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 verifygit 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/verify)<a href="https://agentmods.dev/skills/automagik-dev/genie/verify"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/verify/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/verify"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/verify.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 | $0.00034 | $0.01215 |
| Opus 5.5 | $0.00014 | $0.00486 |
| Sonnet 5.5 | $0.00007 | $0.00243 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
verify 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 24d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify
Evidence before claims, always. This skill runs commands and reads their output; it changes nothing, so a failure it finds routes to fix, never to a quiet repair here. Reading a write back is still reading: the write belonged to whoever was authorized to make it, and this skill never originates one.
The rule
A claim you have not verified in this turn is not a claim, it is a hope. If the command that would prove it has not run since the last change, the honest report is the actual state plus what is still unproven.
Violating the letter of the rule violates its spirit: a paraphrase, an implication, or an expression of satisfaction is a completion claim too.
The gate function
Before any statement that work is done, correct, or passing:
- Identify the one command whose output proves this exact claim.
- Run it fresh and in full. A narrowed re-run proves only the narrowed scope.
- Read the whole output and the exit code, and count the failures rather than scanning for the word "pass".
- Decide. If the output confirms the claim, state the claim with the evidence beside it. If it does not, state the actual status with the same evidence.
Skipping a step is not a faster verification, it is a different activity.
What proves what
| Claim | Proof | Not proof |
|---|---|---|
| The repository is green | the repository's own aggregate gate, its current stage chain read from the manifest rather than recalled, run whole and exiting zero in this turn | a previous run, a passing subset, "should pass" |
| Types are clean | the typecheck stage inside that gate | the linter passing |
| A test suite passes | the suite's own output with a failure count of zero | one file re-run, a cached result |
| A bug is fixed | the original symptom re-exercised and now passing | the code changed and the reasoning looks right |
| A mutation landed | the stored state read back afterwards through a different path than the write took | the writing call's own success return, or a response that echoes what was sent |
| Text sent through a CLI arrived intact | the stored body read back from the system that received it and compared against the source text | the exit code, or a receipt that counts bytes accepted |
| A regression test works | it fails with the fix reverted and passes with it restored | it passes once |
| A worker did the work | git status and git diff over the owned scope |
the worker's success report |
| A branch is mergeable | the remote's checks read back from the pull request | a local gate alone |
| A group is shippable | a reviewer's returned verdict of SHIP | FIX-FIRST treated as "close enough", or your own read of your own work |
| Requirements are met | each wish criterion walked one by one against evidence | the gate being green |
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.
- 24d ago Changed · +8 lines deb693b6524b
- 29d ago First seen · 58 lines · 34 tokens per session scan A 90bf6067944e
verify is a skill published in the GitHub repository automagik-dev/genie (346 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,215 once invoked, about $0.0001 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 2026-09-17.
Other skills, from other repositories
tdd
Enforces red-green-refactor TDD cycle with atomic commits per phase. Used when implementing features, fixing bugs, or when tests should drive the design.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
safe-extraction
Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.
verify-before-complete
Block completion claims until verification evidence has been produced in the current message. Use before marking a task/slice/milestone complete, before creating a commit or PR, before saying "it works" or "tests pass", and any time you are about to claim work is done. The rule is: evidence before claims, always …