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 it235/multica-best-practices --skill multica-verificationgit clone --depth 1 https://github.com/it235/multica-best-practicesWrote 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/it235/multica-best-practices/multica-verification)<a href="https://agentmods.dev/skills/it235/multica-best-practices/multica-verification"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-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/it235/multica-best-practices/multica-verification"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-verification.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 | $0.00000 | $0.00564 |
| Opus 5 | $0.00000 | $0.00282 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
multica-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 9d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification (gatekeeping)
What this is
Verification is a function, not a role. It answers one question:
For every acceptance criterion, is there objective evidence that it is satisfied?
The key: verification must be an objectively decidable action (run commands, read output, map item by item), not "I feel it's fine." It doesn't rely on anyone's character — it relies on the evidence itself. Whoever runs it, the result is the same.
Who executes it
- Gatekeeping: the Leader triggers this Skill at the gate points (G1 / G2 / G3) and reruns independently. The Leader produces no artifacts, so it's naturally a third party.
- Self-check: after finishing, a producer may first run this Skill to self-verify (pasting the command output), but self-check is not gatekeeping — gatekeeping must be rerun by a non-producer.
The gate issuer must be a different party from the gated. Authors cannot stamp "PASS" on themselves.
Process
- Read the Issue's acceptance criteria.
- Map every criterion to evidence (which test / which command / which output).
- Rerun the verification commands; don't cite someone else's described output.
- Check the change scope: does the diff only touch this requirement?
- Give PASS / FAIL for each criterion.
Result
PASS — every criterion has sufficient evidence.
FAIL — at least one criterion unmet. Must provide: the problem, why it matters, where, and the fix direction.
BLOCKED — missing information / environment, cannot verify. Report honestly; never turn it into PASS.
Relationship to CI hard gates
This Skill is the verification function's form in the agent world (soft gate), suitable for getting started, no CI, or an exploration phase.
The same function's machine form is the CI hard-gate template carried by the multica-gate-setup skill. If it can run in CI, run it in CI; the soft gate is transitional.
Why this works
"Verification" is the easiest thing to turn into a formality. Writing verification as a rerunnable action checklist and requiring a non-producer to execute it blocks two kinds of cheating at once: producers pretending they verified (the self-check loophole) and producers stamping themselves PASS (the gatekeeping loophole).
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.
- 9d ago First seen · 48 lines · 0 tokens per session scan A fe48c7795120
multica-verification is a skill published in the GitHub repository it235/multica-best-practices (106 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 564 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 2026-08-30.
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.
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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.