parseltongue-review

parseltongue-review is a skill for Claude Code, Codex from nlebovits/parseltongue-claude. It costs 42 tokens per session (711 once invoked), scanned A, original, Apache-2.0.

A documentation-audit skill that checks documentation against source material, finds duplicated content, and tests whether stated APIs and behavior are accurate. It can be invoked with `/parseltongue-review`.

In plain words
What is it for?
Reviewing README files, documentation sites, API references, and other docs against code or an authoritative source.
Why use it?
It helps catch documentation that is outdated, inconsistent, duplicated, or different from the implementation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reviewing README files, documentation sites, API references, and other docs against code or an authoritative source.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nlebovits/parseltongue-claude/parseltongue-review
Install

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.

Any agent
npx skills add nlebovits/parseltongue-claude --skill parseltongue-review
Clone the repo
git clone --depth 1 https://github.com/nlebovits/parseltongue-claude

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for parseltongue-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/nlebovits/parseltongue-claude/parseltongue-review/github.svg)](https://agentmods.dev/skills/nlebovits/parseltongue-claude/parseltongue-review)
Your own site
<a href="https://agentmods.dev/skills/nlebovits/parseltongue-claude/parseltongue-review"><img src="https://agentmods.dev/badge/skills/nlebovits/parseltongue-claude/parseltongue-review/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.

agentmods 80×15 button for parseltongue-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/nlebovits/parseltongue-claude/parseltongue-review"><img src="https://agentmods.dev/badge/skills/nlebovits/parseltongue-claude/parseltongue-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.00711
Opus 5 $0.00021 $0.00356
Sonnet 5 $0.00008 $0.00142
Haiku 4.5 $0.00004 $0.00071

Measured 11d ago against content hash f16d8add36be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

parseltongue-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 11d 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.

skills/parseltongue-review/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Audit

Verify documentation accuracy using Parseltongue.

When to Use

  • Audit README for accuracy
  • Review mkdocs site against source
  • Find duplicated content that should link upstream
  • Verify API docs match implementation
  • Check consistency across doc pages

Instructions

1. Load Docs + Source of Truth

mcp__parseltongue__parseltongue_create_session
  session_id: "doc-review-{timestamp}"

mcp__parseltongue__parseltongue_register_document
  session_id: "doc-review-..."
  name: "docs"
  content: [documentation to audit]

mcp__parseltongue__parseltongue_register_document
  session_id: "doc-review-..."
  name: "upstream"
  content: [upstream docs, source code, or authoritative source]

2. Extract Claims

For each claim in the documentation, create a fact:

(fact claim-api-returns-json true
    :evidence (evidence "docs"
        :quotes ("Returns JSON response")
        :explanation "API behavior claim"))

3. Cross-Check Against Source

Use diff to verify claims match the source of truth:

(diff api-behavior-matches
    :left claim-api-returns-json
    :right upstream-api-spec
    :expect (= left right))

4. Check for Duplication

If content appears in both docs verbatim, flag it:

(fact duplicated-content true
    :evidence (evidence "docs"
        :quotes ("Install with pip install foo")
        :explanation "This exact text appears in upstream"))

5. Run Consistency Check

mcp__parseltongue__parseltongue_check_consistency
  session_id: "doc-review-..."

Report:

  • Unverified claims — Docs say something source doesn't support
  • Duplicated content — Should link to upstream instead
  • Inconsistencies — Conflicts between docs and source

Example

User: /parseltongue-review docs/

Claude: Loading docs and source files...
        [registers docs + source code/upstream]

        Extracting claims...
        - "API returns JSON" [ref:api-claim]
        - "Requires Python 3.11+" [ref:python-claim]
        - "Install with pip install foo" [ref:install-claim]

        Cross-checking...
        ✓ API returns JSON - verified in source
        ✓ Python 3.11+ - matches pyproject.toml
        ✗ Install instructions duplicate upstream

        ## Findings

        **Duplicated (link instead):**
        - Installation section [ref:install-claim]

        **Verified:**
        - API behavior [ref:api-claim]
        - Python version [ref:python-claim]

Read the full file on GitHub · 116 lines

Changes

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.

  1. 11d ago First seen · 116 lines · 42 tokens per session scan A f16d8add36be

Subscribe to this mod's changes

parseltongue-review is a skill published in the GitHub repository nlebovits/parseltongue-claude (0 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 711 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens