Borrowing it
Nothing to install: this file belongs to Yesterday-AI/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/Yesterday-AI/skills/main/AGENTS.mdgit clone --depth 1 https://github.com/Yesterday-AI/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/yesterday-ai/skills/agents-md)<a href="https://agentmods.dev/instructions/yesterday-ai/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/yesterday-ai/skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01012 | $0.01012 |
| Opus 5 | $0.00506 | $0.00506 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Contributor guide for AI agents working on this repo. Humans: see README.md and CONTRIBUTING.md.
What this repo is
skills is Yesterday's PUBLIC plugin catalog. Two kinds of source content:
- Standalone skills under
./skills/<category>/<slug>/SKILL.md(+ optional.plugin.json) - Bundle plugins under
./plugins/<name>/plugin.json(canonical) with optionalskills/subfolder
A single Node script (compile.mjs) discovers both and produces .compiled/skill-plugins/ plus .compiled/marketplace.json. The marketplace is exposed at ./.claude-plugin/marketplace.json and ./.cursor-plugin/marketplace.json as copies. Nothing in the tree is a symlink -- a Windows checkout turns a symlink into a text file and every install fails on it (decision 2026-09-03 in .ytstack/DECISIONS.md).
Hard rules (do not violate)
- PUBLIC repo. No leaks. Never write Yesterday-internal references (repo names ending in
-internal, internal infra hostnames, internal Slack/Linear refs, refactor-history phrases like "promoted from temp-home in xxx-internal") into user-facing fields (descriptions, READMEs, frontmatter). Run.agents/skills/audit-skills/before claiming done. - Never edit
.compiled/. Always edit sources and runnode compile.mjs. The generated tree is wiped on every build. - Never reintroduce
versioninplugin.json. Decision in.ytstack/DECISIONS.md: rely on git SHA so updates propagate. - Slug = parent folder name. Don't rename folders without updating cross-references; collisions are skipped with a warning.
marketplace.jsonc(if present in.compiled/) is a one-shot reference template, not a build input. Don't reintroduce a JSONC parser.
Common tasks
| Task | Where to edit |
|---|---|
| Author / promote a skill (guided) | skills/operations/create-shareable-skill/SKILL.md -- walks intake → quality gate → placement → scaffold → compile + audit → docs → PR |
| Add a standalone skill | skills/<category>/<slug>/SKILL.md (+ optional .plugin.json), then node compile.mjs |
| Add a bundle | plugins/<name>/plugin.json (canonical), then node compile.mjs |
| Add an external plugin (github-hosted) | marketplace.json (top-level, plugins[] array), then node compile.mjs |
| Tweak top-level catalog metadata | marketplace.json (name, description, owner, allowCrossMarketplaceDependenciesOn) |
| Audit before publishing | .agents/skills/audit-skills/SKILL.md (run inline command) |
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.
- yesterday Changed · +50 tokens per session b54e145e9792
- 6d ago First seen · 69 lines · 962 tokens per session scan A f207941d94ad
skills AGENTS.md is an instructions file published in the GitHub repository Yesterday-AI/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 1,012 tokens to every session, about $0.0051 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).
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.
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.