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.
npx agentmods add instructions/starslingdev/skills/agents-mdgit clone --depth 1 https://github.com/starslingdev/skillsWhat 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 | $0.01238 | $0.01238 |
| Opus 5 | $0.00619 | $0.00619 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
skills AGENTS.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 2d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents contributing to starslingdev/skills.
AGENTS.md is the cross-tool convention (Codex, Cursor, and others read it).
Claude Code reads CLAUDE.md — it carries the same rules in
fuller form. This file is the contributor subset; when they disagree, the
source files below win.
What this repo is
Public Claude Code skills from StarSling. Today it ships one skill,
ci-speedup, self-contained under skills/ci-speedup/. ci-speedup audits a
repository's GitHub Actions workflows for CI optimization opportunities and
produces a prioritized report with measured wall-clock and runner-minute
savings.
Read skills/ci-speedup/SKILL.md before editing
anything under the skill — it is the authoritative spec.
Repository layout
skills/ci-speedup/ the installable skill (self-contained)
SKILL.md canonical contract — read it first
CHANGELOG.md dated, PR-referenced change history
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
docs/methodology.md public front-door methodology
examples/ sanitized sample report(s)
maintainers/ci-speedup/ maintainer-only loop infra — OUTSIDE the installable tree
tests/ repo-level guards (install-surface invariant)
pyproject.toml pytest config; testpaths span the skill + maintainers/
.github/workflows/ ci.yml (self-hosted + fork suites, `test` verdict)
Running tests
From the repo root:
pip install -e ".[dev]" # pytest + PyYAML; the suite needs both
python3 -m pytest -v
This runs every suite — the root pyproject.toml wires the paths so one command
finds tests under tests/, skills/ci-speedup/tests/, and
maintainers/ci-speedup/tests/. CI runs the identical command, so green on
your machine means green in CI — as long as the dev dependencies are installed.
Without PyYAML, pytest aborts at collection with INTERNALERROR and runs nothing.
Enable the local pre-commit hook to run the same suite before each commit:
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.
- 2d ago First seen · 114 lines · 1,238 tokens per session scan A a1bb97f28a14
skills AGENTS.md is an instructions file published in the GitHub repository starslingdev/skills (19 stars, last pushed 6d ago), licensed MIT. It adds 1,238 tokens to every session, about $0.0062 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
harmont-cli CLAUDE.md
Instructions for harmont-dev/harmont-cli, covering testing, documentation, dsl and keep the sdk, hm init templates, and docs in sync.
Tracely-ai CLAUDE.md
Claude Code instructions for Jwuthri/Tracely-ai, covering claude.md, commands, architecture, hard rules and gotchas.
limboo CLAUDE.md
Instructions for limboo-ai/limboo, covering claude.md, 1. what is limboo?, 2. tech stack (current), 3. project structure and the three electron contexts (critical mental model).
devopness AGENTS.md
Instructions for devopness/devopness, covering agents, core flow, shared constraints, monorepo structure and git workflow.
devopness CLAUDE.md
Instructions for devopness/devopness, a project described as: Devopness: AI DevOps on your cloud. Deploy apps, infra and CI/CD. Any cloud and any stack, one MCP. Deterministic API, opinionated and fully configurable. No cloud credentials in AI chats. Free plan.
zuke AGENTS.md
Instructions for zuke-build/zuke, covering agents.md, using zuke — the api, without guessing, tech stack, typescript 7 / tsgo and coding guidelines (non-negotiable).