change-trace-mcp: Instructions file for Codex

AGENTS.md

change-trace-mcp AGENTS.md is an instructions file for Codex, OpenCode from Canlendula/change-trace-mcp. It costs 705 tokens per session, scanned A, original, Apache-2.0.

Repository instructions define how coding agents share work in a project. They assign one coordinator to review and release changes, while other agents work only on assigned tasks.

In plain words
What is it for?
Use them to set rules for agent roles, task files, allowed files, acceptance checks, handoffs, merges, and releases in a shared repository.
Why use it?
They prevent multiple agents from changing project decisions, releases, or shared files without authority. They also make worker tasks and handoffs easier to review.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; reads ~/.codex paths; mentions Codex.

This is Canlendula/change-trace-mcp's own configuration. It tells Codex and OpenCode how to work on change-trace-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything change-trace-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Canlendula/change-trace-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Canlendula/change-trace-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Canlendula/change-trace-mcp

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 change-trace-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/canlendula/change-trace-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/canlendula/change-trace-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/canlendula/change-trace-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/canlendula/change-trace-mcp/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.

agentmods 80×15 button for change-trace-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/canlendula/change-trace-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/canlendula/change-trace-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 705 This file is loaded in full into every session.
When invoked 705 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00705 $0.00705
Opus 5.5 $0.00282 $0.00282
Sonnet 5.5 $0.00141 $0.00141
Haiku 4.5 $0.00071 $0.00071

Measured 2mo ago against content hash 3a9f5c3dc2b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

change-trace-mcp 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.

AGENTS.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Agent Rules

These rules apply to every Agent session working in this repository.

Role resolution

  • One user-designated primary session is the coordinator, reviewer, and release owner.
  • Every other session or sub-agent is an implementation worker unless its task assignment explicitly identifies it as the coordinator.
  • A worker cannot promote itself to coordinator or infer coordinator authority from access to the repository.

Coordinator-only authority

Only the coordinator may:

  • modify docs/ROADMAP.md, milestone status, exit-gate status, or the global backlog;
  • modify docs/PROJECT_DECISIONS.md;
  • modify this file, docs/CONTRIBUTING_WORKFLOW.md, or the work-item templates;
  • accept or reject a worker handoff;
  • merge or cherry-pick work into main;
  • change package versions, create tags or releases, publish npm packages, or change npm dist-tags;
  • publish compatibility claims or declare a milestone/release complete.

Workers may propose any of these changes in their work-item report.

Worker requirements

  • Work only from a task file under docs/work-items/ with a task ID, base commit, scope, allowed paths, acceptance criteria, and validation commands.
  • Use an isolated branch and worktree for any write task. The primary worktree and main belong to the coordinator.
  • Stay inside the assigned scope. Stop and report needs_decision when a public contract, dependency, security policy, or product decision must change beyond the assignment.
  • Do not modify coordinator-only files, merge into main, rebase shared branches, force-push, tag, publish, or perform release actions.
  • Update only the worker-owned handoff section of the assigned work-item file.
  • Commit implementation, tests, permitted documentation, and the handoff record to the task branch. Uncommitted changes are not handoff output.
  • Report task status as ready_for_review, blocked, or needs_decision. These states do not mean the milestone is complete.
  • Include exact validation commands and results, known limitations, deviations, and decision requests in the handoff.

Read the full file on GitHub · 75 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. 2mo ago First seen · 75 lines · 705 tokens per session scan A 3a9f5c3dc2b0

Subscribe to this mod's changes

change-trace-mcp AGENTS.md is an instructions file published in the GitHub repository Canlendula/change-trace-mcp (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 705 tokens to every session, about $0.0028 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.

Related

change-trace-mcp AGENTS.md compared with instructions from other repositories

change-trace-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
change-trace-mcp AGENTS.mdCanlendula/change-trace-mcpInstructions file03mo agoApache-2.0A705Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode