Menu
Audit a calibrated Harbor task for deterministic purchaser export, leakage, evidence completeness, and release readiness.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Build or repair a deterministic Harbor task environment with explicit resources, network policy, health checks, and safe solver-visible boundaries.
Implement a legitimate Harbor Oracle solution and validate its behavior against an independent verifier without weakening the task contract.
Red-team a Harbor verifier for answer leakage, reward hacking, shared-container tampering, artifact manipulation, and semantic under-testing.
Calibrate a frozen tb-hard task using Harbor Oracle and real-agent rollouts, then distinguish authentic difficulty from ambiguity, flakiness, leakage, or infrastructure failure.
Create or evolve a canonical Harbor task inside a stable tb-hard case directory. Use after the design brief names observable acceptance criteria and at least three difficulty dimensions.
Research Harbor and Terminal-Bench 2 patterns to design an original tb-hard task. Use before approving a design brief or when checking whether a candidate is too shallow or derivative.
| name | tb-hard-release-audit |
| description | Audit a calibrated Harbor task for deterministic purchaser export, leakage, evidence completeness, and release readiness. |
| argument-hint | <case_id> |
| user-invocable | true |
| context | fork |
| agent | harbor-release-auditor |
| model | sonnet |
| effort | high |
| allowed-tools | Read Write Edit Glob Grep Bash |
Target case: $ARGUMENTS
Audit only frozen validated tasks. Confirm current Oracle, red-team, and calibration evidence; inspect package contents; run leakage/isolation checks; confirm reward paths and task metadata; and verify the purchaser adapter does not diverge from the canonical Harbor task.
Write audit evidence under evidence/<case_id>/release/. Do not edit task semantics, solution, tests, or delivery archives. Return ready, ready-with-nonblocking-notes, or blocked with exact remediation and retest requirements.
