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/mishanefedov/skill-issue/agents-mdgit clone --depth 1 https://github.com/mishanefedov/skill-issueWhat 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 | $0.00565 | $0.00565 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
skill-issue 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — guide for coding agents working in this repo
skill-issue lints coding-agent skills for activation: whether the agent will actually fire a skill, given its always-on name + description. This file is the tool-agnostic guide (Claude Code, Codex, Cursor, etc. all read it). Sibling tool: skillrot (CLI drift).
Layout
src/— the engine.discover.ts— find SKILL.md / agents under a root, read activation metadata.frontmatter.ts— parse (and rewrite) name/description, folded scalars included.triggers.ts— tokenize, weight terms (name/use-when boosted), generic stoplist, IDF.simulate.ts—--why: rank skills for a prompt by rarity-weighted term coverage.collisions.ts—--collisions: Jaccard over salient terms, union into clusters.lint.ts— per-skill activation rules + A–F grade.fix.ts—--fix: append a body-grounded "Use when …" clause to weak descriptions.llm.ts— optional--llmjudge (shells out to claude/codex; falls back).report.ts,cli.ts,types.ts.
skills/skill-issue/SKILL.md— the skill definition (plugin layout)..claude-plugin/— Claude Code plugin + marketplace manifests.bin/skill-issue— launcher (on PATH under the plugin and viabun link).test/—bun test; deterministic fixtures (good / vague / colliding / no-when).
Conventions
- Runtime: Bun. No build step for dev — Bun runs the TypeScript directly.
- Zero runtime dependencies. Keep it that way; the engine only uses
node:*. --llmis the only network path and is opt-in; everything else is offline.- Before pushing:
bun run lint,bun test, andbun run typecheckmust pass. - Be conservative: only empty/duplicate descriptions are errors; everything that merely lowers firing odds (vague, thin, no "use when", collision) is a warning. A linter that cries wolf on a 100-skill set gets uninstalled.
Dogfood
bun run src/cli.ts skills # skill-issue audits its own skill (CI does this too)
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 · 40 lines · 565 tokens per session scan A 8cb114b79062
skill-issue AGENTS.md is an instructions file published in the GitHub repository mishanefedov/skill-issue (3 stars, last pushed 3mo ago), licensed MIT. It adds 565 tokens to every session, about $0.0028 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
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.
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.