sheal CLAUDE.md

sheal CLAUDE.md is an instructions file for coding agents from liwala/sheal. It costs 240 tokens per session, scanned A, original, MIT.

Project instructions for Claude Code in a TypeScript command-line toolkit called sheal. They define its build and test commands and how work items and open questions are tracked.

In plain words
What is it for?
Use them when changing or testing sheal, rebuilding its globally linked command-line program, or recording tasks and decisions through the project’s tracking command.
Why use it?
They keep code changes, tests, rebuilds, and task records consistent across contributors and agent sessions.

Instructions file

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.

agentmods
npx agentmods add instructions/liwala/sheal/claude-md
Clone the repo
git clone --depth 1 https://github.com/liwala/sheal

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 sheal CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/liwala/sheal/claude-md.svg)](https://agentmods.dev/instructions/liwala/sheal/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/liwala/sheal/claude-md"><img src="https://agentmods.dev/badge/instructions/liwala/sheal/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 240 This file is loaded in full into every session.
When invoked 240 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00240 $0.00240
Opus 5 $0.00120 $0.00120
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured 4d ago against content hash 48f2f2564d7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sheal 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 4d 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 · 23 lines

What it actually says

Claude Code Instructions

See @AGENTS.md for general agent instructions and session learnings.

Project-Specific

  • This is the sheal (self-healing) CLI toolkit — TypeScript, Node.js
  • Build: npx tsc — always rebuild before testing sheal commands
  • Test: npx vitest run
  • The CLI is globally linked via npm link — rebuild dist/ after changes

Skills

  • /retro [checkpoint-id] — Run a deep session retrospective with LLM analysis

Task and question tracking

This project uses docs/tasks/ to track work items and open decisions. Use the /opentasks skill to manage it.

  • When planning or breaking down work, record concrete steps as tasks (/opentasks new task <title>) and open decisions as questions (/opentasks new question <title>).
  • Keep status current: mark items doing when you start, blocked when waiting, done when complete.
  • Never create task or question files manually — always go through /opentasks to keep the index in sync.
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. 4d ago First seen · 23 lines · 240 tokens per session scan A 48f2f2564d7f

Subscribe to this mod's changes

sheal CLAUDE.md is an instructions file published in the GitHub repository liwala/sheal (86 stars, last pushed 1mo ago), licensed MIT. It adds 240 tokens to every session, about $0.0012 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.

Related

Other instructions, from other repositories