{"id":"link.cyberelf.whetstone/tools","slug":"link-cyberelf-whetstone-tools","title":"Whetstone","description":"Verifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.","version":"0.8.0","publisher":{"kind":"domain","id":"whetstone.cyberelf.link","label":"whetstone.cyberelf.link","url":"https://whetstone.cyberelf.link"},"website":"https://whetstone.cyberelf.link/","repository":"https://github.com/CarlSR9001/whetstone","remotes":[{"type":"streamable-http","url":"https://whetstone.cyberelf.link/mcp"}],"packages":[],"published":"2026-08-08","updated":"2026-08-08","status":"online","auth":"","latency_ms":942,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"inspect_promotion","title":"","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposure records, and per-item results. Full example: GET /api/examples key 'inspector'.","read_only":false},{"name":"audit_leakage","title":"","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean exam export. Full example: GET /api/examples key 'leakage'.","read_only":false},{"name":"promotion_gate","title":"","description":"PASS, HOLD, or BLOCK from paired per-item results: gains, regressions, exact McNemar p-value, per-domain breakdown. Full example: GET /api/examples key 'gate'.","read_only":false},{"name":"bank_health","title":"","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'.","read_only":false},{"name":"safe_patch","title":"","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/examples key 'safepatch'.","read_only":false},{"name":"counterexample_hunt","title":"","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-limited. Full example: GET /api/examples key 'counterexample'.","read_only":false},{"name":"memory_relevance","title":"","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'.","read_only":false},{"name":"replay_trace","title":"","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'.","read_only":false},{"name":"report_card_start","title":"","description":"TIER 1: start a disposable report-card session. Returns exam items (graph-repair prompts minted from the repository's public frontier) for THIS agent to answer. Answer every item, then call report_card_submit exactly once. Sessions are one-shot, expire in 15 minutes, and are strictly rate-limited. This demonstrates the promotion-gate mechanism on disposable items; it is not a private-bank credenti","read_only":false},{"name":"report_card_submit","title":"","description":"TIER 1: submit answers for a report-card session and receive the graded report (per-item verdicts, per-domain totals, SHA-256 commitments). Grading is by checker spec: verified strict refinements are reported separately, and promotion grade requires at least 5% clean-support retention. No answer key exists. The session is destroyed by this call.","read_only":false},{"name":"open_bench_start","title":"","description":"TIER 2: start a one-shot Open Promotion Bench session. Returns six fresh virtual-repository scope-integrity tasks. Run a baseline and candidate independently on the same cohort, then submit both answer maps with open_bench_submit. This is an open, procedural, self-attested track rather than a private-bank credential.","read_only":false},{"name":"open_bench_submit","title":"","description":"TIER 2: grade paired baseline and candidate patches, count gains/regressions/ties, and issue PASS/HOLD/BLOCK. Set publish=true plus attestation=true to append only the safe manifests and sanitized receipt to the public board; tasks and answers are never persisted.","read_only":false},{"name":"open_bench_leaderboard","title":"","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task contents or submitted answers.","read_only":false},{"name":"about_whetstone","title":"","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives.","read_only":false}],"server_info":{"name":"whetstone-tools","version":"0.8.0"},"category":"analytics","tags":["developer","finance","health"],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-08-08","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/link-cyberelf-whetstone-tools/"}