aod.project-plan

An implementation-plan generator that turns an approved specification into a technical plan reviewed by a product manager and an architect. An implementation plan describes how the software work will be carried out.

In plain words
What is it for?
Use it to validate the specification, load project context, generate plan phases, handle requested changes, and record approval.
Why use it?
It creates a shared plan before task breakdown begins and makes important product and technical decisions subject to review.

Command for Claude Code

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 commands/davidmatousek/agentic-oriented-development-kit/aod.project-plan
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/agentic-oriented-development-kit

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,253 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00017 $0.03253
Opus 5 $0.00009 $0.01626
Sonnet 5 $0.00003 $0.00651
Haiku 4.5 $0.00002 $0.00325

Measured 2d ago against content hash 403a051f9ba3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aod.project-plan 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.

Origin

This is a copy

100% identical to aod.project-plan — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/aod.project-plan.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

Consider user input before proceeding (if not empty).

Step 0: Parse --autonomous

  1. If $ARGUMENTS contains --autonomous:
    • Set autonomous = true
    • Strip --autonomous from $ARGUMENTS (trim extra whitespace)
  2. Default: autonomous = false

Step 0y: Parse --revision

  1. If $ARGUMENTS contains --revision:
    • Set revision_mode = true
    • Strip --revision from $ARGUMENTS (trim extra whitespace)
    • Read .aod/revision-context.md for reviewer feedback (contains reviewer name, attempt number, artifact path, and full feedback text)
    • Store feedback as revision_feedback
    • Clear governance cache explicitly: Call aod_state_clear_governance_cache "plan" so the upcoming dual review is treated as fresh regardless of mtime-staleness backstop. (Belt-and-suspenders: do NOT rely on the mtime backstop alone.)
  2. Default: revision_mode = false

Overview

Self-contained implementation planning command with automatic PM + Architect dual sign-off.

Flow: Validate spec → Setup & load context → Generate plan (phases 0-1) → Dual review (parallel) → Handle blockers → Inject frontmatter

Step 1: Validate Prerequisites

  1. Get branch: git branch --show-current → must match NNN-* pattern
  2. Find spec: specs/{NNN}-*/spec.md → must exist
  3. Parse frontmatter: Verify triad.pm_signoff.status is APPROVED (or APPROVED_WITH_CONCERNS/BLOCKED_OVERRIDDEN)
  4. If validation fails: Show error with required workflow order and exit

Step 2: Generate Plan

If revision_mode == true (re-invocation after governance rejection):

  1. Read the existing plan at specs/{NNN}-*/plan.md (do not start from scratch)
  2. Read revision_feedback from .aod/revision-context.md
  3. Apply targeted changes to address the specific issues raised by the reviewer
  4. Preserve sections the reviewer did not flag — only regenerate flagged sections
  5. Skip Phase 0 research (already completed) — jump directly to updating the flagged sections
  6. Proceed directly to Step 3 (Dual Sign-off) after updating the plan

Read the full file on GitHub · 290 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 · 290 lines · 17 tokens per session scan A 403a051f9ba3

Subscribe to this mod's changes

aod.project-plan is a command published in the GitHub repository davidmatousek/agentic-oriented-development-kit (22 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 3,253 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to aod.project-plan, differing in 0 lines, and is treated as a copy.