Borrowing it
Nothing to install: this file belongs to slamb2k/mad-skills. 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/slamb2k/mad-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/slamb2k/mad-skillsWrote 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/slamb2k/mad-skills/agents-md)<a href="https://agentmods.dev/instructions/slamb2k/mad-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/slamb2k/mad-skills/agents-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.
<a href="https://agentmods.dev/instructions/slamb2k/mad-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/slamb2k/mad-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.05370 | $0.05370 |
| Opus 5.5 | $0.02148 | $0.02148 |
| Sonnet 5.5 | $0.01074 | $0.01074 |
| Haiku 4.5 | $0.00537 | $0.00537 |
Grade A, and why
mad-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 1mo 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.
This is a copy
86% identical to mad-skills CLAUDE.md — 429 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.
How it starts
The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Skill Usage Guide
MAD Skills provides 14 skills covering the full development lifecycle. When this plugin is installed, use these skills proactively — don't wait for the user to invoke them by name if the situation clearly calls for one.
Positioning: Complementary to Superpowers
MAD Skills is the deterministic ops/infra spine — scaffolding, tooling, CI, IaC, container pipelines, ambient governance (session-guard), and dual-platform (GitHub + Azure DevOps) support. Superpowers has no equivalent for that layer, and MAD Skills is designed to compose underneath Superpowers' methodology rather than compete with it.
Where the two overlap on methodology (plan → build → finish), MAD Skills defers to Superpowers when it is installed, and falls back to its own pipeline when it is absent. Superpowers is a soft/recommended dependency (runtime-detected, like graphify) — never required.
/speccyusessuperpowers:brainstormingfor requirements exploration, but still owns thespecs/*.mdartifact + build handoff./buildkeeps its explore stage, and its review and verify stages now dispatch unconditionally to the native/code-review+/security-review/verifypipeline, but the plan/implement core still routes tosuperpowers:executing-plans/superpowers:subagent-driven-development.
/shipkeeps sync + branch + commit + CI-poll + auto-fix, but hands the final integration tosuperpowers:finishing-a-development-branch(merge/PR/cleanup options) instead of silently auto-merging./primesurfaces a passive hint ifgraphify-out/exists (query via/graphify) — hint only, no dependency.
Each of /speccy, /build, /ship accepts --no-superpowers to force the
standalone pipeline. When Superpowers is absent, all skills behave exactly as
their standalone descriptions below.
Implemented: this deferral behavior is specified in
specs/superpowers-complementary-layer.md. Detection runs throughscripts/lib/superpowers.js(registered + enabled plugins only) and the shared contract inreferences/superpowers-deferral.md, wired into/speccy,/build,/ship, and the/primegraphify hint.
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.
- 1mo ago Changed · +6 lines · +163 tokens per session 16d1957c6b01
- 1mo ago First seen · 423 lines · 5,207 tokens per session scan A 48a207d72fdf
mad-skills AGENTS.md is an instructions file published in the GitHub repository slamb2k/mad-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 5,370 tokens to every session, about $0.0215 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to mad-skills CLAUDE.md, differing in 429 lines, and is treated as a copy.
mad-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mad-skills AGENTS.mdslamb2k/mad-skills | Instructions file | 5 | 1mo ago | MIT | A | 5,370 | Claude Code, Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |