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.
npx skills add strigov/superpowers-strigov-ver --skill writing-plansgit clone --depth 1 https://github.com/strigov/superpowers-strigov-verWrote 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.
[](https://agentmods.dev/skills/strigov/superpowers-strigov-ver/writing-plans)<a href="https://agentmods.dev/skills/strigov/superpowers-strigov-ver/writing-plans"><img src="https://agentmods.dev/badge/skills/strigov/superpowers-strigov-ver/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.
<a href="https://agentmods.dev/skills/strigov/superpowers-strigov-ver/writing-plans"><img src="https://agentmods.dev/badge/skills/strigov/superpowers-strigov-ver/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.04878 |
| Opus 5 | $0.00010 | $0.02439 |
| Sonnet 5 | $0.00004 | $0.00976 |
| Haiku 4.5 | $0.00002 | $0.00488 |
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
Overview
Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch in each phase, code, testing, docs they might need to check, how to test it. Decompose into 2–5 phases of bite-sized TDD steps. DRY. YAGNI. TDD. Frequent commits.
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Context: This should be run in a dedicated worktree (created by brainstorming skill).
Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md
- (User preferences for plan location override this default)
Model split
Same writer/reviewer pair as dev-orchestrator Steps 1–2: Opus max writes, Codex Sol max reviews — writer and reviewer never share a model family.
Main thread (orchestration only): announces, gathers context, assembles the writer prompt from the guidance below, dispatches the Opus plan writer, runs the Codex review loop, commits, offers execution options. Never writes the plan directly.
Opus subagent (max thinking) writes the plan. Invocation per ../dev-orchestrator/opus-plan-writer-prompt.md:
Agent(subagent_type="general-purpose", model="opus", prompt=<assembled prompt>)
The prompt's literal first line MUST be ultrathink. There is no task id to record — every writer dispatch is fresh; the plan file on disk and the ledger are the continuity, so revisions re-read the plan instead of resuming a thread. The subagent has no session context; the prompt must be fully self-contained and include:
- The Mode A opening block from
../dev-orchestrator/opus-plan-writer-prompt.md(research-the-repo / write-plan-file-only framing, no-git rule). - User's original request verbatim.
- Spec file path if available (e.g. when called after brainstorming) — otherwise paste the relevant requirements directly into the prompt.
- Repo root (absolute path), language/framework, any constraints you know.
- Target plan path:
docs/plans/YYYY-MM-DD-<slug>.md(unless user specified a custom location). - All the guidance in this skill below (Scope Check through Self-Review) — these sections define HOW the writer must build the plan. Paste them into the prompt; don't just reference this skill.
- Instruction to run the Self-Review inline after writing, fixing issues in place (no separate round trip).
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.
- 11d ago First seen · 250 lines · 21 tokens per session scan A 86545dc75591
writing-plans is a skill published in the GitHub repository strigov/superpowers-strigov-ver (4 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 4,878 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…