Borrowing it
Nothing to install: this file belongs to acolomba/pi-claude-marketplace. 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/acolomba/pi-claude-marketplace/main/AGENTS.mdgit clone --depth 1 https://github.com/acolomba/pi-claude-marketplaceWrote 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/acolomba/pi-claude-marketplace/agents-md)<a href="https://agentmods.dev/instructions/acolomba/pi-claude-marketplace/agents-md"><img src="https://agentmods.dev/badge/instructions/acolomba/pi-claude-marketplace/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/acolomba/pi-claude-marketplace/agents-md"><img src="https://agentmods.dev/badge/instructions/acolomba/pi-claude-marketplace/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 | $0.03061 | $0.03061 |
| Opus 5.5 | $0.01224 | $0.01224 |
| Sonnet 5.5 | $0.00612 | $0.00612 |
| Haiku 4.5 | $0.00306 | $0.00306 |
Grade A, and why
pi-claude-marketplace 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 3d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-claude-marketplace
Guidelines
General
Before editing any file, read it first. Before modifying a function, trace its callers. Research before you edit.
Git
- NEVER commit to the main branch.
- Branch names:
main,features/*,releases/*, andagent-*for temporary agent worktree branches. New feature branches usefeatures/<name>. - Commit as
.agents/skills/committing/SKILL.mddescribes: its message format also applies to PR titles. NEVER use--no-verifyto skip the hooks. - NEVER rebase, never rewrite history. Update branches by merging.
- When writing PR descriptions, use the
simple-englishskill in Plain mode and thehumanizerskill, if available. - Always use
--squashwhen merging PRs (gh pr merge --squash). The repository does not allow merge commits or rebase merges. - Before merging a PR that ships a GSD milestone, audit and close the milestone (
/gsd-audit-milestone, then/gsd-complete-milestone) on the PR branch, so the archive lands in the same squash.
GSD records
- Prefix each
gsd-tools windows append --descriptionwith the milestone, such as[workflows-replay]. Phase numbers can repeat across milestones. Do not put the milestone in--phaseor hand-edit.planning/WINDOWS.md. - Include
## Threat Flagsin every planSUMMARY.md, even when the answer is "None":
## Threat Flags
None -- no security-relevant surface outside the plan's `<threat_model>` was introduced.
Build verification
Read .agents/skills/local-verification/SKILL.md when planning or running checks. A build input is a file that a build or a CI job reads. When a staged file is a build input, the pre-commit hook runs npm run check:commit. It runs the static checks, the unit tests that have no source pair, and direct coverage for the staged source-test pairs. It runs all pairs when the commit stages shared test support, the test tooling, or a dependency file. A passing hook is not a full verdict, and it cannot satisfy a GSD gate. GSD gates run npm run check on the combined tree: the post-merge gate of each wave, the phase gate, the merge gate, and the final PR or release handoff. npm run check runs what pull request CI runs, except the e2e tests and ESLint with an empty cache. A merge does not run the hook. So a quick task that commits a build input runs npm run check in the main checkout after its worktree is merged, before the task finishes. A gate can reuse a passing result for the same inputs, as the skill defines. This project policy governs the TypeScript and GSD skill instructions.
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.
- 3d ago Changed · +4 lines · +105 tokens per session 9b1d329f5304
- 7d ago Changed · +57 tokens per session 8cd79cf73b83
- 15d ago Changed · -23 lines · -896 tokens per session 6f5dce961758
- 18d ago Changed · +44 tokens per session 2a6b9472a92b
- 19d ago Changed · +17 tokens per session 1348f00fab7b
- 23d ago Changed · -8 lines · +103 tokens per session 85694bc393f9
- 28d ago Changed · +4 lines · +186 tokens per session eb6028e12f3d
- 29d ago Changed · +1 lines · +51 tokens per session 5c7c68bbc57a
- 1mo ago Changed · -11 lines · -426 tokens per session 2bd975c74692
- 1mo ago First seen · 198 lines · 3,820 tokens per session scan A e419c10e4dec
pi-claude-marketplace AGENTS.md is an instructions file published in the GitHub repository acolomba/pi-claude-marketplace (28 stars, last pushed today), licensed MIT. It adds 3,061 tokens to every session, about $0.0122 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 2026-09-20.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.