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 gylove1994/superpowers-deepseek-v4 --skill writing-plansgit clone --depth 1 https://github.com/gylove1994/superpowers-deepseek-v4Wrote 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/gylove1994/superpowers-deepseek-v4/writing-plans)<a href="https://agentmods.dev/skills/gylove1994/superpowers-deepseek-v4/writing-plans"><img src="https://agentmods.dev/badge/skills/gylove1994/superpowers-deepseek-v4/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/gylove1994/superpowers-deepseek-v4/writing-plans"><img src="https://agentmods.dev/badge/skills/gylove1994/superpowers-deepseek-v4/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 | $0.00054 | $0.02364 |
| Opus 5 | $0.00027 | $0.01182 |
| Sonnet 5 | $0.00011 | $0.00473 |
| Haiku 4.5 | $0.00005 | $0.00236 |
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 12d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
Produce a comprehensive implementation plan from a Done spec. Assume the implementing engineer has zero context for our codebase and questionable taste: spell everything out — files, code, expected output, commits. DRY, YAGNI, TDD, frequent commits.
Track the full spec-to-plan process in a *-plan-progress.md file. Mid-process never commits; only Status: Done or Status: Abandoned commits.
Announce at start: "I'm using the writing-plans SKILL."
Step 0 (strict first step): Invoke resume-planning
Always invoke superpowers-deepseek-v4:resume-planning first. It:
- Forces selection of a Done source spec.
- Scans existing plan-progress files for that spec.
- Returns one of:
proceed-with-new-empty+ source spec path (no existing plan-progress for this spec, or user chose new)- A path of an In Progress file to continue (option A)
- A new file path (Based On a Done or Abandoned plan-progress) plus the prior file's content as context
Step 0.5: Worktree consent (before first file write)
Before creating or modifying the plan-progress, plan, spec, or any other project file: Invoke superpowers-deepseek-v4:confirming-worktree-before-edit
Step 1: Initialize the plan-progress file
Use skills/resume-planning/templates/plan-progress-template.md as the verbatim base. Fill the metadata header:
Date Started: <today>Status: In ProgressCurrent Phase: draft_writingSource Spec: <path from Step 0>Based On:(only if resume returned a new-based-on path)Last Updated: <now>
Populate Context Reference:
Source Spec Summary— extract Problem + Goals (or equivalent) from the source spec.User's Launch Instruction— the user's message that triggered this writing-plans invocation, verbatim.
Step 2: Scope check
If the source spec covers multiple independent subsystems, the brainstorming phase should have decomposed it already. If you nonetheless find the spec sprawls into independent areas, push back: suggest splitting into multiple plans — one per subsystem — each producing working, testable software on its own. Record any such decomposition in the plan-progress file (as plain note, not a Q&A — plan-progress has no Q&A section).
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.
- 12d ago First seen · 204 lines · 54 tokens per session scan A 48d5b642b6fb
writing-plans is a skill published in the GitHub repository gylove1994/superpowers-deepseek-v4 (10 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 2,364 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.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.