vstack-s6-hunt-fix — Claude Code skill: bug search and fixes
The vstack-s6-hunt-fix Claude Code skill searches for bugs within a trace-validated model and checks proposed fixes. It classifies counterexamples and tests changes against real code.
MIT ★ 89 updated 2026-11-16
/plugin marketplace add hao-ai-lab/vstack
/plugin install vstack@hao-ai-lab-vstackWhat vstack-s6-hunt-fix does
The skill examines a model reviewed in the previous stage and sorts counterexamples into model defects, known bugs, or new candidates. It records code steps and a minimal trigger for each case. Reproduction proceeds from source-level reasoning to replaying real control code with stubs, then to controlled timing on the actual system.
Repairs are compared in the model first: the original failure must disappear while safety and liveness properties still hold. The skill then checks the code change and regression against frozen expectations. It records the reproduction level as model only, CPU replay of real code, or real engine. A named human_verifier requires the real engine.
What it helps with
- sort a counterexample into a model defect, known bug, or new candidate
- reproduce a failure at a stated verification level
- compare repair candidates in the model
- check patched code and regression against declared expectations
Example prompts for the agent
- Search the trace-validated model for bugs and classify its counterexamples.
- Replay this failure with stubs and record the verification level.
- Compare the repair candidates in the model, then check the patch and regression.
How to install vstack-s6-hunt-fix
1Plugin marketplace
/plugin marketplace add hao-ai-lab/vstack/plugin install vstack@hao-ai-lab-vstackThis installs the whole vstack plugin with all its skills
2Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s6-hunt-fix -a claude-code3Manually: put the files in place
~/.claude/skills/vstack-s6-hunt-fix/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/vstack-s6-hunt-fix/
1Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s6-hunt-fix -a codex2Manually: put the files in place
.agents/skills/vstack-s6-hunt-fix/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s6-hunt-fix -a cursor2Manually: put the files in place
.cursor/skills/vstack-s6-hunt-fix/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hao-ai-lab/vstack skills/vstack-s6-hunt-fix2Manually: put the files in place
.github/skills/vstack-s6-hunt-fix/SKILL.md1Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s6-hunt-fix -a gemini-cli2Platform CLI
gemini skills install https://github.com/hao-ai-lab/vstack --path skills/vstack-s6-hunt-fixManually: put the files in place
.devin/skills/vstack-s6-hunt-fix/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about vstack-s6-hunt-fix
How do I install vstack-s6-hunt-fix in Claude Code?
Add the marketplace with /plugin marketplace add hao-ai-lab/vstack, then install the plugin with /plugin install vstack@hao-ai-lab-vstack.
What does vstack-s6-hunt-fix do?
It classifies counterexamples and checks proposed repairs in the model before validating changes in code. It also records the level at which a failure was reproduced.
What verification level does human_verifier require?
A named human_verifier requires reproduction on the real engine.
Source text
SKILL.md · MIT
--- name: vstack-s6-hunt-fix description: "Search within a trace-validated model scope, classify counterexamples and validate fixes in both the model and real code." --- # S6 — Find and repair bugs Read [Layer 0: shared operating rules](../../docs/layer-0.md), this stage and the assigned input bundle. ## Role and write scope Workers write new search and repair artifacts; approved properties and prior patches stay read-only. ## 1. Input The model reviewed in S5, restricted to the scope actually trace-validated. ## 2. Procedure 1. Write timestamped predictions for each bug family before running. Enable known repairs so shallow known failures do not hide deeper ones; record every switch. 2. Parameterize hardcoded constants first. At the old values, require matching verdicts and state counts; only then increase one dimension. 3. Classify each counterexample as model defect, known bug or new candidate. Attach code steps and a minimal trigger. 4. Reproduce progressively: source-level reasoning, real control-code replay with stubs, controlled timing on the real system. State the actual level as [Gate 3](../../docs/exposure-gate.md#gate-3-real-engine) names it (`model only`, `CPU replay of real code`, `real engine`), never rounded up, and any injected behavior. A named `human_verifier` requires `real engine`. 5. Compare repair candidates in the model: the original failure disappears, other safety and liveness properties hold, and removing the repair restores the failure. Then change code and check unpatched N/N versus patched 0/N under the declared trigger. ## 3. Exit checks - Triage every candidate and record its reproduction scope. - For every finding, record its [method class](../../docs/exposure-gate.md#method-classes), its [Gate 1](../../docs/exposure-gate.md#gate-1-formal-exposure) result (1a and 1b separately) and `found_by` (`checker` or `reading`). A finding that fails 1a or 1b is not reported as caught by formal checking. Gate 2 belongs to S5 and Gate 4 to the coordinator; S6 does not wait for them. - Require repair controls and the full regression to match frozen expectations. - A known-bug baseline matching expectations is not the same as a repaired implementation passing; require the fixed-state contract when validating a repair. ## 4. Rollback Return an unrealizable counterexample to S3, or to S2 if the promise or assumption is wrong. A repair requiring a weaker promise returns to S2 for approval. Use [a rollback ticket](../../templates/rollback.md). ## Concrete Examples For PD KV slot reuse, compare repairs that preserve in-flight accounting across reuse. Check both safe release and eventual release, then remove each repair component to test its role.
© Hao AI Lab · MIT · hao-ai-lab/vstack