skills CLAUDE.md

skills CLAUDE.md is an instructions file for coding agents from BCGen/skills. It costs 288 tokens per session, scanned A, original, MIT.

Project instructions for maintaining a collection of coding-agent skills. They describe how to install dependencies, run checks, organize skills, and handle changes.

In plain words
What is it for?
Use them when adding or editing skills, running lint checks, deciding whether a formal change proposal is needed, and recording lessons after a task.
Why use it?
They give contributors one set of rules for keeping the skill repository consistent and passing its automated checks.

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/bcgen/skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/BCGen/skills

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 skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bcgen/skills/claude-md.svg)](https://agentmods.dev/instructions/bcgen/skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bcgen/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/bcgen/skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 288 This file is loaded in full into every session.
When invoked 288 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 $0.00288 $0.00288
Opus 5 $0.00144 $0.00144
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured 3d ago against content hash 943a6fe1f9bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills 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 3d 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 · 25 lines

What it actually says

Skills — repo notes

Install deps with pnpm install; lint everything with pnpm lint (skill lint + markdownlint over skills/**).

Layout: skills/<name>/SKILL.md are the installable units (English-only, enforced by lint) — a flat directory, since the installer flattens names anyway. Grouping is a README concern, not a filesystem one; group a skill by adding it under the right ## section in README.md. Acceptance tests and fixtures live in tests/.

Governance is per group, not repo-wide. The agent harness & skill authoring group is spec-driven: changes to it go through openspec/ (/opsx:propose, /opsx:apply, /opsx:archive). Every other group is lint-only — write the skill, pass pnpm lint, done. Do not open an OpenSpec proposal for a skill outside the harness group.

Skills that depend on personal context (a specific employer, client, toolchain, or project layout) do not belong here — they live in a separate private repo. The test: does the skill need to know who I am?

Run the retro skill when a task ends; lessons land in .ai/learnings/, ideas in .ai/backlog/.

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. 3d ago First seen · 25 lines · 288 tokens per session scan A 943a6fe1f9bd

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository BCGen/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 288 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