bootstrap

A minimal setup tool for adding missing AgentOps documentation and, when requested, a directory for storing durable verdict records. It never overwrites existing documents.

In plain words
What is it for?
Use it to inspect a project for canonical AgentOps documents and create only the missing files that were explicitly requested. It can also create .agents/ao/verdicts/sha256/ for local verdict storage.
Why use it?
It prevents setup from creating unwanted files or taking control of a repository's workflow. When product intent or goals are missing, it asks the caller instead of guessing.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/boshu2/agentops/bootstrap
Any agent
npx skills add boshu2/agentops --skill bootstrap
Clone the repo
git clone --depth 1 https://github.com/boshu2/agentops

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00738
Opus 5 $0.00017 $0.00369
Sonnet 5 $0.00007 $0.00148
Haiku 4.5 $0.00003 $0.00074

Measured 2d ago against content hash 3c11e215a1d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

images/gemini/skills/bootstrap/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bootstrap — minimal project setup

Bootstrap fills only explicitly requested, missing AgentOps entry documents and, when requested, the durable verdict directory. It does not initialize Git, install hooks, create tracker state, start runtimes, or impose a delivery workflow.

Never-overwrite is what makes bootstrap safe to run on any repository: a setup step that can only add is idempotent by construction, while one that can replace must first prove it understands what it is replacing.

Named failure mode — scaffold sprawl: creating files the caller never requested because a "complete" setup feels more helpful than a minimal one.

Anti-pattern: inferring product intent from directory names and READMEs to avoid asking the caller. Corrective: ask for the missing content; a wrong PRODUCT.md written confidently is worse than a question.

Procedure

  1. Inspect the target directory and report which canonical files already exist.
  2. Ask the caller for missing product intent or goal content when it cannot be inferred safely.
  3. Create only missing, explicitly requested files. Never overwrite an existing document.
  4. Create .agents/ao/verdicts/sha256/ when durable local verdict storage is requested.
  5. Validate filesystem existence and report created, skipped, and failed paths.
  6. Stop.

Typical documents are PRODUCT.md, GOALS.md, AGENTS.md, and a README section that explains the RPI traversal. Generated product copy starts from the operations-layer category and preserves the ownership boundary. Repositories remain free to use their own Git, CI, tracker, release, and deployment policies.

Naming. Three surfaces share the word "bootstrap"; they are distinct. This skill authors missing entry documents. ao init is the CLI command that creates the local evidence and verdict directories (.agents/ao/**). ao session bootstrap is a read-only session command that reports which local orientation files are present. This skill invokes neither.

Non-goals

Read the full file on GitHub · 91 lines

Changes

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.

  1. 2d ago First seen · 91 lines · 34 tokens per session scan A 3c11e215a1d3

Subscribe to this mod's changes

bootstrap is a skill published in the GitHub repository boshu2/agentops (431 stars, last pushed 4d ago), licensed Apache-2.0. It adds 34 tokens to every session and 738 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 2026-08-30.

Related

Other skills, from other repositories

brainstorm

Explore vague or ambitious ideas into a right-sized requirements-only plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning, not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or…

OutlineDriven/odin-claude-plugin · 85 tokens

doc-review

Use when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.

OutlineDriven/odin-claude-plugin · 32 tokens

audit-project

Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".

OutlineDriven/odin-claude-plugin · 50 tokens

autolearn

Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.

OutlineDriven/odin-claude-plugin · 65 tokens

doubt-driven

Doubt-driven adversarial review. Use when correctness matters more than speed, the code is unfamiliar, stakes are high, a claim can't be checked by the type system or compiler, or verifying now is cheaper than debugging later.

OutlineDriven/odin-claude-plugin · 49 tokens

drift-detect

Use when the user says "plan drift", asks whether the roadmap, plans, or docs still match the code, or is deciding what to rebuild when restarting a stalled project. For doc-vs-code drift inside a specific diff, use sync-docs.

OutlineDriven/odin-claude-plugin · 56 tokens