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 agents/8dionysus/aoa-agents/agentsgit 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/agents/8dionysus/aoa-agents/agents)<a href="https://agentmods.dev/agents/8dionysus/aoa-agents/agents"><img src="https://agentmods.dev/badge/agents/8dionysus/aoa-agents/agents.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 | $0.00000 | $0.00998 |
| Opus 5 | $0.00000 | $0.00499 |
| Sonnet 5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
AGENTS 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Applies To
This card applies to agents/ and every nested path until a nearer
AGENTS.md narrows the lane.
Role
agents/ is the source-authored agent home for aoa-agents.
It holds the repo-owned role objects and compact role-facing contract inputs
that publish into generated registries and projection surfaces.
It is not the workspace .agents/ install/export lane. .agents/ carries
operator-facing skill exports and agent-facing installs; agents/ carries
agent-layer source meaning.
Operating Card
| Field | Route |
|---|---|
| role | source-authored agent object home |
| input | role, tier, class, cohort, adjunct, and runtime-seam source edits |
| output | updated source object, source-home manifest route, regenerated reader, validation result, or stronger-owner handoff |
| owner | agents/source_home.manifest.json, nearest branch AGENTS.md, and source JSON family |
| next route | agents/README.md, agents/source_home.manifest.json, target branch AGENTS.md, owning docs, builder, validator |
| tools | scripts/validate_agent_source_home.py, scripts/build_published_surfaces.py, formation builders, projection builders |
| validation | this card's Validation section plus target family checks |
Route Stack
- Above: root
AGENTS.mdowns repo identity, boundaries, and verification. - Here:
agents/README.mdowns the source home map andagents/source_home.manifest.jsonowns the checked family topology. - Below:
agents/roles/owns role houses and their nested forms;agents/operating-model/owns cross-role tiers, orchestrators, cohorts, and runtime-seam bindings.
Read Before Editing
Read:
- root
AGENTS.md DESIGN.mdDESIGN.AGENTS.mdagents/README.mdagents/source_home.manifest.json- the nearest child
AGENTS.md - the docs named by the child route card
Owner Routes
| Need | Owner route |
|---|---|
| base role contracts | agents/roles/*/profile.json |
| agonic and assistant adjuncts | agents/roles/*/forms/ |
| tier-shaped execution posture | agents/operating-model/tiers/*.tier.json |
| orchestrator class identity | agents/operating-model/orchestrators/*.class.json |
| bounded role cohort hints | agents/operating-model/cohorts/*.pattern.json |
| role x tier runtime seam bindings | agents/operating-model/runtime-seams/*.binding.json |
| checked source-home topology | agents/source_home.manifest.json |
| generated readers | generated/ and the owning builder |
| operation topology | mechanics/ |
| role doctrine and public explanation | docs/ |
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 · 106 lines · 0 tokens per session scan A f5b972319382
AGENTS is an agent published in the GitHub repository 8Dionysus/aoa-agents (2 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 998 tokens. 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 agents, from other repositories
AGENTS
Agent "AGENTS" from 8Dionysus/aoa-memo, covering agents.md, purpose, source, route and validate.
code-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
test-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
ecosystem-doc-bridge-corpus-scanner
Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.
ecosystem-doc-bridge-handoff-author
Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.
content-fact-checker
Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.