masterplan AGENTS.md

A repository guide file for masterplan, a Claude Code and Codex plugin that turns brainstorming into an executable plan and tracks its progress.

In plain words
What is it for?
Use it when working on masterplan to understand its architecture, development rules, workflow, and durable planning state.
Why use it?
It tells coding agents what the project is, where to read first, and which shared policies they must follow. This reduces conflicting instructions and guesswork across repositories.

Instructions file for CodexOpenCode

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/rasatpetabit/masterplan/agents-md
Clone the repo
git clone --depth 1 https://github.com/rasatpetabit/masterplan

Made for: Codex, OpenCode.

Per session 1,277 This file is loaded in full into every session.
When invoked 1,277 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 $0.01277 $0.01277
Opus 5 $0.00639 $0.00639
Sonnet 5 $0.00255 $0.00255
Haiku 4.5 $0.00128 $0.00128

Measured 2d ago against content hash 0935b7e327ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

masterplan 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 2d 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 · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — masterplan

Central agent policy

Cross-repo AskUserQuestion/ask_user_question (AUQ), Serena, Hindsight, context-mode, and subagent/model-dispatch policy is centralized in the fleet policy. Routing resolves from the repo-local policy/workflow-map.json (a checked-in copy of the fleet workflow routing map) and the fleet dispatch policy at /srv/workflows/policy/dispatch.md. Do not duplicate or override that policy here.

What this repo is

masterplan is a Claude Code (and Codex) plugin providing the /masterplan command — a resumable brainstorm → plan → execute → finish workflow on top of obra/superpowers skills. As of v8 it is a real Node codebase, not a markdown monolith: deterministic decisions live in lib/*.mjs behind bin/masterplan.mjs (mp, unit-tested), the markdown prompt is a thin sequencer that only orders mp calls / agent dispatches / gates, and durable state lives in docs/masterplan/<slug>/state.yml. It is built in five thin layers (L0 run bundle → L4 doctor).

This file is a thin index. The full five-layer architecture and failure modes are in docs/internals.md; the public overview is README.md.

Where to read first

If you need... Read
The orchestrator prompt itself (L1 — the sequencer) commands/masterplan.md
Deterministic logic (the real "source code") lib/*.mjs behind bin/masterplan.mjs
Layer-by-layer internals + failure modes docs/internals.md index → docs/internals/{bundle-resume,wave-dispatch,plan-parser,task-verification,doctor}.md
Public-facing overview + install + usage README.md · docs/install.md · docs/verbs.md
Release history + decision rationale per version CHANGELOG.md
Cross-cutting rules (CD-1…CD-10) + plan-field contract docs/conventions/cd-rules.md · docs/conventions/plan-annotations.md
Build/test/lint + contributor discipline docs/development.md
Agent registration (CC + pi) CC: agents/masterplan:mp-* (plugin loader). pi: bin/register-pi-agents.mjs writes ~/.pi/agent/agents/bare mp-*.md only (model: is a routing-policy lane name, e.g. frontier, resolved to its lane model ref from policy/workflow-map.json; managed colon leftovers removed; --check for drift). See docs/development.md §"Never silently inline a delegated role"
Active plans (current work) docs/masterplan/*/state.yml (source of truth per CD-7)

Read the full file on GitHub · 77 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. 2d ago First seen · 77 lines · 1,277 tokens per session scan A 0935b7e327ef

Subscribe to this mod's changes

masterplan AGENTS.md is an instructions file published in the GitHub repository rasatpetabit/masterplan (9 stars, last pushed 2d ago), licensed MIT. It adds 1,277 tokens to every session, about $0.0064 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.