Borrowing it
Nothing to install: this file belongs to QinxiangCao/QualifiedCProgramming. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/QinxiangCao/QualifiedCProgramming/main/.agents/skills-en/group-worker-proving/SKILL.mdgit clone --depth 1 https://github.com/QinxiangCao/QualifiedCProgrammingWrote 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/qinxiangcao/qualifiedcprogramming/group-worker-proving)<a href="https://agentmods.dev/skills/qinxiangcao/qualifiedcprogramming/group-worker-proving"><img src="https://agentmods.dev/badge/skills/qinxiangcao/qualifiedcprogramming/group-worker-proving/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/qinxiangcao/qualifiedcprogramming/group-worker-proving"><img src="https://agentmods.dev/badge/skills/qinxiangcao/qualifiedcprogramming/group-worker-proving.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 | $0.00075 | $0.00623 |
| Opus 5.5 | $0.00030 | $0.00249 |
| Sonnet 5.5 | $0.00015 | $0.00125 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
group-worker-proving 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 1mo 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Group Worker Proving
Role boundary
Use only the current claim/handoff, this skill, and its linked documents. Do not read the orchestrator or another role's skill, rely on a parent transcript, read or wait for a sibling group, dispatch another group, or perform merge, parent verify, or annotation retry.
These read rules prevent non-current content from becoming proof input; an accidental extra read is not itself a blocker. Continue the delivery when there is no out-of-bound write, no dependence on current-round sibling output, and the final proof still passes this group's controller validation.
Complete this group's top-level VCs and applicable split goals under the controller-validated proof_mode. Maintain proofs/helpers only in the fixed copies named by the handoff, use the handoff-rendered commands for optional preflight checks, then stop writing and deliver the report so main can invoke finalize-delivery for complete current report, structure, and group Rocq acceptance. Assignments and paths derive from the current plan; owners maintain no controller files.
When history exists, search the earlier proving round and annotation history paths listed in the handoff for relevant proof/helper blocks. Decide whether to copy, adapt, or redo them. The controller does not search, seed, or rename historical proofs. The optional proof_reuse.md is a human note. Do not read current siblings; copied helpers use the current suffix and all reused proofs still require current Coq validation.
When an annotation/spec gap is diagnosed, that gap is this group's terminal result: stop adding out-of-bound repairs to this group's copies and write a complete blocker. Its vcs entries give exact current-manual name, parent, and annotation_location; message only explains the existing premises and missing conclusion. This worker does not use that result to decide, stop, or advance any other group or parent phase.
Required reading
- Always read Proof flow, Commands and checks, and Mandatory forbidden-lemma rules in full.
- Before proving a manual VC, read Whole separation-logic proof tactics.
- When this group contains a refinement target, read Refinement proof tactics.
- When this group uses ordering, bounds, sum, or another pure-proposition predicate, read Pure proposition proof patterns.
- Read Reference cases only when an analogous proof is genuinely needed.
What ships with it
7 files 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.
- 1mo ago Changed 6aba26460516
- 1mo ago Changed · +4 lines · +8 tokens per session 09c63027e906
- 2mo ago First seen · 23 lines · 67 tokens per session scan A a1c661a03752
group-worker-proving is a skill published in the GitHub repository QinxiangCao/QualifiedCProgramming (51 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 623 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
train-pose
Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.
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.
experiment-audit
A review step that checks whether an experiment's reported results are supported by real data and a sufficiently broad test.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.
i4h-catheter-navigation-render-drr
Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.
i4h-catheter-navigation-smoke
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.