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-agents --skill aoa-agents-skillsgit clone --depth 1 https://github.com/8Dionysus/aoa-agentsWrote 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-agents/aoa-agents-skills)<a href="https://agentmods.dev/skills/8dionysus/aoa-agents/aoa-agents-skills"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-agents/aoa-agents-skills/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-agents/aoa-agents-skills"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-agents/aoa-agents-skills.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 | $0.00056 | $0.01153 |
| Opus 5 | $0.00028 | $0.00576 |
| Sonnet 5 | $0.00011 | $0.00231 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
aoa-agents-skills 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aoa-agents-skills
Turn an independent obligation into a role-bearing actor with a bounded mandate, replaceable incarnation, and explicit return owner. A role may retain identity and responsibility while no process or model instance is running.
When responsibility needs its own holder
Use judgment about the work, not the presence of an agent tool. A distinct holder is useful when a branch must be carried autonomously to a return gate, has its own authority envelope, or needs continuity beyond one process. A convenient parallel read or bounded helper does not acquire that lifecycle.
For ordinary work, continue with Codex's native workflow and delegation rules. Do not call the SDK router, mint a negative classification, or route a native helper through summon merely to establish that this skill is unnecessary. An instruction to work alone remains in force.
Before forming anything, check whether the request already identifies an obligation, actor, mandate, or return. Reuse that identity. Session resumption alone does not create a new obligation or require semantic reclassification.
Work at the current lifecycle boundary
| Situation | Relevant procedure |
|---|---|
| A new independent duty needs an actor | role-first-entry.md |
| An existing duty needs its incarnation inspected or replaced | bind-incarnation.md |
| A complete mandate must move to another holder | transfer-responsibility.md |
| An actor returns, pauses, refuses, fails, or requests wake | receive-return.md |
For a new duty, start with Goal, obligation, authority, and expected result from the request and available context. Resolve only missing facts that change the decision. Use detect-obligation.md for uncertain independence and form-actor.md for role and mandate detail; neither is a compulsory extra stage for every helper.
What ships with it
20 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.
- agents/openai.yaml 332 B
- references/actor-mandate-v1.schema.json 7.6 KB
- references/agent-obligation-v1.schema.json 3.2 KB
- references/bind-incarnation.md 2.6 KB
- references/capability-router.md 1.6 KB
- references/contract.yaml 8.2 KB
- references/delegation-classes.md 4.2 KB
- references/detect-obligation.md 3.2 KB
- references/form-actor.md 3.9 KB
- references/receive-return.md 1.7 KB
- references/responsibility-classification-v1.schema.json 2.0 KB
- references/responsibility-classification.md 2.6 KB
- references/role-first-entry.md 7.6 KB
- references/role-first-intent-v1.schema.json 1.8 KB
- references/role-resolution-v1.schema.json 3.4 KB
- references/source-return.md 3.9 KB
- references/task-local-dag.md 1.6 KB
- references/transfer-responsibility.md 2.0 KB
- scripts/compile_actor_contract.py 12 KB runs code
- scripts/resolve_role_binding.py 13 KB runs code
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 Changed · -65 lines · -111 tokens per session 4b90599c9f53
- 11d ago First seen · 168 lines · 167 tokens per session scan A 4e7d6cadbb21
aoa-agents-skills is a skill published in the GitHub repository 8Dionysus/aoa-agents (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,153 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…
aoa-memo-writeback
Use only before any memo artifact exists to decide whether live-session, closeout, landed-work, PR, diff, or review evidence yields one guarded memo candidate, export, or no-write result. If a concrete memo candidate, export, object, corpus, lifecycle, or read-model target already exists, use aoa-memo. Do not use for…
aoa-eval
Select or apply an owner-local or cross-repository eval, route a confirmed no-fit to intake/design, or classify supplied session hits as eval candidates. Do not use for central proof bundles, named results or verdicts, source-linked reports, proof lifecycle, ordinary tests, undefined invariants, or generic session…
aoa-checkpoint-closeout-bridge
Carry provisional checkpoint hints into a reviewed session closeout: harvest, progression, quest-promotion, and branch handoff. Use to collect bounded hints or execute after the current session artifact is closed and reviewed. Do not use mid-session for final judgment, without reviewed evidence, as a hidden playbook…
aoa-knowledge-stewardship
Sanitize private technical material into a public-safe owner-bounded derivative, or resolve authority among authored, generated, runtime, and installed sources. Use for governed incidents, logs, configs, diagnostics, or conflicting source roles. Do not use for ordinary editing, memo/session work, direct publication…
aoa-decision
Find, record, correct, or supersede a durable repository decision and its derived indexes. Use for prior rationale, a meaningful accepted choice, or decision-source/index drift. Do not use for ordinary documentation, an open choice, current source-authority conflicts, or runtime/generated authority mapping.