source-faithful-summary-skill: Instructions file for Claude Code

CLAUDE.md

source-faithful-summary-skill CLAUDE.md is an instructions file for Claude Code from Kinneyzhang/source-faithful-summary-skill. It costs 287 tokens per session, scanned A, original, MIT.

A set of instructions for a reusable source-faithful summarization skill. It describes how to map a source, preserve its main argument and evidence, and check the final summary for distortions or omissions.

In plain words
What is it for?
Use it to summarize long or complex sources, including multi-speaker transcripts. It also defines a fresh-source process for rewriting an existing summary.
Why use it?
It reduces the risk of producing a polished summary that misrepresents what the original source emphasized or concluded.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is Kinneyzhang/source-faithful-summary-skill's own configuration. It tells Claude Code how to work on source-faithful-summary-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything source-faithful-summary-skill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Kinneyzhang/source-faithful-summary-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Kinneyzhang/source-faithful-summary-skill/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Kinneyzhang/source-faithful-summary-skill

Made for: Claude Code.

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 source-faithful-summary-skill CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kinneyzhang/source-faithful-summary-skill/claude-md/github.svg)](https://agentmods.dev/instructions/kinneyzhang/source-faithful-summary-skill/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kinneyzhang/source-faithful-summary-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/kinneyzhang/source-faithful-summary-skill/claude-md/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 source-faithful-summary-skill CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kinneyzhang/source-faithful-summary-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/kinneyzhang/source-faithful-summary-skill/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 287 This file is loaded in full into every session.
When invoked 287 The same file — it is already loaded in full.
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 $0.00287 $0.00287
Opus 5 $0.00143 $0.00143
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00029 $0.00029

Measured 9d ago against content hash bed2d979603a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

source-faithful-summary-skill CLAUDE.md 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 9d 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.

CLAUDE.md · 36 lines

What it actually says

CLAUDE.md — Source-Faithful Summary Skill

This repository contains a reusable summarization skill. When working in this project or using this instruction pack, follow SKILL.md as the source of truth.

Summary protocol

  1. Classify the source type.
  2. Build a source map.
  3. List named concepts and classify their role.
  4. Extract failure modes or tensions.
  5. Extract action chain or argument chain.
  6. Build a decision-model map.
  7. Draft the source-faithful summary.
  8. Run main-thread, concept-overreach, missing-details, and decision-model audits.

Key principle

A readable summary can still be wrong if it makes the reader misunderstand what the source was mainly doing.

Do not optimize for elegance before preserving:

  • main thread;
  • attention weight;
  • concrete examples;
  • source order where relevant;
  • speaker/author decision model;
  • timestamps or evidence trail.

If asked to rewrite a summary

Do not anchor on the old summary. Re-open the original source or transcript, rebuild the source map, and regenerate from the extracted structure.

Long sources

For sources longer than ~50k characters, longer than ~60 minutes, or multi-speaker/panel transcripts, use templates/long-source-plan.md before summarizing. State chunking/sampling strategy, chapter coverage, recurrence checks, speaker coverage, and evidence budget.

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. 9d ago First seen · 36 lines · 287 tokens per session scan A bed2d979603a

Subscribe to this mod's changes

source-faithful-summary-skill CLAUDE.md is an instructions file published in the GitHub repository Kinneyzhang/source-faithful-summary-skill (2 stars, last pushed 3mo ago), licensed MIT. It adds 287 tokens to every session, about $0.0014 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens