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 instructions/8dionysus/aoa-agents/agents-mdgit 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/instructions/8dionysus/aoa-agents/agents-md)<a href="https://agentmods.dev/instructions/8dionysus/aoa-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/8dionysus/aoa-agents/agents-md.svg" alt="Measured on agentmods" 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 | $0.01225 | $0.01225 |
| Opus 5 | $0.00613 | $0.00613 |
| Sonnet 5 | $0.00245 | $0.00245 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
aoa-agents AGENTS.md 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 today.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Root route card for aoa-agents.
Role
This repository owns role-bearing actor meaning: profile structure, role
contracts, handoff posture, memory posture, evaluation posture, operating-model
surfaces, bounded cohort hints, role specializations, and generated
agent-layer consumer seams. It also owns the meaning of agent-local
statistical questions and evidence references exposed through stats/.
It does not implement runtime autonomy and does not own skill workflow truth, technique truth, proof doctrine, memory objects, routing policy, playbook scenario canon, KAG substrate semantics, shared statistical grammar, cross-owner statistical composition, or runtime workers.
This card supplies the repository-wide route. A nearer AGENTS.md narrows it
with a local delta; neither replaces authored source, public explanation, or a
named stronger-owner contract.
Operating Map
| Field | Route |
|---|---|
| input | role, persona, handoff, posture, projection, or agent-layer operation pressure |
| output | source role object, mechanic-local contract, generated companion, decision record, or stronger-owner handoff |
| owner | source objects under agents/, operation packages under mechanics/, and route docs under docs/ |
| next route | nearest nested AGENTS.md, then the source surface, mechanic package, builder, validator, or sibling owner |
| validation | VALIDATION.md, plus the nearest local card |
Route Modes
| Route mode | Use when | First surface |
|---|---|---|
first-reading |
you need the shortest honest overview | README |
authority-boundary |
repository authority, owner split, or role-layer claim changes | CHARTER and BOUNDARIES |
system-design |
repository shape, source/generated posture, or layer relationship changes | DESIGN |
agent-surface-design |
route-card shape, agent-facing guidance, or card mesh posture changes | DESIGN.AGENTS |
source-object |
role profiles, forms, specializations, tiers, capabilities, orchestrators, cohorts, or runtime-seam bindings change | agents |
mechanic-change |
repeatable operation topology, package route, part-local contract, provenance, or validation changes | mechanics |
codex-projection |
Codex custom-agent projection, specialization eligibility, workspace install, or freshness changes | codex-projection and mechanics/codex-projection/parts/refresh-law/docs/subagent-refresh-law.md |
direction-change |
roadmap, release contour, future trigger, or repo-level direction changes | ROADMAP.md |
current-contour |
shipped surface families or root discoverability change | CURRENT_CONTOUR |
generated-surface |
generated registries, readers, or projections change | source surface -> builder -> generated output -> validator |
local-memory-port |
repo-local memo candidate, receipt, export, or local note changes | memo/AGENTS |
local-stats-port |
agent-local statistical question, contract, or reference packet changes | stats/AGENTS |
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.
- today Changed · -18 lines · -241 tokens per session 53cf2be428e2
- yesterday Changed · -50 lines · -489 tokens per session 8adc68af83dc
- 5d ago First seen · 167 lines · 1,955 tokens per session scan A 0f2ee4b4cec1
aoa-agents AGENTS.md is an instructions file published in the GitHub repository 8Dionysus/aoa-agents (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,225 tokens to every session, about $0.0061 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 instructions, from other repositories
Agents-of-Abyss AGENTS.md
AGENTS.md instructions for 8Dionysus/Agents-of-Abyss, covering agents.md, applies to, role, read before editing and boundaries.
aoa-skills AGENTS.md
AGENTS.md instructions for 8Dionysus/aoa-skills, covering agents.md, applies to, role, read before editing and boundaries.
aoa-memo AGENTS.md
AGENTS.md instructions for 8Dionysus/aoa-memo, covering agents.md, purpose and owner lane, route modes and conditional sources, authority and agent stack and memory route and stop-lines.
aif-handoff CLAUDE.md
Instructions for lee-to/aif-handoff, covering claude.md, project overview, tech stack, project structure and key entry points.
agentskit-registry AGENTS.md
AGENTS.md instructions for AgentsKit-io/agentskit-registry, covering agents.md, non-negotiable boundaries and doc-bridge.
brief-spec CLAUDE.md
Instructions for luanmorenommaciel/brief-spec, a project described as: Type-aware, evidence-backed delivery contract for AI coding harnesses. Different agents in. One predictable human handoff out.