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 skills add 8Dionysus/aoa-skills --skill aoa-decisiongit clone --depth 1 https://github.com/8Dionysus/aoa-skillsWrote 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.
[](https://agentmods.dev/skills/8dionysus/aoa-skills/aoa-decision)<a href="https://agentmods.dev/skills/8dionysus/aoa-skills/aoa-decision"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-skills/aoa-decision/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/8dionysus/aoa-skills/aoa-decision"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-skills/aoa-decision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.01022 |
| Opus 5 | $0.00031 | $0.00511 |
| Sonnet 5 | $0.00012 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
aoa-decision 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aoa-decision
Intent
Provide one front door for durable decision work without loading three procedures into every request. Keep owner-authored decision records authoritative; indexes, retrievers, KAG packets, caches, and session evidence may locate or contextualize a record but never supply its rationale.
Trigger boundary
Select this family only after the request fits its frontmatter description. Treat an undecided option, ordinary documentation edit, current authority map, or non-decision generated/runtime drift as a different task. Lack of evidence or write authority never becomes implicit approval.
Inputs
- one decision intent and the target owner, subject, ID, path, or mismatch
- exact owner routes, records, template, index contract, and effect authority for the exact effect, target, and scope required by the selected mode
Outputs
- one typed result from
references/contract.yamlwith owner source, actual effects, verification, skipped checks, uncertainty, and stop line
Procedure
Choose exactly one mode:
| Mode | Select when | Do not select when |
|---|---|---|
find |
Existing rationale, status, supersession, or impact is requested. | A write or correction is already known to be required. |
record |
A meaningful accepted decision lacks an adequate owner record. | The choice is open, trivial, already recorded, or only needs correction. |
correct |
An existing decision record or its derived decision view is stale or wrong. | The task is pure lookup, a current non-decision source-authority conflict, or a genuinely new decision. |
- Read
references/contract.yaml, then read the selected mode reference to EOF. Do not load another mode or a retired child bundle. - Use an exact supplied owner root, decision ID, path, or source surface before discovery. Read the owner's route law before any source or generated write. If that law defines a disposable or non-VCS owner root, do not probe Git; use its named files, builder checks, and direct hashes or comparisons.
- Use a decision retriever only as an optional narrowing aid. Verify every rationale, status, supersession, and owner claim in the authored decision record.
- Execute one mode against one target. A handoff to another mode is a later selection, not an implicit continuation.
- Stop as
blocked_missing_inputbefore target reads or effects when a required owner source, accepted decision field, index contract, builder, or effect authority is unavailable. For a write, bind authorization to the exact effect, target, and scope. A current Operator or human authorization that already matches all three satisfies the approval gate without a repeated question; a new or changed effect, target, or scope requires fresh authorization. - Return the selected mode, exact source refs, result state, actual effects, verification, skipped checks, residual uncertainty, and stop line.
What ships with it
5 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.
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 Changed · +5 lines 8c0f6173d872
- 11d ago First seen · 104 lines · 62 tokens per session scan A f347426516a3
aoa-decision is a skill published in the GitHub repository 8Dionysus/aoa-skills (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,022 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
aoa-memo
AoA/Abyss durable memory and owner orientation: use when ongoing work may depend on reviewed prior decisions, provenance, lifecycle/currentness, or an existing memo artifact, even when none is named. Also use to recall, review, or evolve a candidate, export, quarantine packet, object, corpus identity, lifecycle…
git-ai-search
Search and restore AI conversation context from git history.
brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page.
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code or Codex SessionStart hook.
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log to draft the six root pages and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the brain CLI. Run it after brain-setup.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.