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/research-codebasenpx skills add nikeyes/stepwise-dev --skill research-codebasegit 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 | $0.00015 | $0.00808 |
| Opus 5 | $0.00008 | $0.00404 |
| Sonnet 5 | $0.00003 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
research-codebase 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Codebase
You are tasked with researching the codebase to answer user questions. Your only job is to document and explain the codebase as it exists today — never suggest improvements, critique the implementation, or recommend changes unless the user explicitly asks.
Input
Research Query: $ARGUMENTS
- If $ARGUMENTS is empty, ask the user for their research question and wait.
- If $ARGUMENTS is vague or ambiguous (e.g., "investigate tests", "look at the code"), ask the user to clarify scope before proceeding. A good research question names a specific component, flow, or concept.
- If $ARGUMENTS is clear, proceed directly.
How to research
-
Read mentioned files first. If the user references specific files, read them fully in your main context before doing anything else.
-
Investigate the question. Use whatever approach makes sense — read files directly, spawn sub-agents for parallel research, or both. The specialized agents available to you are:
- stepwise-core:codebase-locator — finds WHERE files and components live
- stepwise-core:codebase-analyzer — understands HOW specific code works
- stepwise-core:codebase-pattern-finder — finds examples of existing patterns with code
- stepwise-core:thoughts-locator — discovers relevant documents in thoughts/
- stepwise-core:thoughts-analyzer — extracts key insights from thoughts/ documents
- stepwise-web:web-search-researcher — web research (only if user explicitly asks)
When the question spans multiple components, spawn agents in parallel for efficiency.
-
Synthesize findings. Prioritize live codebase findings over historical thoughts/ documents. Include specific file paths and line numbers.
Save the research document
- If
thoughts/doesn't exist, initialize it:bash ${CLAUDE_PLUGIN_ROOT}/skills/thoughts-management/scripts/thoughts-init
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 · 86 lines · 15 tokens per session scan A cd2012c7e641
research-codebase is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 13d ago), licensed Apache-2.0. It adds 15 tokens to every session and 808 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…