aoi-bootstrap

aoi-bootstrap is a skill for Codex from Ryan529616/aoi-orgware. It costs 85 tokens per session (1,641 once invoked), scanned A, original, MIT.

A guided setup process for AOI, a system that organizes project work into departments, roles, and evidence requirements. It inspects an existing Git repository and prepares a proposed configuration.

In plain words
What is it for?
Use it to inspect a project, draft and validate an aoi.toml file, preview the result, and apply it only after approving the exact candidate.
Why use it?
It reduces the risk of applying unsuitable governance settings or changing a repository before the proposed setup has been reviewed.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md; mentions Codex.

Good fit Use it to inspect a project, draft and validate an aoi.toml file, preview the result, and apply it only after approving the exact candidate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ryan529616/aoi-orgware/aoi-bootstrap
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.

Any agent
npx skills add Ryan529616/aoi-orgware --skill aoi-bootstrap
Clone the repo
git clone --depth 1 https://github.com/Ryan529616/aoi-orgware

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aoi-bootstrap

README.md
[![agentmods](https://agentmods.dev/badge/skills/ryan529616/aoi-orgware/aoi-bootstrap.svg)](https://agentmods.dev/skills/ryan529616/aoi-orgware/aoi-bootstrap)
Your own site
<a href="https://agentmods.dev/skills/ryan529616/aoi-orgware/aoi-bootstrap"><img src="https://agentmods.dev/badge/skills/ryan529616/aoi-orgware/aoi-bootstrap.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,641 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00085 $0.01641
Opus 5 $0.00043 $0.00821
Sonnet 5 $0.00017 $0.00328
Haiku 4.5 $0.00009 $0.00164

Measured 8d ago against content hash d1d2ddfb59b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aoi-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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/inspect_project.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/aoi-bootstrap/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AOI Bootstrap

Bootstrap AOI through a gated workflow:

inspect -> draft -> validate -> preview -> approve -> apply -> doctor

Keep the target repository unchanged during inspection, drafting, validation, and preview. A candidate may be written only to an external scratch path. Never apply it until the user explicitly approves the exact candidate SHA-256.

1. Inspect

Confirm that the requested root is the exact root of an existing Git worktree. Read the repository's AGENTS.md, README.md, current runbooks, and existing aoi.toml when present. Then run:

python <skill-directory>/scripts/inspect_project.py --root <repository-root>

Treat the JSON as inventory, not as authority. It intentionally does not read source contents or infer the organization.

Treat truncated, filesystem errors, linked entries, an unreadable/invalid state marker, or git.tracked_changes_checked = false as incomplete evidence. The bounded inspector intentionally does not run a full-worktree git status. Resolve the affected boundary or present it as an explicit unknown before drafting.

Stop without writing when any of these are true:

  • the path is not the exact Git worktree root;
  • the root or candidate configuration is a symlink or junction;
  • aoi.toml already exists and the user has not explicitly requested a review or interrupted-initialization recovery;
  • AOI state already exists without the same valid installed profile, is linked, or records a different Windows/WSL lock domain;
  • the user's goal, risk tolerance, or project boundary is materially unclear.

2. Draft

Read profile-schema.md and organization-heuristics.md. Combine:

  • the user's stated goal and constraints;
  • repository evidence from inspection and current docs;
  • the smallest useful set of stable specialist lanes;
  • model-agnostic capability tiers and evidence gates.

Write a candidate TOML to a scratch path outside the target repository. Keep hooks.codex.enabled = false and legacy.enabled = false unless the user explicitly requests otherwise. Do not create agents or tasks during bootstrap. If state_dir is customized, require that path to be absent or empty and include the exact directory prefix in policy.high_risk_paths.

Read the full file on GitHub · 170 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 170 lines · 85 tokens per session scan A d1d2ddfb59b6

Subscribe to this mod's changes

aoi-bootstrap is a skill published in the GitHub repository Ryan529616/aoi-orgware (2 stars, last pushed 14d ago), licensed MIT. It adds 85 tokens to every session and 1,641 once invoked, about $0.0004 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.