vstack-s4-calibrate-tv — Claude Code skill for trace calibration
The vstack-s4-calibrate-tv Claude Code skill calibrates behavior models and checks them against real traces. It runs stage S4 checks for bugs, fixes, repair components, and reachability witnesses.
MIT ★ 89 updated 2026-11-16
/plugin marketplace add hao-ai-lab/vstack
/plugin install vstack@hao-ai-lab-vstackWhat vstack-s4-calibrate-tv does
The skill tests whether a model reproduces the expected bug and whether its fix passes the required checks. It also tests each repair component by removing it and verifies paired reachability witnesses. Stage S4 uses models, configurations, source anchors, and witnesses prepared in S3.
For real traces, it keeps observation, instrumentation, completion, and safety evidence separate, then inspects each NOT_CONSUMED at its first divergence. Clean-baseline counterexamples receive explicit classifications, and results must agree with the coordinator’s clean reruns. A timeout, unknown result, empty exploration, or zero required coverage cannot pass. Property errors go back to S2; models that are too narrow or broad return to S3.
What it helps with
- check whether a model reproduces the expected bug
- test a fix and its components against required checks
- locate the first mismatch between a model and a real trace
- classify clean-baseline counterexamples and pending reproductions
Example prompts for the agent
- Run stage S4 on the models, configurations, and witnesses from S3.
- Check the real traces against the conformance checklist and classify counterexamples.
- Trace the first
NOT_CONSUMEDdivergence and prepare a rollback with the trace hash, event index, and source anchor.
How to install vstack-s4-calibrate-tv
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-s4-calibrate-tv -a claude-code3Manually: put the files in place
~/.claude/skills/vstack-s4-calibrate-tv/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/vstack-s4-calibrate-tv/
1Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s4-calibrate-tv -a codex2Manually: put the files in place
.agents/skills/vstack-s4-calibrate-tv/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s4-calibrate-tv -a cursor2Manually: put the files in place
.cursor/skills/vstack-s4-calibrate-tv/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hao-ai-lab/vstack skills/vstack-s4-calibrate-tv2Manually: put the files in place
.github/skills/vstack-s4-calibrate-tv/SKILL.md1Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s4-calibrate-tv -a gemini-cli2Platform CLI
gemini skills install https://github.com/hao-ai-lab/vstack --path skills/vstack-s4-calibrate-tvManually: put the files in place
.devin/skills/vstack-s4-calibrate-tv/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-s4-calibrate-tv
How do I install vstack-s4-calibrate-tv in Claude Code?
Add the marketplace with /plugin marketplace add hao-ai-lab/vstack, then install the skill with /plugin install vstack@hao-ai-lab-vstack.
What does vstack-s4-calibrate-tv do?
It calibrates behavior models, tests fixes, and compares model results with real traces. It also classifies mismatches and counterexamples.
What inputs does stage S4 need?
It uses models, configurations, source anchors, and witnesses from S3. Real traces are used for conformance checks.
Source text
SKILL.md · MIT
--- name: vstack-s4-calibrate-tv description: "Calibrate buggy/fixed/ablated behaviors and validate model conformance using real traces, witnesses and explicit mismatch triage." --- # S4 — Calibrate and align traces Read [Layer 0: shared operating rules](../../docs/layer-0.md), this stage and the assigned input bundle. ## Role and write scope Model and trace workers own distinct outputs; the coordinator consolidates the checklist and independently reruns representatives. ## 1. Input Models, configurations, source anchors and witnesses from S3. ## 2. Procedure 1. Timestamp predictions. Run four calibration checks: the historical bug violates the expected property by the expected mechanism; the fix completes within bounds; removing each repair component causes a violation; reachability witnesses are reached and their negations fail. Aggregated over the frozen denominator `I_U`, these results give the numerators `Cov_expr` and `Cov_emergent` of the [adequacy readout](../../docs/model-adequacy.md#numerators). 2. Repeat two-sided contract calibration at the minimum scale and one increment above it. A component outside the abstraction is unverified, not a pass. 3. Apply [trace-conformance checklist](../../docs/trace-validation.md) to real traces. Keep observation, instrumentation, completion and safety evidence separate. Report [readout 1](../../docs/model-adequacy.md#readout-1-trace-and-baseline-agreement): `TAR` with its negative-mutant rejection rate, or `TAR = N/A (no trace harness)`, and clean-baseline counterexamples as `Confirmed Bug`, `Model Defect` and `Unjudged (pending repro)` counts. 4. Classify every NOT_CONSUMED at the first divergence; never edit a trace to make it count as accepted. 5. Review every run with [the seven questions](../../docs/run-review.md). ## 3. Exit checks - Check expected verdicts and mechanisms for the bug, fix, repair ablations and paired witnesses. Generic mechanism and action-coverage automation is missing. - Supply evidence and state covered and untested scope for every trace checklist item. - Require agreement with the coordinator's clean reruns. Timeout, unknown, empty exploration and zero required coverage cannot pass. - Complete S4 even when an S7 proof is planned. ## 4. Rollback Return a wrong property to S2 and an overly narrow or broad model to S3. Repair instrumentation errors and record new traces within S4. Send real code failures to S6. Carry the trace hash, event index and source anchor. Use [a rollback ticket](../../templates/rollback.md). ## Concrete Examples A PD slot model can pass its configured safety checks while rejecting a real slot-reuse trace. Diagnose the first divergence before using that model to justify a repair.
© Hao AI Lab · MIT · hao-ai-lab/vstack