Borrowing it
Nothing to install: this file belongs to ariadoss/superskills. 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/ariadoss/superskills/main/AGENTS.mdgit clone --depth 1 https://github.com/ariadoss/superskillsWrote 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/ariadoss/superskills/agents-md)<a href="https://agentmods.dev/instructions/ariadoss/superskills/agents-md"><img src="https://agentmods.dev/badge/instructions/ariadoss/superskills/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/ariadoss/superskills/agents-md"><img src="https://agentmods.dev/badge/instructions/ariadoss/superskills/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 | $0.01023 | $0.01023 |
| Opus 5.5 | $0.00409 | $0.00409 |
| Sonnet 5.5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
superskills 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 15d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superskills: agent instructions
Context for any coding agent (Codex, Claude Code, Cursor, …) working in this repository. It is contributor context, not plugin context: a plugin's own CLAUDE.md/AGENTS.md is not loaded for end users, so nothing here reaches them.
The rules live in two files; this page only points at them so they are defined once:
CLAUDE.md: release process (VERSION bump →scripts/sync-version.sh),./setupafter pulls and new skills, vendoring rules for imported skills, public-repo exports.ENGINEERING_STANDARDS.md: the quality bar for all code here and for the code the skills produce (TDD, DRY, SOLID, YAGNI), plus the skill-authoring conventions every SKILL.md follows.
Repository structure
skills/: the core skills (one<name>/SKILL.mdeach; sibling files are linked too).design-skills/,marketing-skills/: the design and marketing packs. Marketing skills nest up to three levels deep;marketing-skills/plugin-skills/(symlinks named by frontmatter name) andmarketing-skills/.claude-plugin/plugin.jsonare generated byscripts/sync-marketing-manifest.sh; never edit them by hand.vendor/gstack/: markdown-only snapshot of gstack, a stopgap for offline installs..claude-plugin/,.codex-plugin/,.cursor-plugin/: host manifests.VERSIONis the single source of truth; the manifests are stamped, never hand-edited.scripts/+scripts/lib/: installer helpers, all unit-tested intests/*.bats.evals/:claude plugin evalsuite (skill-trigger and outcome evals; seeevals/README.md). The suite's rubric isevals/RUBRIC.md; the general method (synthetic datasets, judge calibration, the TPR/TNR/accuracy/precision definitions) isevals/METHODOLOGY.md.
Invariants
- Never rewrite published
main./superskills-upgradeforce-syncs canonical installs toorigin/main; releases must stay forward-only. - VERSION drives every manifest. Bump VERSION, run
./scripts/sync-version.sh, update the README badge. A bump that misses a manifest means installs never see it. - A new skill is invisible until
./setupruns. Run it before you push. - Imported skills are vendored. No live dependency on an external repo without an
in-tree copy (or
vendor/snapshot) andmetadata.upstreamin the frontmatter. - Public skill repos are exports. The dbmap skill (and its auto-update
toggles) is canonical here;
scripts/export-dbmap.shpushes it to ariadoss/dbmap before a release (and owns only its three<name>.mdpaths; the rest of that repo is edited there via PR), exactly asscripts/export-humanize.shdoes for/humanizeandscripts/export-eval.shfor/eval.scripts/sync-gstack.shremains a maintainer pull step for thevendor/gstacksnapshot;./setupnever modifies the source tree. - Read-only skills stay read-only.
/superskills-doctordiagnoses; only/superskills-upgradeand./setupchange an install. - No release automation or paid CI without an explicit decision: GitHub Actions on a private repo is a recurring charge.
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.
- 15d ago Changed · +1 lines · +11 tokens per session 69273baf5044
- 16d ago Changed · +2 lines · +35 tokens per session 2ccd3677b122
- 20d ago Changed · +14 lines · +219 tokens per session f28a8af9fa9c
- 25d ago Changed · -9 tokens per session f111a6fa27fe
- 1mo ago First seen · 53 lines · 767 tokens per session scan A 119c3394e4c3
superskills AGENTS.md is an instructions file published in the GitHub repository ariadoss/superskills (12 stars, last pushed 2d ago), licensed MIT. It adds 1,023 tokens to every session, about $0.0041 per session on Opus 5.5. 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 2026-09-17.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.