Borrowing it
Nothing to install: this file belongs to daijx-ai/skillwitness. 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/daijx-ai/skillwitness/main/AGENTS.mdgit clone --depth 1 https://github.com/daijx-ai/skillwitnessWrote 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/daijx-ai/skillwitness/agents-md)<a href="https://agentmods.dev/instructions/daijx-ai/skillwitness/agents-md"><img src="https://agentmods.dev/badge/instructions/daijx-ai/skillwitness/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/daijx-ai/skillwitness/agents-md"><img src="https://agentmods.dev/badge/instructions/daijx-ai/skillwitness/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 | $0.00275 | $0.00275 |
| Opus 5 | $0.00138 | $0.00138 |
| Sonnet 5 | $0.00055 | $0.00055 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
skillwitness 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 10d 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.
What it actually says
SkillWitness contributor rules
Product boundary
SkillWitness is a local, read-only Agent Skills validator and evidence reporter. It does not install, copy, sync, enable, invoke, score, or repair skills.
Evidence invariants
- Keep
present,copied,eligible_by_path,runtime_discovered,enabled, andinvokedindependent. - A conventional path never proves runtime discovery, enablement, or invocation.
- Equal content hashes prove byte identity, not provenance. Only a declared source plus exact hash may produce
copied=yes. - A realpath alias or symlink is never a copy.
- Use
unknownwhen the required runtime-owned receipt is absent.
Privacy invariants
- Never read conversations, config values, credentials, cookies, environment variables, or telemetry.
- Never render skill body text, description text, unknown metadata values, or absolute home paths.
- Follow a skill-directory symlink only when its target stays inside a registered root; record it as an alias, never a copy.
- Fixtures and demo data must remain synthetic.
Development
Use Node.js 22 or newer. Runtime code must stay dependency-free.
npm test
npm run check
npm run demo
Add a failing test before changing behavior. Every finding needs a stable code and evidence boundary.
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.
- 10d ago First seen · 33 lines · 275 tokens per session scan A 24929c1a095b
skillwitness AGENTS.md is an instructions file published in the GitHub repository daijx-ai/skillwitness (2 stars, last pushed 1mo ago), licensed MIT. It adds 275 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.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.