What is parseltongue?

A document-analysis skill that records facts with exact quotes from the source, derives conclusions using formal logic, and checks for made-up claims. It can be invoked with `/parseltongue`.

Analyzing reports, papers, filings, or other documents; extracting supported facts; checking conclusions; and answering with citations.

It helps make answers traceable to the document and exposes claims that are not supported by the text.

parseltongue — Skill for Claude Code and Codex by nlebovits

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

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nlebovits/parseltongue-claude/parseltongue/github.svg)](https://agentmods.dev/skills/nlebovits/parseltongue-claude/parseltongue)

Your own site

<a href="https://agentmods.dev/skills/nlebovits/parseltongue-claude/parseltongue"><img src="https://agentmods.dev/badge/skills/nlebovits/parseltongue-claude/parseltongue/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nlebovits/parseltongue-claude/parseltongue"><img src="https://agentmods.dev/badge/skills/nlebovits/parseltongue-claude/parseltongue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,694 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.01694
Opus 5.5	$0.00025	$0.00678
Sonnet 5.5	$0.00012	$0.00339
Haiku 4.5	$0.00006	$0.00169

Measured 2mo ago against content hash fda71b1c8788, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

parseltongue 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 2mo 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/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parseltongue Grounded Analysis

Analyze documents with provable claims. Every fact traces to a verbatim quote. Hallucinations are automatically detected.

Quick Start

/parseltongue [paste document] What are the key findings?

Or with a file:

/parseltongue @report.pdf Are there any red flags in this SEC filing?

How It Works

┌─────────────────────────────────────────────────────────────────────┐
│  1. REGISTER    │  Load document into Parseltongue session          │
│  2. EXTRACT     │  Generate facts with verbatim :evidence quotes    │
│  3. DERIVE      │  Draw conclusions using formal logic              │
│  4. VERIFY      │  Check all quotes match source (catch hallucinations) │
│  5. ANSWER      │  Respond with [ref:symbol] citations              │
└─────────────────────────────────────────────────────────────────────┘

Instructions

Step 1: Create Session & Register Document

mcp__parseltongue__parseltongue_create_session
  session_id: "analysis-{timestamp}"

mcp__parseltongue__parseltongue_register_document
  session_id: "analysis-..."
  name: "doc"  # or descriptive name like "10k-filing"
  content: [document text]

Step 2: Extract Facts (Pass 1)

Generate Parseltongue DSL with facts. Every fact MUST have a verbatim quote.

(fact revenue-q3 42000000
    :evidence (evidence "doc"
        :quotes ("Total revenue for Q3 2024 was $42 million")
        :explanation "Quarterly revenue figure"))

(fact growth-target 40000000
    :evidence (evidence "doc"
        :quotes ("Growth target was $40 million")
        :explanation "Target figure for comparison"))

Rules:

:quotes must be EXACT text from the document (case-insensitive matching allowed)
One fact per distinct claim
Use descriptive symbol names (kebab-case)

Load and check:

mcp__parseltongue__parseltongue_load_dsl
  session_id: "analysis-..."
  dsl_source: [your DSL]

If unverified_count > 0, you hallucinated! Fix the quotes.

Read the full file on GitHub · 223 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.

2mo ago First seen · 223 lines · 62 tokens per session scan A fda71b1c8788

Subscribe to this mod's changes

parseltongue is a skill published in the GitHub repository nlebovits/parseltongue-claude (0 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,694 once invoked, about $0.0002 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 2026-08-31.

Documents Research

parseltongue next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
parseltonguenlebovits/parseltongue-claude	Skill	0	7mo ago	Apache-2.0	A	62	Claude Code, Codex
orbit-notionnexu-io/open-design	Skill	107k	today	Apache-2.0	A	117	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	yesterday	Apache-2.0	A	123	Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	48	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	yesterday	Apache-2.0	A	68	Claude Code
report-to-pdfasgeirtj/system_prompts_leaks	Skill	71k	yesterday	CC0-1.0	A	17	Claude Code, Codex
artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks	Skill	71k	yesterday	CC0-1.0	A	54	Claude Code, Codex