agentmods.dev

godplans: Instructions file for Codex

AGENTS.md

godplans AGENTS.md is an instructions file for Codex, OpenCode from hannsxpeter/godplans. It costs 1,065 tokens per session, scanned A, original, MIT.

A project instruction file for godplans, an agent skill that creates a detailed project plan before coding begins. It also documents how the skill's source files, generated prompt, and validation checks must be maintained.

In plain words
What is it for?
Guiding project planning, maintaining the canonical skill files, regenerating the prompt, and running regular or release validation.
Why use it?
It keeps planning output and the skill's supporting files consistent and ensures changes pass the repository's checks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions Claude Code.

This is hannsxpeter/godplans's own configuration. It tells Codex and OpenCode how to work on godplans 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 godplans configures →

not rated 2repo +1 changed 28d ago A scan 1,065 tokens original MIT
View source ↗ hannsxpeter/godplans
Reuse

Borrowing it

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

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 godplans AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hannsxpeter/godplans/agents-md"><img src="https://agentmods.dev/badge/instructions/hannsxpeter/godplans/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,065 This file is loaded in full into every session.
When invoked 1,065 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 $0.01065 $0.01065
Opus 5.5 $0.00426 $0.00426
Sonnet 5.5 $0.00213 $0.00213
Haiku 4.5 $0.00106 $0.00106

Measured 28d ago against content hash e38b6aa75364, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

godplans 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 28d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repository ships the godplans Agent Skill: a planning superskill that produces a comprehensive, audit-aware master plan (.godplans/PLAN.mdx) for a software project before any code is written.

If you are an agent asked to plan a project: read skills/godplans/SKILL.md and follow its method. The skill is also installed via .agents/skills/godplans and .claude/skills/godplans projections in consuming projects.

If you are an agent working on this repository itself:

  • The canonical skill lives at skills/godplans/. It has three symlink projections: .agents/skills/godplans and .claude/skills/godplans point at it, and plugins/godplans/skills points at skills/ for the Claude Code plugin. Edit the canonical files only; the symlinks-valid lint check covers all three links (run one check with bash scripts/lint.sh <check>).
  • Three outputs are generated; never edit them by hand: PROMPT.md (scripts/build-prompt.sh), the %catalog_max and %doc_catalog tables in skills/godplans/scripts/validate-plan.sh (scripts/build-catalog.js), and evals/metrics/context-cost.json (scripts/context-metrics.js). After changing SKILL.md, a reference module, the PLAN template, the validator, or plan-halflife.sh, run npm run generate, which runs npm run catalog, npm run build:prompt, and npm run metrics:context in that order, then npm run check.
  • Style and product contracts are mechanically enforced by npm run check: ASCII punctuation only, no em or en dashes, no Unicode arrows (write ASCII ->), no emojis, no smart quotes, no box-drawing characters, in every authored file.
  • Release-grade validation uses npm run release:check with the pinned official Agent Skills validator from requirements/skills-ref.txt and an authenticated GitHub CLI. Ordinary npm run check remains offline-friendly.
  • The 19 domain modules under skills/godplans/references/ follow a fixed six-section contract (Lineage, Decisions to force, Plan requirements, Task seeds, Self-audit rubric, Anti-patterns refused); the modules-complete lint check enforces it. The five contract modules (plan-format, discovery, compliance, exemplar, doc-set) are exempt. The domain-parity check confirms that every domain module appears in the SKILL.md Phase 4 table, the validator's domain and prefix tables, the prompt build, the context metrics, the portable-prompt test, the template and discovery matrices, and the schema's row count, with its own requirement prefix.
  • The skill description lives in the SKILL.md frontmatter. Change it there first, then copy it verbatim into plugins/godplans/.claude-plugin/plugin.json and the godplans entry in .claude-plugin/marketplace.json; the description-parity lint check fails on any difference.
  • Version appears in every published surface and must agree: SKILL.md frontmatter and body, the top CHANGELOG.md entry, package.json, marketplace and plugin metadata, the PLAN template, the README version badge, and the generated PROMPT.md. npm run check checks them together: version:check and the version-parity lint check compare the surfaces, and the prompt-fresh lint check catches a stale PROMPT.md. Never hand-edit a synced version string; bump package.json and run npm run version:sync, which writes every surface except the CHANGELOG.md heading (npm run release:prepare -- <patch|minor|major|X.Y.Z> does both and stubs that heading when it is missing).
  • Never run npm run eval, npm run eval:matrix, npm run eval:outcome, or npm run eval:external without the maintainer's go-ahead. They invoke model CLIs and spend real model runs; the matrix alone runs every case, both arms, for at least three model families. npm run check, npm run eval:check, and bash scripts/eval-matrix.sh --check call no model.
  • Maintainer rituals are in MAINTAINING.md, the map of sources, generators, artifacts, and checks is in docs/ARCHITECTURE.md, and the log of drift that reviews found is in docs/DRIFT.md.

Read the full file on GitHub · 67 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. 28d ago Changed · +35 lines · +649 tokens per session e38b6aa75364
  2. 2mo ago First seen · 32 lines · 416 tokens per session scan A d56eae7e4bf1

Subscribe to this mod's changes

godplans AGENTS.md is an instructions file published in the GitHub repository hannsxpeter/godplans (2 stars, last pushed 14d ago), licensed MIT. It adds 1,065 tokens to every session, about $0.0043 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.

Claude CodePlanningagent-skillsai-agentsarchitecturecodexcursor
Related

Other instructions, from other repositories

data-scientist copilot-instructions.md

Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.

realnghon/data-scientist · 373 tokens

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,750 tokens