Borrowing it
Nothing to install: this file belongs to lunchpaillola/pipa-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/lunchpaillola/pipa-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/lunchpaillola/pipa-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/lunchpaillola/pipa-skills/agents-md)<a href="https://agentmods.dev/instructions/lunchpaillola/pipa-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/lunchpaillola/pipa-skills/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/lunchpaillola/pipa-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/lunchpaillola/pipa-skills/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 | $0.00511 | $0.00511 |
| Opus 5.5 | $0.00204 | $0.00204 |
| Sonnet 5.5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
pipa-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 2mo 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Notes
This repository stores Pipa skills for AI agents. Pipa is the primary PM brain and command router for project delivery work.
Expectations
- Keep skill names stable once published.
- Version skills in
SKILL.mdfrontmatter undermetadata.versionand bump on every published behavior change. - Versioning policy: do not bump
VERSIONS.mdormetadata.versionduring draft/branch work. Only bump versions when changes are being finalized for merge tomain(published state). - Prefer broadly reusable workflows over company-specific process details.
- Keep proprietary orchestration, customer context, and private integrations out of this repo.
- When adding a skill, create
skills/<skill-name>/SKILL.mdfirst and add supporting material only as needed. - Update public inventory docs when a migration reaches its public-cutover slice; do not expose partial operation inventories early.
- Keep public eval artifacts generic; store client-specific eval prompts/data in
skills/<skill-name>/evals/private/(gitignored). - For connected-tool workflows, especially Composio-backed ones, prefer concise provenance in the skill contract: name the tools used and cite the specific record IDs, doc names, links, or references that materially support the answer.
- Pipa's core router lives in
skills/pipa/. The six business lanes are broad entry surfaces; meta surfaces route Pipa configuration and utilities. - A substantial workflow belongs in an operation skill whose description permits only explicit invocation or delegation from its owning lane/meta surface. Its skill owns the workflow, output contract, safety rules, and local positive/negative evals.
- Generic business language enters a lane. Explicit operation invocation wins; otherwise the lane selects one operation and preserves the user's business objective.
- References are non-routing assets such as templates, schemas, examples, source-handling rules, and shared presentation guidance. Do not keep promoted workflow bodies or fallback copies in lanes or references.
- Preserve
pipa-audio-brief,composio-mcp, andpipa-triggersas standalone breakouts unless a future plan explicitly changes that architecture. - Keep routers and lanes concise. Route to an operation by skill name and fail clearly when it is unavailable instead of embedding a compatibility copy.
docs/solutions/stores documented solutions to past problems (bugs, best practices, workflow patterns), organized by category with YAML frontmatter (module,tags,problem_type); relevant when implementing or debugging in documented areas.
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.
- 2mo ago First seen · 23 lines · 511 tokens per session scan A d5e0440a0570
pipa-skills AGENTS.md is an instructions file published in the GitHub repository lunchpaillola/pipa-skills (3 stars, last pushed 15d ago), licensed MIT. It adds 511 tokens to every session, about $0.0020 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 2026-08-31.
pipa-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pipa-skills AGENTS.mdlunchpaillola/pipa-skills | Instructions file | 3 | 15d ago | MIT | A | 511 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |