Menü
Run evaluation suites against the Loa framework
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Single-pass network health observation. Checks API liveness, namespace freshness, drift, computes Network Health Score.
Deep investigation of a single construct. Identity-reality drift, maintenance pattern, composition analysis.
Single-pass network health observation. Checks API liveness, namespace freshness, drift, computes Network Health Score.
Autonomous observation loop. Time-boxed cycles with ratcheting health score, commits findings to grimoires.
Synthesize observations into a readable network health report. Aggregates patterns and trends from observation cycles.
Single-pass coherence sense of an ARBITRARY estate (a registry/state pair). Resolves the read-command from operator-local estate-config, shells the estate's own doctor read-only, emits exactly the STATUS|SIGNAL|MISMATCH tile. Sense-only — never mutates the estate.
| name | eval |
| description | Run evaluation suites against the Loa framework |
| role | review |
| allowed-tools | Read, Grep, Glob, Bash(evals/harness/*), Bash(bats tests/*) |
| capabilities | {"schema_version":1,"read_files":true,"search_code":true,"write_files":false,"execute_commands":{"allowed":[{"command":"bats","args":["tests/*"]}],"deny_raw_shell":true},"web_access":false,"user_interaction":false,"agent_spawn":false,"task_management":false} |
| cost-profile | moderate |
Run evaluation suites against the Loa framework to detect regressions and benchmark skill quality.
# Run framework correctness suite
/eval --suite framework
# Run regression suite
/eval --suite regression
# Run a single task
/eval --task constraint-proc-001-enforced
# Run all tasks for a skill
/eval --skill implementing-tasks
# Update baselines
/eval --suite framework --update-baseline --reason "Post-refactor re-baseline"
/eval commandevals/harness/run-eval.sh with appropriate flagsWhen invoked, translate the user's request into run-eval.sh arguments:
# Default: run all default suites
./evals/harness/run-eval.sh --suite framework --trusted
# With suite specified
./evals/harness/run-eval.sh --suite <suite> --trusted
# With task specified
./evals/harness/run-eval.sh --task <task-id> --trusted
# With skill filter
./evals/harness/run-eval.sh --skill <skill-name> --trusted
# Update baseline
./evals/harness/run-eval.sh --suite <suite> --update-baseline --reason "<reason>" --trusted
# JSON output for programmatic use
./evals/harness/run-eval.sh --suite <suite> --json --trusted
Note: --trusted flag is always added for local execution. In CI, the container sandbox provides isolation.
| Code | Meaning |
|---|---|
| 0 | All pass, no regressions |
| 1 | Regressions detected |
| 2 | Infrastructure error |
| 3 | Configuration error |