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 SathiaAI/adversarial-review --skill shipping-artifactsgit clone --depth 1 https://github.com/SathiaAI/adversarial-reviewWrote 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/sathiaai/adversarial-review/shipping-artifacts)<a href="https://agentmods.dev/skills/sathiaai/adversarial-review/shipping-artifacts"><img src="https://agentmods.dev/badge/skills/sathiaai/adversarial-review/shipping-artifacts/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/sathiaai/adversarial-review/shipping-artifacts"><img src="https://agentmods.dev/badge/skills/sathiaai/adversarial-review/shipping-artifacts.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 | $0.00040 | $0.00648 |
| Opus 5.5 | $0.00016 | $0.00259 |
| Sonnet 5.5 | $0.00008 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
shipping-artifacts 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipping artifacts
A claim without an artifact a skeptic would accept is an opinion. This project's whole premise is "is this change correct?" answered with evidence, not model self-assurance — so hold yourself to the same bar.
The rule
When you assert something is done, correct, safe, or passing, attach the artifact that lets someone else confirm it without rerunning your reasoning:
| Claim | Artifact that ships with it |
|---|---|
| "Tests pass" | The suite's N passed, M failed line, and — for a change that could regress others — the byte-identical fail-set vs the base branch (prove the deltas are yours or nobody's). |
| "No regressions" | A baseline run of the unchanged base plus your run; a diff of the two fail-sets. |
| "The verdict is X" | The run dir under .adversarial-review/ — the immutable audit record — and the aggregate.py-computed verdict.json, never a hand-authored verdict. |
| "It's tamper-evident" | The compute_attestation() digest (and a detached signature when --sign is used). |
| "It was reviewed" | The adversarial-review run's verdict, attached to the PR, at the stated tier. |
| "A behavior holds" | An offline test that asserts the observable outcome and the failure path, not a mocked success. |
Discipline
- Determinism. An artifact you cite must be reproducible: same inputs → same artifact.
No
Date.now, unsorted iteration, or unrecorded RNG in anything recorded. - No secrets in artifacts. Keys never land in run dirs, tests, logs, or docs.
- Honest status. If a check could not run (a missing permission, an unavailable binary), the artifact records BLOCKED / unknown — never a faked pass. A BLOCKED verdict from an honest gap is a correct artifact; a green one you can't back is a lie that outlives you.
- The sandbox is not storage. A build environment can vanish, so don't let keepable work live only
in a scratch dir. But push only when you have explicit authorization to push — this repo makes that
non-negotiable (see
AGENTS.md). Where you may push, do it the same turn you commit; where you may not, keep the work safe another way (a durable clone, a patch) and hand the commit to whoever merges. The durable artifact is the recorded commit, not the scratch copy.
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 · 41 lines · 40 tokens per session scan A 2579bad57ecd
shipping-artifacts is a skill published in the GitHub repository SathiaAI/adversarial-review (3 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 648 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 2026-09-13.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.