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 automagik-dev/genie --skill genie-orca-reviewgit clone --depth 1 https://github.com/automagik-dev/genieWrote 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/automagik-dev/genie/genie-orca-review)<a href="https://agentmods.dev/skills/automagik-dev/genie/genie-orca-review"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/genie-orca-review/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/automagik-dev/genie/genie-orca-review"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/genie-orca-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00741 |
| Opus 5 | $0.00025 | $0.00370 |
| Sonnet 5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
genie-orca-review 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 7d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
genie-orca:review
Runtime syntax: invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime.
A reviewer is a read-only worker dispatched by the coordinator, never the engineer of the same group, preferably a different model family (brain default: Codex reviews Claude-Sonnet work; Fable/Opus for the two gate reviews).
Contract
- Input: the group spec (
WISH.mdsection), ground truth (SCOUT.md),git diff <wish-branch>..HEAD, the validation command. - The reviewer re-runs validation and quotes the summary line. A review that did not run the gate is not a review.
- Body starts with
VERDICT: SHIP | FIX-FIRST | BLOCKED, then numbered findings[critical|major|minor]withfile:lineand a concrete fix. FIX-FIRST only on critical/major. - One
worker_done,--outcome succeeded= review delivered (the verdict is in the body). The reviewer'sworker_donenever authorizes coordinator edits; fixes are re-dispatched. - Name the environments in the adversarial question: the dev box with the product installed, the compiled binary from cwd
/with no env, a DSN/detached service, the vault literally named like the product. On brain, the same precedence bug survived four gates because each ran in one environment. - Ask the adversarial question explicitly in the brief ("how does this still fail in the compiled binary / under DSN / on a box with brain installed?"). On brain, 3 of 5 groups went FIX-FIRST from exactly that prompt.
Tiers
| When | Reviewers | Merge rule |
|---|---|---|
| per group | 1 capable model (≠ engineer) | verdict as-is |
| wish-approval, PR | 3 in parallel (claude / codex / third), same read-only worktree | severity-max; any BLOCKED → BLOCKED; SHIP only if all SHIP; one merged Linear comment |
| council | lenses (questioner / architecture / simplifier / perf …) on a decision | synthesis + unresolved tensions, persisted next to the wish |
| retro | the run's RETRO.md from skills/genie-orca-work/scripts/retro-collect.ts |
findings → skill edits, not prose |
What ships with it
1 file 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.
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.
- 7d ago First seen · 37 lines · 50 tokens per session scan A 4ec21b1b3546
genie-orca-review is a skill published in the GitHub repository automagik-dev/genie (335 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 741 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 2026-09-03.
Other skills, from other repositories
argot-check
Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…
test-driven-development
This skill should be used when implementing new features, fixing bugs, or writing new code. Enforces RED-GREEN-REFACTOR.
goal-test
A local experiment for testing a goal command that keeps an AI coding session working until a stated condition is judged complete. It uses a separate language model to evaluate the conversation after each assistant turn.
qa
This skill should be used when performing scenario-based acceptance testing, designing QA test plans, or validating that implementation behavior matches acceptance criteria beyond unit tests.
testing
This skill should be used when the user asks to "write tests", "fix failing tests", "improve test coverage", "add integration tests", "debug a flaky test", or reviews test quality. Provides behavior-focused testing patterns, coverage analysis, and detection of brittle test anti-patterns like implementation coupling…
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.