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 skills/mrinalwadhwa/fluent/review-documentationnpx skills add mrinalwadhwa/fluent --skill review-documentationgit clone --depth 1 https://github.com/mrinalwadhwa/fluentWrote 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/skills/mrinalwadhwa/fluent/review-documentation)<a href="https://agentmods.dev/skills/mrinalwadhwa/fluent/review-documentation"><img src="https://agentmods.dev/badge/skills/mrinalwadhwa/fluent/review-documentation.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 | $0.00038 | $0.00468 |
| Opus 5 | $0.00019 | $0.00234 |
| Sonnet 5 | $0.00008 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
review-documentation 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.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Decide whether the code under review has documentation at every level — function docstrings, file-header comments, module READMEs, codebase-level docs, and user-facing pages. Identify code that lacks documentation, and existing docs that are inaccurate, unclear, or poorly organized.
Scope
The invoking layer decides what's in scope. For a diff-scoped review, that's the code and documentation changed in the diff. For a full-codebase audit, that's the entire codebase and its documentation. Check the documentation for accuracy, writing quality, and vocabulary consistency, and check the code for documentation that should exist but doesn't.
Method
-
Read the code under review to understand what needs documenting.
-
Read
references/documentation.mdfor writing-quality standards. -
For each in-scope documentation file:
- Read it alongside the code it describes.
- Check accuracy against the code.
- Evaluate writing quality against the standards.
- Identify improvements.
-
Check the codebase for undocumented capabilities at every level — function docstrings, file-header comments, module READMEs, codebase-level architecture and contributing docs, and user-facing documentation. Skip when the code speaks for itself; not every function needs a docstring.
-
Check the documentation set as a whole for vocabulary drift — the same concept named differently across pages, or a doc term that conflicts with what the code, tests, or user-facing surface calls it.
-
Check the candidate's commit messages over the provided commit range against the project's stated commit-message conventions in
AGENTS.mdorCLAUDE.md. If the project states commit conventions, flag any commit that violates them. If the project states no commit conventions, skip this step — do not impose conventions the project did not state. -
For each improvement, decide if it blocks shipping. Inaccurate paths, commands, or workflows that would break a reader's task typically block. Vague phrasing, minor AI tells, and small clarity nits typically don't.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 35 lines · 38 tokens per session scan A dfcc921d956e
review-documentation is a skill published in the GitHub repository mrinalwadhwa/fluent (87 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 468 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 2026-08-30.
Other skills, from other repositories
ciel
Ciel — self-improving, self-researching orchestration intelligence. A living skill graph that routes, acquires, integrates, and evolves capabilities across any skill-aware agent runtime.
design-token-architecture
CIEL's framework for three-layer design token systems (primitive→semantic→component) with CSS variables and naming conventions. Advisory only.
chronos
Gives coding agents temporal awareness by reading the session transcript the host already writes, so the agent stops guessing about time and stops repeating commands that just failed. Activates whenever an agent reasons about recency, elapsed time, retry windows, deploy cooldowns, memory or file staleness, idle…
ui_ux_mastery
UI/UX design governance — design systems, accessibility audits, performance budgets, agentic UX patterns.
dev-browser
CIEL's framework for browser automation with persistent page state. Navigates URLs, fills forms, takes screenshots, scrapes data, and tests web apps via sandboxed JavaScript scripts.
devin-conversation-recovery
CIEL's framework for recovering past Devin CLI/ACP conversations from local SQLite stores. A conversation archaeology primitive for context recovery across sessions.