agentmods.dev

skilllens: Instructions file for Claude Code

CLAUDE.md

skilllens CLAUDE.md is an instructions file for Claude Code from mathieu0905/skilllens. It costs 209 tokens per session, scanned A, a copy of skilllens AGENTS.md, MIT.

A set of Claude Code project instructions covering collaboration rules, version management, and experiment records. It recommends using Git history for versions instead of making many numbered copies of folders.

In plain words
What is it for?
Use it when managing SkillScope code, analyzer or optimizer changes, workflow rules, experiment artifacts, schema versions, and Git-based rollbacks.
Why use it?
It keeps code changes and experiment results traceable, making comparisons, rollbacks, and later investigation easier.

Instructions file for Claude Code

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

This is mathieu0905/skilllens's own configuration. It tells Claude Code how to work on skilllens 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 skilllens configures →

not rated 2repo 4mo ago A scan 209 tokens copy · 98% MIT
View source ↗ mathieu0905/skilllens
Reuse

Borrowing it

Nothing to install: this file belongs to mathieu0905/skilllens. 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/mathieu0905/skilllens/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mathieu0905/skilllens

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 skilllens CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mathieu0905/skilllens/claude-md/github.svg)](https://agentmods.dev/instructions/mathieu0905/skilllens/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mathieu0905/skilllens/claude-md"><img src="https://agentmods.dev/badge/instructions/mathieu0905/skilllens/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 skilllens CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mathieu0905/skilllens/claude-md"><img src="https://agentmods.dev/badge/instructions/mathieu0905/skilllens/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 209 This file is loaded in full into every session.
When invoked 209 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 98% copy Near-identical to another mod 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 $0.00209 $0.00209
Opus 5.5 $0.00084 $0.00084
Sonnet 5.5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured 2mo ago against content hash 5c0add3ca73b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skilllens 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 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.

Origin

This is a copy

98% identical to skilllens AGENTS.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 16 lines

What it actually says

Claude Code Collaboration Rules

Version Management

  • Use git commits to version SkillScope code, analyzer logic, optimizer prompts, and workflow rules.
  • Do not manage logic history by creating endless v1, v2, v3, v8 directories or constants. That makes rollback and comparison noisy.
  • Use git revert, branches, tags, and commit hashes for rollback or comparison.
  • Keep experiment artifacts under semantic names that describe intent, such as fresh-from-original, native-target-split, or cia-batch-smoke.
  • Every experiment artifact should record the code commit, analyzer version or schema version, source skill path, trace path, and native verifier result.
  • Only bump explicit schema/analyzer version strings when cache compatibility or persisted data format genuinely changes.
  • Temporary numbered directories are allowed only for short-lived scratch work. Promote useful results into a semantic run name or a database record, then clean up redundant copies.

Principle

Experiment outputs are data. Git history is the version manager.

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. 2mo ago First seen · 16 lines · 209 tokens per session scan A 5c0add3ca73b

Subscribe to this mod's changes

skilllens CLAUDE.md is an instructions file published in the GitHub repository mathieu0905/skilllens (2 stars, last pushed 4mo ago), licensed MIT. It adds 209 tokens to every session, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to skilllens AGENTS.md, differing in 2 lines, and is treated as a copy.

Git and workflow
Related

skilllens CLAUDE.md compared with instructions from other repositories

skilllens CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skilllens CLAUDE.mdmathieu0905/skilllensInstructions file24mo agoMITA209Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode