Borrowing it
Nothing to install: this file belongs to MarceloCaporale/clean-process-ended. 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/MarceloCaporale/clean-process-ended/main/AGENTS.mdgit clone --depth 1 https://github.com/MarceloCaporale/clean-process-endedWrote 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/marcelocaporale/clean-process-ended/agents-md)<a href="https://agentmods.dev/instructions/marcelocaporale/clean-process-ended/agents-md"><img src="https://agentmods.dev/badge/instructions/marcelocaporale/clean-process-ended/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/marcelocaporale/clean-process-ended/agents-md"><img src="https://agentmods.dev/badge/instructions/marcelocaporale/clean-process-ended/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 | $0.01167 | $0.01167 |
| Opus 5.5 | $0.00467 | $0.00467 |
| Sonnet 5.5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
clean-process-ended 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
This repository is optimized for MCP-compatible AI agents, coding workflows and maintainers who need a fast, accurate map of the public surface.
Public name vs package names
- Public repository name:
clean-process-ended - npm package name:
clean-process-ended - MCP Registry name:
io.github.marcelocaporale/clean-process-ended - Main MCP command:
clean-process-ended-mcp - Local CLI commands:
cpe-scan,cpe-run
What this project is
- A local-first MCP process janitor for coding-agent workflows.
- A diagnostic and dry-run-first close-session tool.
- An ownership-first classifier that separates
owned_current_session,related_unownedandunknown_owner. - A managed lifecycle wrapper for subprocesses that should carry explicit process evidence.
- A source of sanitized receipts and audit bundles that can optionally be referenced by
codex-agent-mem.
What this project is not
- Not an automatic process killer.
- Not a name-based cleanup script.
- Not a daemon or OS service by default.
- Not a guarantee that every MCP host will call its tools after installation.
- Not a tool that should clean
related_unownedorunknown_ownerby default. - Not a secrets vault; command lines are not stored by default and should not be included in public evidence.
Working rules for agents
- Preserve the dry-run-first public surface.
- Never make real cleanup, auto-cleanup terminate or
--no-dry-runthe default. - Keep cleanup claims tied to explicit ownership evidence and policy gates.
- Keep compatibility with the optional
codex-agent-memreceipt contract. - Keep public docs free of private LAB paths, local audit dossiers and personal machine routes.
- Keep the language READMEs equivalent in content across languages.
- Do not tag, release, publish to npm or change GitHub release state from a dirty tree.
Fastest commands
npm ci
npm test
npm run check:syntax
npm run smoke:stdio
npm run validate:package:strict
npm run public-tree:check
npm run public-beta-candidate
node .\bin\cpe-scan.js janitor-discovery --client codex --json
node .\bin\cpe-scan.js session-close-check --project-key my-project --json
node .\bin\cpe-scan.js audit-bundle --output-dir .\evidence\cpe --json
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 · 135 lines · 1,167 tokens per session scan A 475ab72689b6
clean-process-ended AGENTS.md is an instructions file published in the GitHub repository MarceloCaporale/clean-process-ended (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,167 tokens to every session, about $0.0047 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.
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.