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/ryan529616/aoi-orgware/codexnpx skills add Ryan529616/aoi-orgware --skill codexgit clone --depth 1 https://github.com/Ryan529616/aoi-orgwareWhat 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 | $0.00059 | $0.02457 |
| Opus 5 | $0.00030 | $0.01229 |
| Sonnet 5 | $0.00012 | $0.00491 |
| Haiku 4.5 | $0.00006 | $0.00246 |
Grade A, and why
aoi 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 3d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Govern work with AOI
This is a user-scope, cross-project skill. Project-specific paths, architecture,
tool flows, evidence requirements, and exclusions belong in that project's
AGENTS.md, aoi.toml, and current source/docs—not in this skill.
AOI is a cooperative procedural guardrail for authority, exact claims, evidence, checkpoints, jobs, and bounded delegation. It is not a filesystem sandbox.
Client-adapter authority boundary
This skill is only a client_adapter_only guide shipped inside the same exact
AOI distribution as the CLI/runtime. It does not define or grant governance
authority. The installed CLI/runtime, ledger, aoi.toml, .aoi/POLICY.md, and
repository instructions remain authoritative when this prose disagrees with
them. aoi doctor must report the package-bound Codex client skill as exact
before relying on it for governed work; a missing, drifted, uninspectable, or
legacy-unbound skill must not be treated as current policy.
For this unpublished ARISE Operational Alpha candidate (not a complete v0.5
release), current schema-v3 hooks can be created only from reviewed local-v2
exact-wheel proof. Public schema-v1 receipts are readable and historically
upgradable, but cannot newly enable current hooks; the public current-hook route
is deferred. With hooks disabled, missing, drifted, or user-path-uninspectable
adapter status is warning/status only and does not block doctor; corrupt
receipt/schema/package/wheel provenance remains blocking. The skill never turns
any of those states into governance authority.
The user-scope install is a transitional compatibility surface for this release. A repository-scoped skill or stable bootstrap contract is future work; do not interpret this layout as the final multi-repository/company architecture.
Establish the project and executable
- Find the exact Git worktree root.
- Read every applicable
AGENTS.md. - Read
aoi.toml,.aoi/POLICY.md, and the short.aoi/INDEX.mdwhen present. - Run
aoi --version,aoi status --json, andaoi chief-status --json. - For current schema-v3 hooks, inspect the recorded absolute venv Python
command
-I -B -m aoi_orgware.codex_hookand use its sibling absoluteaoiCLI for read-only checks. The pipaoi-codex-hooklauncher is v1/v2 historical/diagnostic only; do not promote its local-v2 console/bridge evidence into current-hook authority.
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.
- 3d ago First seen · 271 lines · 59 tokens per session scan A 171af2f57777
aoi is a skill published in the GitHub repository Ryan529616/aoi-orgware (2 stars, last pushed 9d ago), licensed MIT. It adds 59 tokens to every session and 2,457 once invoked, about $0.0003 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
takt
TAKT ワークフローエンジン。codex exec でサブエージェントを起動し、ワークフロー YAML（steps / initialstep）に従って マルチエージェントオーケストレーションを実行する。.
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
codebase-context-extractor
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
deep-researcher
Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources.
llmtornado-tutorial-generator
Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.
skill-creator
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.