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/verification-orchestrator/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/verification-orchestrator)<a href="https://agentmods.dev/skills/qinxiangcao/qualifiedcprogramming/verification-orchestrator"><img src="https://agentmods.dev/badge/skills/qinxiangcao/qualifiedcprogramming/verification-orchestrator/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/verification-orchestrator"><img src="https://agentmods.dev/badge/skills/qinxiangcao/qualifiedcprogramming/verification-orchestrator.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 | $0.00058 | $0.00588 |
| Opus 5.5 | $0.00023 | $0.00235 |
| Sonnet 5.5 | $0.00012 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
verification-orchestrator 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.
What it actually says
Verification Orchestrator
For main only. Read all four documents before executing a case:
On Windows, also read the Windows runtime rules. At final-check, read
final-check/SKILL.md and its required workflow.
Main maps controller owners to actual agent targets and executes the returned structured invocations.
Claim each owner action first, then send the claim response's handoff.prompt verbatim to that agent.
Create only one annotation agent per run; send repairs and later annotation attempts to that same agent.
Use an independent owner for each VC-checking attempt and each group's first claim; repairs of the same
task retain its owner. Main executes controller actions for vc-proving preparation, dispatch, merge,
and parent checks; there is no separate phase agent.
After an owner writes its terminal report and stops editing, main executes finalize-delivery. This
command performs all acceptance checks for that role directly; a completed report alone is not
acceptance. Derive the next step from current task facts. Continue until phase: done, wait while
owners are running, and report an explicit blocker when no action can proceed.
Main does not edit annotations, plans, or proofs on an owner's behalf, or proactively read, summarize, or restate owner skills. Owners read their role knowledge from their own handoffs. This division controls context; acceptance depends on current files, reports, and actual checks, not accidental extra reading.
If a frozen user specification must change, the owner records the proposal and stops. Main pauses
the run and asks the user to approve it. After explicit approval, resume the run, execute unfreeze
for the current annotation round, and return the work to the same owner. An unfrozen model-written
specification may be repaired within the current annotation attempt.
When the user requests pause or stop, execute cancel-action for the current action, or pause-run
if its exact id is unavailable. Wait for running tools to clean up their processes, then stop advancing.
Call resume-run only after the user explicitly requests resumption, then run step. Tasks and owners
remain unchanged; actions are recomputed from current state.
What ships with it
5 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 · +7 lines · -12 tokens per session cf7c76fe41aa
- 1mo ago Changed · +6 lines 5dda51705aad
- 2mo ago First seen · 31 lines · 70 tokens per session scan A 849751918842
verification-orchestrator is a skill published in the GitHub repository QinxiangCao/QualifiedCProgramming (51 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 588 once invoked, about $0.0002 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
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.