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 agentmods add skills/nikeyes/stepwise-dev/implement-plannpx skills add nikeyes/stepwise-dev --skill implement-plangit clone --depth 1 https://github.com/nikeyes/stepwise-devWhat 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 | $0.00013 | $0.01360 |
| Opus 5 | $0.00006 | $0.00680 |
| Sonnet 5 | $0.00003 | $0.00272 |
| Haiku 4.5 | $0.00001 | $0.00136 |
Grade A, and why
implement-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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Plan
You are tasked with implementing an approved technical plan from thoughts/shared/plans/. These plans contain phases with specific changes and success criteria.
Getting Started
When given a plan path:
- Read the plan completely and check for any existing checkmarks (- [x])
- Read the original ticket if referenced
- Create a todo list to track your progress (one item per phase)
- Then follow the Phase Cycle below for each phase
Do NOT read source or test files mentioned in the plan. The delegated skills will read them. Your role is orchestrator: you understand the plan's structure and delegate execution. If you read the implementation files, you will be tempted to implement directly — that defeats the purpose of this skill.
If no plan path provided, ask for one.
Your Role: Orchestrator
Your job is to coordinate, not to implement on your own initiative:
- Understand what each phase needs to accomplish
- Delegate implementation to
/stepwise-core:tdd— let it decide what to write and when - Delegate quality checks to
/stepwise-core:bugmagnetand/stepwise-core:test-desiderata - Run verification commands and update progress
You may edit files when a delegated skill instructs you to. What you must not do is decide on your own to write code, add tests, or modify source files.
If a delegated skill reports a structural mismatch (file doesn't exist, architecture changed), STOP and ask the user:
Issue in Phase [N]:
Expected: [what the plan says]
Found: [actual situation]
Why this matters: [explanation]
How should I proceed?
Phase Cycle
For each phase in the plan, follow this cycle in order:
Step 1 — Delegate to TDD skill
Invoke /stepwise-core:tdd using the Skill tool. Pass it:
- The phase description (copy the relevant section from the plan)
- The file paths that need to be created or modified
- The success criteria for this phase
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.
- 2d ago First seen · 165 lines · 13 tokens per session scan A 4a0d3e402e77
implement-plan is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 13d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,360 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…