Borrowing it
Nothing to install: this file belongs to iops-leo/claude-slim. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/iops-leo/claude-slim/main/CLAUDE.mdgit clone --depth 1 https://github.com/iops-leo/claude-slimWrote 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/instructions/iops-leo/claude-slim/claude-md)<a href="https://agentmods.dev/instructions/iops-leo/claude-slim/claude-md"><img src="https://agentmods.dev/badge/instructions/iops-leo/claude-slim/claude-md.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 5.1 | $0.00770 | $0.00770 |
| Opus 5 | $0.00385 | $0.00385 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
claude-slim 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 8d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-slim — Claude context
This file is loaded by Claude Code sessions running in this repo. Keep it short; link out to runbooks instead of inlining.
Project summary
claude-slim scans ~/.claude/** for skill/plugin/memory bloat and either
reports or cleans it up. TypeScript CLI, tested with vitest, published to
npm as claude-slim.
- Source:
src/**(build withnpm run build, tests withnpm test) - Ship artifact:
dist/**(committed sonpx claude-slimworks without a build step) - Release channel: npm registry, OIDC Trusted Publisher
Runbooks
- Release process:
docs/internal/release.md— how to cut a new version (bump → tag → push), Trusted Publisher config, troubleshooting the GitHub Actions workflow.
Conventions
- Bug fixes and small hardening land as
fix:/chore:commits; refactors asrefactor:. - Every release ships:
package.jsonversion bump,CHANGELOG.mdentry with### Fixed|Changed|Added, updatedpackage-lock.json, a matchingvX.Y.Zannotated tag. docs/internal/and other personal runbooks are gitignored — treat them as local-only context for future Claude sessions.
Version bumps touch three manifests
package.json, .claude-plugin/plugin.json, .claude-plugin/marketplace.json
(metadata.version), and the seven claude-slim@^x.y.z npx pins in
skills/claude-slim/SKILL.md must all move together. claude plugin install reads the
plugin manifests, not package.json — drift here shipped a stale version to
plugin users for three releases before anyone noticed.
The SKILL.md pin is not decoration. npx reuses any cached _npx install that
satisfies the range and never re-checks the registry, so a major-only @^2 strands
skills.sh users on whatever 2.x they fetched first — v2.14.1's security fix reached
none of them until the pin moved. --prefer-online does not override this.
Run npm run check:versions to verify. It is wired into CI and prepublishOnly.
README changes are a set of four — this gets forgotten every time
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.
- 8d ago First seen · 65 lines · 770 tokens per session scan A 92ef264d2efd
claude-slim CLAUDE.md is an instructions file published in the GitHub repository iops-leo/claude-slim (45 stars, last pushed 11d ago), licensed MIT. It adds 770 tokens to every session, about $0.0038 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 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.
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.
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).
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).
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.
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.