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 pwdev-solucoes/pwdev-claude-marketplace --skill power-verifygit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/power-verify)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-verify"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-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/pwdev-solucoes/pwdev-claude-marketplace/power-verify"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-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 | $0.00029 | $0.00791 |
| Opus 5 | $0.00015 | $0.00396 |
| Sonnet 5 | $0.00006 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
power-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 8d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Before Claims
Read collaboration and artifacts before acting.
Route
- no argument, mid-work: the gate below, then continue
<feature-slug>: full adversarial verification, ending in a verdict--strict: two verifier lenses in parallel; the verdict is the worse of the two
The gate
Before any claim that something works, fixed, passes, or is done:
- Identify the command that would prove it.
.planning/power/context/project.mdrecords this repository's real test, lint and build commands; use those rather than the ones that are conventional for the ecosystem. - Run it, fresh and complete. Not a cached result, not a subset.
- Read the whole output: the exit code, the failure count, the warnings.
- Verify the output actually says what you are about to claim.
- Only then, claim it.
Skipping a step is not verifying faster; it is asserting.
| Claim | Requires | Not sufficient |
|---|---|---|
| "Tests pass" | the full suite run now, output read | the last run, before your change |
| "It builds" | the real build command | the linter passed |
| "The bug is fixed" | the regression test failing before and passing after | the symptom is gone |
| "Nothing else broke" | the full suite | the touched file's tests |
| "The agent did it" | the VCS diff | the agent said DONE |
No satisfaction before evidence. Not "Great!", not "Perfect!", not "That should do it". Those phrases commit you to a conclusion you have not yet checked, and having committed, you will read the output looking for agreement.
Adversarial verification
When verifying a whole feature, dispatch the verifier subagent. Its instruction is not
"check whether this is complete" — it is "try to refute that this is complete".
Give it the spec, the plan, the ledger, and the branch range. It falsifies each stated truth — objective, acceptance criteria, definition of done, prohibitions — with real commands, and reports what survived.
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.
- 8d ago First seen · 76 lines · 29 tokens per session scan A bce7b799e895
power-verify is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 791 once invoked, about $0.0001 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
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.