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 agentmods add skills/qinxiangcao/qualifiedcprogramming/vc-checkingnpx skills add QinxiangCao/QualifiedCProgramming --skill vc-checkinggit clone --depth 1 https://github.com/QinxiangCao/QualifiedCProgrammingWhat 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 | $0.00091 | $0.00511 |
| Opus 5 | $0.00046 | $0.00255 |
| Sonnet 5 | $0.00018 | $0.00102 |
| Haiku 4.5 | $0.00009 | $0.00051 |
Grade A, and why
vc-checking 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 2d 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VC Checking
You are the vc-checking owner for the current attempt and complete only VC analysis, grouping, and this delivery. Every attempt is a new independent session; rely only on the controller claim/handoff, the current agent_input.md, and files bound by the handoff. Do not depend on the parent transcript or speculate about or advance later annotation, group proving, merge, final apply, or other phases.
Reading order
- Read the VC analysis and grouping workflow in full. It is the process, write, command, and output contract for the current role.
- As required by the workflow, read the VC analysis guide and natural-language analysis. They provide proof-analysis knowledge only; if an obsolete process description in either document conflicts with the workflow, the workflow prevails.
- Read the
agent_input.mdnamed by the claim message in full, then read only the source, reuse source, and controller blocker bound there.
Do not read the root AGENTS.md, verification-orchestrator, another role's skill, controller state/event, or unbound history to supplement the process. If required information is absent from this skill and the claim/handoff, report it as missing under the workflow without expanding the read scope.
Delivery objectives
- Apply the exhaustive split-first analysis and unique
proof_modedecision strictly to every top-level VC. - Write executable strategies only for the selected formal targets; generate conditional reuse hints only when the controller explicitly binds the preceding sealed proving source.
- Complete preliminary grouping and a second load, coupling, and critical-path review; output a strict
group_plan.jsonand conciseagent_output.md. - Write
agent_report.jsonlast, stop all writes, and return the delivery to main/controller; if the controller requires an in-place report repair, repair it only within the same owner, attempt, and permitted boundary.
What ships with it
3 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.
- 2d ago First seen · 24 lines · 91 tokens per session scan A dfb9cd9f09f9
vc-checking is a skill published in the GitHub repository QinxiangCao/QualifiedCProgramming (43 stars, last pushed 11d ago), licensed MIT. It adds 91 tokens to every session and 511 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…