writing-plans

writing-plans is a skill for Claude Code from brunob54/superpowers-orchestrator. It costs 57 tokens per session (7,862 once invoked), scanned A, original, MIT.

A guide for turning an approved software design into a detailed implementation plan. The plan is saved in a prescribed documentation folder and includes the order of work and verification commands.

In plain words
What is it for?
It breaks requirements into executable tasks, follows test-driven development ordering, records how to verify each step, and saves the plan using the project's required folder structure.
Why use it?
It gives another developer or coding agent enough detail to carry out the work with fewer open questions. It also keeps testing and verification steps in the right order.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code.

Part of the superpowers-orchestrator plugin — 28 skills, 2 agents, 6 hooks shipped together

Good fit It breaks requirements into executable tasks, follows test-driven development ordering, records how to verify each step, and saves the plan using the project's required folder structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brunob54/superpowers-orchestrator/writing-plans
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.

Any agent
npx skills add brunob54/superpowers-orchestrator --skill writing-plans
Clone the repo
git clone --depth 1 https://github.com/brunob54/superpowers-orchestrator

Made for: Claude Code.

Or install superpowers-orchestrator, the plugin that ships this one along with the rest of its 28 skills, 2 agents, 6 hooks.

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 writing-plans

README.md
[![agentmods](https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/writing-plans/github.svg)](https://agentmods.dev/skills/brunob54/superpowers-orchestrator/writing-plans)
Your own site
<a href="https://agentmods.dev/skills/brunob54/superpowers-orchestrator/writing-plans"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/writing-plans/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 writing-plans

Your own site · 80×15
<a href="https://agentmods.dev/skills/brunob54/superpowers-orchestrator/writing-plans"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,862 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00057 $0.07862
Opus 5 $0.00028 $0.03931
Sonnet 5 $0.00011 $0.01572
Haiku 4.5 $0.00006 $0.00786

Measured yesterday against content hash a2568e26887a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

writing-plans 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.

skills/writing-plans/SKILL.md · 526 lines

How it starts

The opening of the file, as written. The whole thing — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Plans

Create an implementation plan another agent can execute with minimal ambiguity.

Output Path

Derive the topic folder from the spec path (the derivation rule and the folder shape are defined in the "Artifact Layout" section of skills/brainstorming/SKILL.md): the spec must be <D>/specs/<file> where <D> is a direct child of docs/superpowers-orchestrator/ at the repository root and <D>'s basename matches ^[0-9]{4}-[0-9]{2}-[0-9]{2}-[a-z0-9]+(-[a-z0-9]+)*$. Then <D> is the topic folder, its basename is <date>-<slug>, and <slug> is that basename minus the date prefix.

Save to docs/superpowers-orchestrator/<date>-<slug>/plans/<slug>.md, creating plans/ if it does not exist.

  • User preferences for plan location override this default.
  • A spec that is outside the layout is handled by "Spec Outside the Layout" below — do not write a plan next to it.

Spec Outside the Layout

A spec whose path is not <D>/specs/<file> — where <D> is a direct child of docs/superpowers-orchestrator/ at the repository root whose basename matches the topic-folder shape defined in the "Artifact Layout" section of skills/brainstorming/SKILL.md — gets no plan written beside it. The specs/ segment is required: the general derivation rule in that section also accepts <D>/plans/<file>, but a spec sitting in a plans/ folder is outside the layout and gets the offer below, exactly as this task's "Does NOT cover" note states. The invariant this protects: every plan lives in a topic folder together with its spec.

  1. Compute <slug> = the spec basename with YYYY-MM-DD-, -design and .md stripped, each only if present, then normalized by the "Slug" rule in the "Artifact Layout" section of skills/brainstorming/SKILL.md (the same normalization brainstorming applies to a topic name). Without it, a basename such as MyFeature-design.md yields a folder name that fails the layout check, and the offer below repeats on every run.
  2. Name the expected location: docs/superpowers-orchestrator/<today>-<slug>/specs/<slug>-design.md. If a folder matching docs/superpowers-orchestrator/????-??-??-<slug>/ already exists, reuse that folder instead of <today> (slug uniqueness). More than one match → stop and report the ambiguity; write nothing. If the reused folder already holds specs/<slug>-design.md or its specs/<slug>-design-review-log.md sidecar, stop and report the collision — a different spec already owns that slug — and move and write nothing.
  3. State the reason the spec is outside the layout — wrong parent directory, or a folder name that does not match ^[0-9]{4}-[0-9]{2}-[0-9]{2}-[a-z0-9]+(-[a-z0-9]+)*$ — next to the expected location, so a spec already in the right place but wrongly named is never described as a move onto itself.
  4. Ask the user once whether to move the spec there.
    • Yes: mkdir -p the destination specs/ folder first (git mv fails when the destination directory does not exist), then git mv the spec to specs/<slug>-design.md and — when it exists — its -review-log.md sidecar to specs/<slug>-design-review-log.md. A file git does not track yet (git ls-files --error-unmatch <path> fails — the normal state of a spec that was written and never committed) cannot be moved with git mv: move it with plain mv and git add the destination path instead. Use plain mv when the project is not a git repository. The sidecar is renamed together with the spec because the sidecar rule derives the log name from the document name: a sidecar that kept its old basename would be orphaned and a later spec review would start a new log. Then continue with the moved spec.
    • No: stop. No plan is written.

Read the full file on GitHub · 526 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. yesterday Changed · +105 lines a2568e26887a
  2. 5d ago Changed · +136 lines 97c4af28b377
  3. 10d ago First seen · 285 lines · 57 tokens per session scan A eb5f02d336cf

Subscribe to this mod's changes

writing-plans is a skill published in the GitHub repository brunob54/superpowers-orchestrator (3 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 7,862 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

github-pr-review

Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…

fvadicamo/dev-agent-skills · 95 tokens

privacy-guard

Prevents private infrastructure details (node hostnames, internal project names, local usernames and personal emails, absolute home paths, private and VPN IP ranges) from leaking into public repositories through commits, PRs, docs or release artifacts. Use when working in a public or soon-to-be-public repo, before…

fvadicamo/dev-agent-skills · 128 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens

github-pr-merge

Merges GitHub Pull Requests after validating pre-merge checklist. Use when user wants to merge PR, close PR, finalize PR, complete merge, approve and merge, or execute merge. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge cleanup.

fvadicamo/dev-agent-skills · 72 tokens

git-commit

Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.

fvadicamo/dev-agent-skills · 49 tokens

qa

Code review + QA vs Acceptance Criteria, including A+ status suggestions and review comment draft.

sequant-io/sequant · 20 tokens