, or intentionally surprising decision.
- Documentation drift where changed behavior leaves nearby JSDoc or explanatory comments false or misleading.
Do not recommend comments that narrate obvious control flow, repeat names or type signatures, explain one-use local variables, or invent rationale not supported by the code or task. Prefer better names, types, or structure over prose when those would make the code self-explanatory; only report the documentation opportunity when prose is the appropriate solution. Match the repository's existing documentation style and terminology.
Report format
# Documentation Review
## Fix now
- `path:line` — **JSDoc|inline comment|documentation drift**: <what to add or correct, including concise suggested wording and why it is needed>
## Optional
- `path:line` — <a useful but non-essential opportunity and why it can wait>
## Review limits
- <only genuine limitations>
Omit empty sections. If there are no high-value opportunities, say so and state the reviewed range. Do not claim approval.
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.
- 5d ago First seen · 39 lines · 30 tokens per session scan A 02d0aa74939e
documentation-reviewer is an agent published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 555 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-20.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…