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 HappyMonkeyAI/AgentsProtocol --skill owner-adversary-verificationgit clone --depth 1 https://github.com/HappyMonkeyAI/AgentsProtocolWrote 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/happymonkeyai/agentsprotocol/owner-adversary-verification)<a href="https://agentmods.dev/skills/happymonkeyai/agentsprotocol/owner-adversary-verification"><img src="https://agentmods.dev/badge/skills/happymonkeyai/agentsprotocol/owner-adversary-verification/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/happymonkeyai/agentsprotocol/owner-adversary-verification"><img src="https://agentmods.dev/badge/skills/happymonkeyai/agentsprotocol/owner-adversary-verification.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 | $0.00039 | $0.00974 |
| Opus 5.5 | $0.00016 | $0.00390 |
| Sonnet 5.5 | $0.00008 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
owner-adversary-verification 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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Owner-as-Adversary Verification
Operationalizes ADR-0001. Use before marking a feature or behavior-changing slice Done, merging Worker output, or Ratcheting.
Do not use when
- Pure docs, comments, or chore with no runtime behavior
- Human explicitly accepted residual gaps in writing
- Emergency hotfix where human waives V2/V3 (record waiver in verification artifact)
Ground truth
| Use as truth | Do not treat as proof of Done |
|---|---|
| SPEC, ADR, acceptance criteria, CONTEXT | Worker “what I built” summary |
| Live URL / real API responses / DOM readback | “Tests passed” with no Owner review |
| Independent Owner tests | Worker-authored tests alone (they are V0 support, not V2) |
Rule: Worker self-report is never Done proof.
Ladder (run applicable stages)
V0 — Deterministic (always for code)
- [ ] Touched packages: test / typecheck / build green
- [ ] Failures fixed or Pulse stop — do not Ratchet red
V1 — Contract / Ripple (any boundary touch)
- [ ] Blast-radius map: callers, API types, UI fields, DB/schema
- [ ] Shared contract holds (OpenAPI / RPC / Zod / Pydantic / types)
- [ ] No silent optional field drift across UI ↔ API ↔ DB
V2 — Adversary tests (Owner only)
Spawn Owner (or parent session) with brief:
Review SPEC and ADR only. Write/run the most aggressive tests you can to disprove acceptance criteria: missing UI, dead clicks, empty states, invalid input, auth gaps, partial wiring. Do not trust the Worker narrative. Stop when criteria are evidenced or failures are listed.
- [ ] Owner ≠ Worker monologue
- [ ] Tests derived from acceptance criteria, not from implementation story
- [ ] At least one negative/empty/invalid path per critical criterion
- [ ] Worker self-tests not counted as satisfying V2
V3 — Live / exploratory (UI or deployable runtime)
Against the actual target (local feature URL or exact deploy — not a proxy claim):
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.
- 1mo ago First seen · 112 lines · 39 tokens per session scan A 833f1d669a24
owner-adversary-verification is a skill published in the GitHub repository HappyMonkeyAI/AgentsProtocol (5 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 974 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.