plan

A planning step that turns an approved product specification into a detailed build plan, linked to an exact hash of that specification.

In plain words
What is it for?
Listing the files, tests, implementation steps, and commits needed to build an approved feature.
Why use it?
It prevents development from starting with unfinished requirements and makes sure every described behavior has a corresponding task.

Skill for Claude CodeCodex

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 skills/artttj/rapid-stack/plan
Any agent
npx skills add artttj/rapid-stack --skill plan
Clone the repo
git clone --depth 1 https://github.com/artttj/rapid-stack

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 429 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00034 $0.00429
Opus 5 $0.00017 $0.00215
Sonnet 5 $0.00007 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured yesterday against content hash 8ef4aa2366f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

plugins/op/skills/plan/SKILL.md · 43 lines

What it actually says

op:plan

Think expensive, execute cheap: plan at high effort so the build can run lean.

Steps

  1. Locate the spec: the argument, else the newest docs/specs/*/spec.md with status: approved. Hard stop if not approved or Open questions is non-empty — route back to /op:spec.

  2. Effort check: suggest max for this step (arrow-choice).

  3. Compute the spec pin (body = everything after the closing frontmatter ---):

    awk 'c==2{print} /^---$/{if(c<2)c++}' docs/specs/<slug>/spec.md | shasum -a 256 | cut -c1-12

  4. Write docs/specs/<slug>/plan.md:

---
spec: docs/specs/<slug>/spec.md
spec-version: <12-hex pin>
status: draft
---
# <title> — build plan

## Tasks

### Task 1: <name>
- Files: exact paths to create or modify
- Tests: the failing test to write first, named from the spec's Tests section
- Steps: write test → see it fail → implement → see it pass → commit

(one section per task; every spec Behavior maps to a task; every task ends committable)
  1. Self-check against the spec: every Behavior covered, no placeholders, exact paths. Fix inline.
  2. Sign-off gate (arrow-choice): sign off / revise / abandon. On sign-off → status: signed-off, commit (docs: add <slug> plan), offer /op:build.
  3. Re-run: /op:plan on a spec that already has a plan regenerates plan.md fresh (new pin). It never edits the spec.

Proof at end: plan path, pin value, status.

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. yesterday First seen · 43 lines · 34 tokens per session scan A 8ef4aa2366f5

Subscribe to this mod's changes

plan is a skill published in the GitHub repository artttj/rapid-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 429 once invoked, about $0.0002 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.