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 flow-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/flow-verify)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-verify"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-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/flow-verify"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-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 | $0.00045 | $0.00432 |
| Opus 5 | $0.00023 | $0.00216 |
| Sonnet 5 | $0.00009 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
flow-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 6d 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.
What it actually says
Verify completion adversarially
Read workflow, artifacts, and safety before verification.
The goal is to refute completion, not confirm the implementation narrative. Treat summaries and prior test claims as untrusted until reproduced.
Inputs
Resolve, in order:
- objective;
- acceptance criteria;
- definition of done;
- prohibitions and safety constraints;
- changed files and implementation evidence;
- prior review findings.
If no verifiable contract exists, return BLOCKED and list the missing truths. Do not invent acceptance criteria after implementation.
Procedure
- Convert every contract statement into an independently testable truth.
- For each truth, choose the command, inspection, or counterexample most likely to disprove it.
- Run fresh verification and record the exact result; do not rely on earlier output.
- Inspect the final diff for scope violations and prohibited behavior.
- Reconcile unresolved review findings with the truth list.
- Calculate passed truths and identify critical failures.
- When rejected, write bounded correction tasks only if artifact persistence is authorized.
Verdicts
APPROVED: every truth passes and no prohibition is violated.WITH_CAVEATS: all critical truths pass; only explicitly low-impact caveats remain.REJECTED: any critical truth fails, a prohibition is violated, or required evidence contradicts completion.BLOCKED: verification cannot run or the contract is absent.
Never weaken a failing criterion to obtain approval.
Output
Return a truth table with Truth, Refutation attempt, Evidence, and Result, followed by the verdict and correction paths. Persist the verification report only when the user requested it or an active Flow phase already authorizes artifacts.
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.
- 6d ago First seen · 47 lines · 45 tokens per session scan A 439c06005d7e
flow-verify is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 45 tokens to every session and 432 once invoked, about $0.0002 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.