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 commands/joncik91/ucai/bootstrapgit clone --depth 1 https://github.com/Joncik91/ucaiWhat 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 | $0.00014 | $0.01133 |
| Opus 5 | $0.00007 | $0.00566 |
| Sonnet 5 | $0.00003 | $0.00227 |
| Haiku 4.5 | $0.00001 | $0.00113 |
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap Project Infrastructure
You are helping a developer set up the foundational infrastructure that enables autonomous development workflows. Without tests, linting, and CI, there is no feedback loop — Claude cannot verify its own work.
Core Principles
- Minimal viable infrastructure: Scaffold the simplest thing that works, not a complete CI/CD platform.
- Real tests, not dummy tests: The example test should test an actual function in the codebase.
- Standard tools for the stack: Use what the ecosystem expects (Vitest for JS, pytest for Python, etc.).
- One approval gate: Present the plan, get approval, then scaffold everything.
Skill Loading
Before Phase 2, load relevant skills:
Skill(ucai:qa)— for test framework selection and patternsSkill(ucai:devops)— for CI pipeline scaffolding
Phase 1: Detect
Goal: Inventory what infrastructure exists and what is missing.
Scope: $ARGUMENTS (default: "all")
Actions:
- Run infrastructure detection:
Bash(node "${CLAUDE_PLUGIN_ROOT}/scripts/detect-infra.js") - Parse the JSON output to understand:
- Tech stack (language, framework, package manager)
- Test framework (detected? which one? config file?)
- Linter (detected? which one? config file?)
- Formatter (detected? which one? config file?)
- CI pipeline (detected? which platform? config file?)
- If
$ARGUMENTSspecifies a scope (test, lint, ci), filter findings to only that scope - Present findings clearly:
- "Found: [list what exists with tool names and config files]"
- "Missing: [list what needs scaffolding]"
- If nothing is missing: "Your project already has all infrastructure. You're ready for
/ship." — stop here.
Phase 2: Recommend
Goal: Propose the right tools for this stack.
Actions:
-
Based on the detected stack, recommend standard tools:
JavaScript/TypeScript:
- Test: Vitest (fast, ESM-native, compatible with Jest API)
- Format: Prettier
- Lint: ESLint (flat config)
- CI: GitHub Actions
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 · 124 lines · 14 tokens per session scan A 9c3a135947ac
bootstrap is a command published in the GitHub repository Joncik91/ucai (29 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 1,133 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 commands, from other repositories
f5-gate
Quality gate management with evidence collection.
f5-classify
Classify input files by type using content-first analysis, detect gaps, and generate coverage declaration.
f5-implement
Implement features and fix bugs with traceability.
f5-design
Generate design documents and specifications (D1-D4).
f5-import
Import documents - single, batch, analyze, or schema management.
f5-agent
Manage AI agents, personas, and get smart suggestions.