agentmods.dev

clean-process-ended AGENTS.md

clean-process-ended AGENTS.md is an instructions file for Codex, OpenCode from MarceloCaporale/clean-process-ended. It costs 1,167 tokens per session, scanned A, original, Apache-2.0.

Project instructions for clean-process-ended, a local MCP tool that diagnoses and manages processes created during coding-agent sessions. It uses dry runs, tracks ownership, and can create sanitized audit records.

In plain words
What is it for?
It helps inspect ended sessions, classify processes, manage subprocess lifecycles, run scans or cleanup checks, and preserve process evidence for audits.
Why use it?
It helps distinguish processes belonging to the current session from related or unknown processes, reducing the risk of cleaning up the wrong ones.

Instructions file for CodexOpenCode

not rated 2 4mo ago A scan 1,167 tokens original Apache-2.0
View the source file MarceloCaporale/clean-process-ended
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/marcelocaporale/clean-process-ended/agents-md
Clone the repo
git clone --depth 1 https://github.com/MarceloCaporale/clean-process-ended

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for clean-process-ended AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/marcelocaporale/clean-process-ended/agents-md.svg)](https://agentmods.dev/instructions/marcelocaporale/clean-process-ended/agents-md)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 1,167 This file is loaded in full into every session.
When invoked 1,167 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01167 $0.01167
Opus 5 $0.00583 $0.00583
Sonnet 5 $0.00233 $0.00233
Haiku 4.5 $0.00117 $0.00117

Measured 5d ago against content hash 475ab72689b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 5d 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.

AGENTS.md · 135 lines

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_unowned and unknown_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_unowned or unknown_owner by 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-run the default.
  • Keep cleanup claims tied to explicit ownership evidence and policy gates.
  • Keep compatibility with the optional codex-agent-mem receipt 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

Read the full file on GitHub · 135 lines

Changes

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.

  1. 5d ago First seen · 135 lines · 1,167 tokens per session scan A 475ab72689b6

Subscribe to this mod's changes

clean-process-ended AGENTS.md is an instructions file published in the GitHub repository MarceloCaporale/clean-process-ended (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,167 tokens to every session, about $0.0058 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.

ai-agentsclaude-codecodexcoding-agentsdeepseekdeveloper-tools
Related

Other instructions, from other repositories

DevWhale AGENTS.md

Instructions for tzz123-hub/DevWhale, covering agents.md, test commands and loop conventions.

tzz123-hub/DevWhale · 48 tokens

cherry-studio AGENTS.md

AGENTS.md instructions for CherryHQ/cherry-studio, a project described as: AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs.

CherryHQ/cherry-studio · 4 tokens

pcl copilot-instructions.md

Copilot instructions for personamanagmentlayer/pcl, covering project overview, pcl bootstrap system, core architecture principles, 1. compiler pipeline and 2. type system.

personamanagmentlayer/pcl · 8,233 tokens

matt-skills-with-to-goal CLAUDE.md

Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.

tt-a1i/matt-skills-with-to-goal · 989 tokens

ephemeral-sandbox CLAUDE.md

Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.

Ephemeral-AI-Lab/ephemeral-sandbox · 1,203 tokens

claude-code-vision-skill CLAUDE.md

Instructions for xiincs/claude-code-vision-skill, covering claude code visual inspection configuration and front-end page check workflow (mandatory).

xiincs/claude-code-vision-skill · 264 tokens