mcp-debug: Instructions file for Codex

AGENTS.md

mcp-debug AGENTS.md is an instructions file for Codex, OpenCode from giantswarm/mcp-debug. It costs 502 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for the giantswarm/mcp-debug project. They describe local conventions for generated files, public-safe information, code style, commits, releases, and pre-commit checks.

In plain words
What is it for?
Use it when editing this repository, preparing commits or pull requests, running formatting checks, and deciding whether to update a changelog or generated release file.
Why use it?
Following these rules prevents changes from being overwritten, exposes no customer information, and keeps commits and releases consistent with the repository.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is giantswarm/mcp-debug's own configuration. It tells Codex and OpenCode how to work on mcp-debug 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 mcp-debug configures →

Reuse

Borrowing it

Nothing to install: this file belongs to giantswarm/mcp-debug. 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/giantswarm/mcp-debug/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/giantswarm/mcp-debug

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 mcp-debug AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/giantswarm/mcp-debug/agents-md"><img src="https://agentmods.dev/badge/instructions/giantswarm/mcp-debug/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 502 This file is loaded in full into every session.
When invoked 502 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 $0.00502 $0.00502
Opus 5.5 $0.00201 $0.00201
Sonnet 5.5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured today against content hash 7bb158856b4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-debug 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 today.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Giant Swarm conventions

devctl maintains this block from its template and overwrites changes to it. Instructions for this repository go in the section below. Where they differ from this block, they take precedence.

  • Never put customer names or other customer information in code, commit messages, issues or pull requests. Most Giant Swarm repositories are public, and private ones are kept ready to become public.
  • Giant Swarm's style guides are in https://github.com/giantswarm/fmt, one directory per topic (go, helm, kubernetes, prometheus, …). Read the relevant guide before you write or review that kind of code.
  • Use conventional commits for commit messages and pull request titles.
  • If .github/workflows/zz_generated.auto_release.yaml exists, GitHub Releases are written from pull request titles: do not edit CHANGELOG.md. Otherwise, add your change to CHANGELOG.md as described in https://github.com/giantswarm/fmt/blob/main/releases/changelog.md.
  • If .pre-commit-config.yaml exists, run pre-commit run --files <changed files> before committing; not every clone has the hooks installed.
  • Do not add linters, formatters or other tooling unless asked; use what the repository already has.
  • Put documentation in docs/ rather than growing README.md, which gives an overview and links into docs/. When a change affects documented behaviour, update the documentation in the same pull request.
  • If the skills of the giantswarm/claude-code plugin marketplace are not available to you and the user works at Giant Swarm, tell them once that they can install the gs-base, gs-dev and gs-godev plugins from it.
  • Go: run goimports -local github.com/giantswarm/<repository> on the files you change. CI with architect-orb fails when imports are grouped differently.

Read the full file on GitHub · 42 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. today First seen · 42 lines · 502 tokens per session scan A 7bb158856b4b

Subscribe to this mod's changes

mcp-debug AGENTS.md is an instructions file published in the GitHub repository giantswarm/mcp-debug (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 502 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 2026-11-11.

Related

mcp-debug AGENTS.md compared with instructions from other repositories

mcp-debug AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-debug AGENTS.mdgiantswarm/mcp-debugInstructions file38yesterdayApache-2.0A502Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot