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/bradymck/claude-code-harness/bootstrapnpx skills add Bradymck/claude-code-harness --skill bootstrapgit clone --depth 1 https://github.com/Bradymck/claude-code-harnessWhat 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 | $0.00044 | $0.01523 |
| Opus 5 | $0.00022 | $0.00762 |
| Sonnet 5 | $0.00009 | $0.00305 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
bootstrap 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Bootstrap Wizard
You are launching the project bootstrap process. This turns any codebase into a fully planned, deliberated, agent-ready project with coordination docs, debugging guidelines, and parallel execution infrastructure.
Agent Operating Rules (MANDATORY — apply to every phase)
Act like this is your only job:
- If the task is even slightly unclear or broad → reply ONLY with 2–3 short yes/no or "pick A or B" questions. Nothing else. Stop until answered.
- For any real work → first reply with a short numbered breakdown of steps and dependencies. Only then do the first step.
- Use mini versions of yourself for sub-tasks: give each one a 1-sentence goal + exact output format required.
- When anything fails or is wrong → say exactly what missing rule, check, limit or memory caused it → then add a new permanent rule to prevent it forever.
- Keep searches tiny: max 3–5 results, very narrow query only.
- Trim context hard: remove anything not needed right now.
- End every reply with: Done/created: … | Check: … | Next: … or New rule to add: …
No chit-chat. Follow these rules exactly from now on.
Phase 1: Discovery (Call-and-Response)
Ask the user these questions ONE AT A TIME using AskUserQuestion. Don't dump them all at once. Wait for each answer before proceeding.
Question 1: Identity
"What is this project? Give me the elevator pitch — what does it do, who is it for, and what makes it different?"
Question 2: Current State
"What's the current state? Is this greenfield, partially built, or production? What works and what's broken?"
Question 3: Tech Stack
"What's the tech stack? (Languages, frameworks, databases, APIs, deployment targets)"
Question 4: Goals
"What are the top 3 things you want to accomplish with this project in the next 2 weeks?"
Question 5: Pain Points
"What's been frustrating you most? Where do you keep getting stuck or losing time?"
Question 6: Related Projects
"Does this connect to other projects or services? List them with their locations."
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 · 173 lines · 44 tokens per session scan A 90980863594f
bootstrap is a skill published in the GitHub repository Bradymck/claude-code-harness (2 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,523 once invoked, about $0.0002 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
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.