Borrowing it
Nothing to install: this file belongs to joao-aires/agent-skills-public. 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/joao-aires/agent-skills-public/main/AGENTS.mdgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/agents-md)<a href="https://agentmods.dev/instructions/joao-aires/agent-skills-public/agents-md"><img src="https://agentmods.dev/badge/instructions/joao-aires/agent-skills-public/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/joao-aires/agent-skills-public/agents-md"><img src="https://agentmods.dev/badge/instructions/joao-aires/agent-skills-public/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 | $0.01036 | $0.01036 |
| Opus 5.5 | $0.00414 | $0.00414 |
| Sonnet 5.5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
agent-skills-public 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
Source and ownership
- Edit owning sources under
plugins/<bundle>/:plugin.json,skills/<name>/SKILL.md, neighboring resources and package-root framing. Build output is generated. - Use the ownership map to locate a capability.
agent-depot.jsonowns accepted artifact commits, destinations and per-artifactmetadata.packaging;agent-depot.lock.jsonowns snapshot identities. Managed upstream folders are immutable inputs; the builder applies adaptations only to generated bundles. - Keep packages self-contained. Preserve original strategy/visual resources, complete upstream groups, native invocation controls and licenses. Acquire public sources through Agent Depot at reviewed artifact commit pins and record adaptations in notices; never redistribute private installed skills.
For acquisition and updates, follow upstream maintenance. Ordinary builds use committed resources and never fetch upstream repositories.
Architecture and authoring
- Preserve independently useful generic activities, application disciplines, technical expertise and supporting capabilities. Development is the default build; technical packages are explicit additions and do not select an application stack.
- Select optional expertise by capability and actual available descriptions, without hardcoded cross-package names or a dependency resolver. Required same-package resources may use precise relative links. Without a specialist, retain acceptance standards using project evidence, general expertise and primary sources; distinguish missing guidance from missing tools or decisions.
- Write decision principles with applicability and completion evidence. Keep ordinary implementation choices with the project and agent; reserve strict sequences for real dependencies. Link conditional detail with a reading trigger, and keep each rule with its owner.
- Explain the working method and consequential reasoning in language a contributor can follow. Use checklists to support that explanation. Choose paragraphs, lists, sequences and tables according to meaning; use the authoring guidance when rewriting skills.
- Generalize findings into decision guidance; put concrete reproductions in
evals/or justified deterministic tests. Avoid incident-specific prohibition lists, generated applications, scaffolds and mandatory process machinery. - Preserve explicit-only activity controls and the requested action scope. Descriptive metadata does not enforce permissions. Add MCP connections or client hooks only for a concrete need with documented setup.
- Use lowercase kebab-case: short activities for tasks and recognizable disciplines for support. Preserve upstream names and established operations terminology. Rename folders, frontmatter and maintained references together; record old names in migration notes without duplicate aliases.
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 · +3 lines · +121 tokens per session 143700858a21
- 2d ago Changed · +33 lines · +522 tokens per session 6b0af5055bd5
- 7d ago Changed · +2 lines · +115 tokens per session 5ab38dc6cabd
- 10d ago Changed · +4 lines · +93 tokens per session a0c43d445f71
- 11d ago First seen · 10 lines · 185 tokens per session scan A 5b95b09bcbe7
agent-skills-public AGENTS.md is an instructions file published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 1,036 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 2026-10-11.
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.