skills CLAUDE.md

skills CLAUDE.md is an instructions file for coding agents from starslingdev/skills. It costs 2,026 tokens per session, scanned A, original, MIT.

Repository instructions for four Claude Code skills that audit CI/CD setup, security, and speed, plus a live question-routing skill.

In plain words
What is it for?
Use them when developing or maintaining the skills, reviewing CI configuration, checking CI/CD security risks, measuring wasted build time, or routing live questions.
Why use it?
They give contributors the repository structure, operating rules, and testing expectations needed to change these skills safely.

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/starslingdev/skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/starslingdev/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/starslingdev/skills/claude-md.svg)](https://agentmods.dev/instructions/starslingdev/skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/starslingdev/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/starslingdev/skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,026 This file is loaded in full into every session.
When invoked 2,026 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 $0.02026 $0.02026
Opus 5 $0.01013 $0.01013
Sonnet 5 $0.00405 $0.00405
Haiku 4.5 $0.00203 $0.00203

Measured 4d ago against content hash 001b07b87181, 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 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 · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

starslingdev/skills

Public Claude Code skills from StarSling. The repo ships four skills, each in its own self-contained directory under skills/: ci-speedup (measured speed / runner-minute waste), ci-score (configuration best practices), ci-secure (the ten critical CI/CD attack vectors), and sling (live single-run questions, routed between the sling and gh CLIs).

The first three audit a local checkout offline and ship deterministic Python engines. sling is deliberately different: it is prose plus a routing contract over a live CLI, with no engine of its own, so its tests pin the contract (the commands it names exist; state changes never route to a read-only CLI) rather than detector behavior.

Repository layout

skills/
  ci-score/                         # skill: configuration best practices (the CI Score)
  ci-secure/                        # skill: the ten critical CI/CD attack vectors
  ci-speedup/                       # skill: measured speed waste (self-contained)
    SKILL.md                        # the skill's canonical contract — read it first
    CHANGELOG.md                    # dated, PR-referenced change history (keep updated)
    ARCHITECTURE.md                 # how the pipeline fits together
    scripts/                        # the deterministic engine (stdlib only)
    references/                     # the pattern catalog + methodology docs
    evals/                          # eval cases
    tests/                          # oracle tests + verify_report.py invariants
  sling/                            # skill: live run/job questions (prose only:
                                    #   SKILL.md, references/, evals/, tests/)
docs/methodology.md                 # public front-door methodology (links into the skill)
examples/                           # sanitized sample report(s)
maintainers/                        # maintainer-only loop infra, OUTSIDE the installable tree
  ci-score/                         #   (ci-score's maintainer-only material)
  skills-registry-security/         # skill: triage a registry audit verdict (see its README.md)
  ci-speedup/                       #   (the `skills` CLI copies skills/<name>/ recursively, so
    MAINTAINERS.md                  #    keeping this here is the only way to keep it out of installs)
    loops/                          # loop prompts + summary schema (gap→catalog, transcript)
    scripts/                        # draft_detector.py, aggregate_lessons.py, dogfood helpers
    workflows/                      # the automated dogfood loop (ci-speedup-dogfood.js)
    tests/                          # tests for the above
tests/                              # repo-level guard (install-surface invariant)
pyproject.toml                      # pytest config; testpaths span the skill + maintainers/
.github/workflows/ci.yml            # runs `pytest -v` on push / PR to main (ubuntu-latest)

Read the full file on GitHub · 137 lines

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 · 137 lines · 2,026 tokens per session scan A 001b07b87181

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository starslingdev/skills (20 stars, last pushed today), licensed MIT. It adds 2,026 tokens to every session, about $0.0101 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.