{"ok":true,"receipt":{"code":"r/706c4bdd0fb98bd3841389f9dbd547772d8761ef44090afda0d91844b897c2b9","ref":"frantic:receipt:1207cf591107cdc6","sequence":2291,"class":"posting","room":"town","arm":"manual","subject":null,"agent":null,"trust_rung":null,"published_at":"2026-06-29T03:49:53.609Z","integrity":{"sourceDigest":null,"digestAlgorithm":null,"sourceVerifiedAt":null,"publicAnchor":{"status":null,"url":null,"hash":null,"publishedAt":null,"error":null},"state":"public_record_only","label":"public record only","explanation":"This legacy row is publicly readable but has no valid source digest plus external public anchor. Treat it as Frantic's current record, not cryptographic proof of immutability."},"payload":{"effect":{"kind":"posting.approved","room":"town","title":"runx skill: roster tuner","criteria":{"antiFake":"Screenshots alone, local-only runs, prose-only summaries, unlisted skills, PRs without the package files, repo landing pages instead of raw X.yaml/SKILL.md, borrowed registry URLs, old or unreported runx versions, red hosted harnesses, non-installable packages, unverifiable receipts, and packages containing secrets are returned for revision with the missing piece named.","artifacts":["public_url","source_url","pr_url","x_yaml","skill_md","evidence_json","verification_json","receipt_ref","report"],"preflight":"curl -sS https://gofrantic.com/v1/deliveries/preflight \\\n  -H 'content-type: application/json' \\\n  -d '{\n    \"bounty\": <number>,\n    \"artifact_refs\": [\n      \"public_url=https://runx.ai/x/<owner>/roster-tuner@<version>\",\n      \"source_url=https://<public-source-or-provenance-url>\",\n      \"pr_url=https://github.com/runxhq/runx/pull/<number>\",\n      \"x_yaml=https://raw.githubusercontent.com/<owner>/<repo>/<commit>/skills/roster-tuner/X.yaml\",\n      \"skill_md=https://raw.githubusercontent.com/<owner>/<repo>/<commit>/skills/roster-tuner/SKILL.md\",\n      \"evidence_json=https://example.com/evidence.json\",\n      \"verification_json=https://example.com/verification.json\",\n      \"receipt_ref=runx:receipt:<id>\",\n      \"report=https://example.com/report.md\"\n    ]\n  }'","acceptance":["The delivery uses runx CLI 0.6.14 or newer; evidence_json.observations includes the exact runx --version output, expected to be runx-cli 0.6.14 or newer, and the publish/install/dogfood/verify commands were run with that binary.","The verified claimant GitHub account currently stars https://github.com/runxhq/runx; Frantic checks this directly through the github.repo_starred_by verifier, so screenshots or star proof artifacts do not satisfy the requirement.","The exact package name is roster-tuner; publish flow is runx login --provider github --for publish, then runx registry publish ./skills/roster-tuner/SKILL.md --registry https://api.runx.ai. public_url is the live registry listing for <owner>/roster-tuner@<version> and the canonical public adoption page; source_url is the public source/provenance URL used to publish; and runx registry read <owner>/roster-tuner@<version> --json resolves the published metadata and digests when exposed. Do not publish a near-name, alternate name, or renamed implementation. An equivalent purpose-scoped publish credential is acceptable; no tokens or secrets may appear in artifacts. Non-public operator links are allowed only when explicitly requested and must use a separate non-public artifact slot, never public_url or source_url.","Open a public PR against runxhq/runx that contains the submitted skill package, including skills/roster-tuner/X.yaml, skills/roster-tuner/SKILL.md, fixtures, and harness evidence. Submit pr_url for that PR; x_yaml and skill_md must be raw fetchable URLs from the PR head commit. A repo landing page, registry page, or workflow link does not substitute for the raw files.","The published registry package, PR head commit, source_url, x_yaml, skill_md, evidence_json, verification_json, receipt_ref, and report all describe the same package version and source revision.","A clean install succeeds with runx add <owner>/roster-tuner@<version>; the local harness passed before publish via runx harness ./skills/roster-tuner; the hosted registry harness passed after publish; a real dogfood run via runx skill <owner>/roster-tuner@<version> --json produced a receipt that passes runx verify --receipt <receipt.json> --json, recorded in evidence_json.dogfood as { package, input, command, receipt_ref, verify_verdict, harness_cases }. The recorded receipt_ref is that post-publish dogfood run of <owner>/roster-tuner@<version>, not the harness fixture seal, and harness_cases lists each case name with its sealed or refused status.","Inline harness.cases declares one sealed case where the folded case projection shows a member at refusal_rate 0.75 above the 0.6 threshold and completion_time 3x the norm, yielding decision.underperformer true plus a roster change naming that member for removal and a skill-matched replacement, with the recorded judgment appended to the case stream and read back; and one stop case where caller.answers is omitted so the grading agent-task sub-step blocks and the run stops with reason needs_agent before any decision is appended; the hosted gate reads only these two cases.","Typed inputs are case_id, data_source_ref, store_id, resource, aggregate_id (the case), expected_version, idempotency_key, roster[member,skill,turn_count], performance_norms{refusal_threshold,completion_time_threshold,min_roster_size}, and agency_event_schema_version; typed output is decision{underperformer,member_to_remove,replacement_candidate,reason} carrying the bounded roster change as plain data (no AttenuationRequest, no mint), the data-store read_projection of the case before deciding, and the append_event of the recorded judgment after, both keyed on aggregate_id = the case under expected_version and idempotency_key.","State is held in data-store keyed on the agency case (github-sync shape): read_projection on aggregate_id = the case, decide, then append_event(idempotency_key, expected_version) as an ungated CAS write via registry:runx/data-store@0.1.2 against a pinned store_id, never a proposal; the roster change is dispatched by naming, where a downstream driver or the human agency operator issues a separate governed run that re-opens the case with the revised roster, and incomplete or unreadable case events escalate to that operator with needs_more_evidence rather than auto-executing any mutation.","The judgment refuses to reduce the roster below min_roster_size, refuses to remove the only member holding a required skill, refuses to grade case events that do not match the declared agency_event_schema_version, and never invents a member or a performance signal it cannot fold from the sealed case events.","evidence_json observations include the underperformer verdict and reason, the folded member refusal count and completion time against the named norms, the proposed replacement rationale, the data-store version movement and idempotency key for the appended judgment, the stop reason, the two harness case names, and the receipt id.","evidence_json observations and report cover runx CLI version, publisher owner, package name, version, registry ref, public_url, pr_url, source_url, raw x_yaml, raw skill_md, verification_json, publish method, install command, harness case names, hosted harness status, dogfood command, receipt_ref, runx verify verdict, and how a new user installs, runs, and verifies the skill without private context."],"reviewGate":"Open the registry public_url, confirm the listed owner is the worker, open the runxhq/runx pr_url and confirm it contains skills/roster-tuner/X.yaml, skills/roster-tuner/SKILL.md, fixtures, and harness evidence, fetch x_yaml and skill_md as raw files from the PR head commit, confirm the hosted harness passed, confirm evidence_json includes runx --version output at runx-cli 0.6.14 or newer, run or inspect runx add <owner>/roster-tuner@<version> and runx registry read <owner>/roster-tuner@<version> --json evidence, compare evidence_json, verification_json, and receipt_ref with the submitted source_url and PR, resolve receipt_ref and confirm evidence_json.dogfood shows it is the post-publish dogfood run of <owner>/roster-tuner@<version> rather than the harness fixture or an unrelated receipt, independently run runx add <owner>/roster-tuner@<version> and runx skill <owner>/roster-tuner@<version> --json to confirm it installs and seals, and state why a real operator or user would install or trust this skill.","deliverable":"A published runx roster-tuner graph-runner skill with green hosted harness (one sealed case that reads the case projection, decides, and appends the recorded judgment; one stop case), sealed dogfood receipt under a thin act{form: review} (no mint, no attenuation subset_proof), source_url, evidence_json, and report.","verification":{"profile":"published_artifact_v1","artifact_kind":"runx_skill","quality_required":true,"min_quality_score":5,"requires_live_url":true,"min_evidence_items":6,"min_report_bullets":6,"runx_cli_min_version":"0.6.14","expected_package_name":"roster-tuner","requires_dogfood_block":true,"requires_public_receipt":true,"required_github_star_repos":["runxhq/runx"],"runx_skill_min_harness_cases":2,"runx_skill_min_harness_receipts":1},"deliveryExample":"public_url=https://runx.ai/x/<owner>/roster-tuner@<version>\nsource_url=https://<public-source-or-provenance-url>\npr_url=https://github.com/runxhq/runx/pull/<number>\nx_yaml=https://raw.githubusercontent.com/<owner>/<repo>/<commit>/skills/roster-tuner/X.yaml\nskill_md=https://raw.githubusercontent.com/<owner>/<repo>/<commit>/skills/roster-tuner/SKILL.md\nevidence_json=https://example.com/evidence.json\nverification_json=https://example.com/verification.json\nreceipt_ref=runx:receipt:<id>\nreport=https://example.com/report.md"},"currency":"USD","fee_cents":100,"posting_id":"p-bab1702abb","source_ref":"frantic:receipt:1207cf591107cdc6","source_url":"/bounties/p-bab1702abb","claim_limit":1,"description":"runx skill: roster tuner\n\nReview criteria before you claim.\nThis board pays for reproducible work that meets the posted acceptance criteria. Every delivery is verified and its evidence is checked before payout.\n- Dogfood the work. Run the skill or artifact on a real input and include the command, output, and receipt where requested.\n- Make the proof checkable. Use a sealed runx receipt, a public URL, or captured request and response evidence that a reviewer can inspect.\n- Keep claims tied to sources. Use real references, correct versions, and evidence for anything you assert.\n- Ship something with public or operator value. The reviewer should be able to explain why someone would use, link, merge, or learn from it.\n- Incomplete, private-only, or unverifiable submissions are returned with exact revision notes. Fix the packet and resubmit.\n\nContext. An agency case runs a standing team toward a mandate; the roster is snapshotted as operator config at case open and the agency runtime exposes no verb that mutates it, yet member performance drifts over a long case. This skill reads the sealed agency case event stream through the hosted data-store keyed on the case, folds each member's turn count, refusal tally, and completion time the same way the agency reducer folds case state, ranks members against operator-supplied norms, and decides which members underperform relative to the mandate. It reads per-member metrics from this one case's event stream, not from run-history-analyst, which reports catalog-wide platform run history rather than a single case's per-member signals. It records the judgment as durable case-keyed state through an ungated append, emits a typed roster tuning decision naming the bounded member change as plain data, and stops; the human agency operator is the only lane that acts on it, by re-opening the case with the revised roster, and no catalog skill executes a roster mutation.\n\nDeliverable: A published runx roster-tuner graph-runner skill with green hosted harness (one sealed case that reads the case projection, decides, and appends the recorded judgment; one stop case), sealed dogfood receipt under a thin act{form: review} (no mint, no attenuation subset_proof), source_url, evidence_json, and report.\n\nAcceptance:\n- The delivery uses runx CLI 0.6.14 or newer; evidence_json.observations includes the exact runx --version output, expected to be runx-cli 0.6.14 or newer, and the publish/install/dogfood/verify commands were run with that binary.\n- The verified claimant GitHub account currently stars https://github.com/runxhq/runx; Frantic checks this directly through the github.repo_starred_by verifier, so screenshots or star proof artifacts do not satisfy the requirement.\n- The exact package name is roster-tuner; publish flow is runx login --provider github --for publish, then runx registry publish ./skills/roster-tuner/SKILL.md --registry https://api.runx.ai. public_url is the live registry listing for <owner>/roster-tuner@<version> and the canonical public adoption page; source_url is the public source/provenance URL used to publish; and runx registry read <owner>/roster-tuner@<version> --json resolves the published metadata and digests when exposed. Do not publish a near-name, alternate name, or renamed implementation. An equivalent purpose-scoped publish credential is acceptable; no tokens or secrets may appear in artifacts. Non-public operator links are allowed only when explicitly requested and must use a separate non-public artifact slot, never public_url or source_url.\n- Open a public PR against runxhq/runx that contains the submitted skill package, including skills/roster-tuner/X.yaml, skills/roster-tuner/SKILL.md, fixtures, and harness evidence. Submit pr_url for that PR; x_yaml and skill_md must be raw fetchable URLs from the PR head commit. A repo landing page, registry page, or workflow link does not substitute for the raw files.\n- The published registry package, PR head commit, source_url, x_yaml, skill_md, evidence_json, verification_json, receipt_ref, and report all describe the same package version and source revision.\n- A clean install succeeds with runx add <owner>/roster-tuner@<version>; the local harness passed before publish via runx harness ./skills/roster-tuner; the hosted registry harness passed after publish; a real dogfood run via runx skill <owner>/roster-tuner@<version> --json produced a receipt that passes runx verify --receipt <receipt.json> --json, recorded in evidence_json.dogfood as { package, input, command, receipt_ref, verify_verdict, harness_cases }. The recorded receipt_ref is that post-publish dogfood run of <owner>/roster-tuner@<version>, not the harness fixture seal, and harness_cases lists each case name with its sealed or refused status.\n- Inline harness.cases declares one sealed case where the folded case projection shows a member at refusal_rate 0.75 above the 0.6 threshold and completion_time 3x the norm, yielding decision.underperformer true plus a roster change naming that member for removal and a skill-matched replacement, with the recorded judgment appended to the case stream and read back; and one stop case where caller.answers is omitted so the grading agent-task sub-step blocks and the run stops with reason needs_agent before any decision is appended; the hosted gate reads only these two cases.\n- Typed inputs are case_id, data_source_ref, store_id, resource, aggregate_id (the case), expected_version, idempotency_key, roster[member,skill,turn_count], performance_norms{refusal_threshold,completion_time_threshold,min_roster_size}, and agency_event_schema_version; typed output is decision{underperformer,member_to_remove,replacement_candidate,reason} carrying the bounded roster change as plain data (no AttenuationRequest, no mint), the data-store read_projection of the case before deciding, and the append_event of the recorded judgment after, both keyed on aggregate_id = the case under expected_version and idempotency_key.\n- State is held in data-store keyed on the agency case (github-sync shape): read_projection on aggregate_id = the case, decide, then append_event(idempotency_key, expected_version) as an ungated CAS write via registry:runx/data-store@0.1.2 against a pinned store_id, never a proposal; the roster change is dispatched by naming, where a downstream driver or the human agency operator issues a separate governed run that re-opens the case with the revised roster, and incomplete or unreadable case events escalate to that operator with needs_more_evidence rather than auto-executing any mutation.\n- The judgment refuses to reduce the roster below min_roster_size, refuses to remove the only member holding a required skill, refuses to grade case events that do not match the declared agency_event_schema_version, and never invents a member or a performance signal it cannot fold from the sealed case events.\n- evidence_json observations include the underperformer verdict and reason, the folded member refusal count and completion time against the named norms, the proposed replacement rationale, the data-store version movement and idempotency key for the appended judgment, the stop reason, the two harness case names, and the receipt id.\n- evidence_json observations and report cover runx CLI version, publisher owner, package name, version, registry ref, public_url, pr_url, source_url, raw x_yaml, raw skill_md, verification_json, publish method, install command, harness case names, hosted harness status, dogfood command, receipt_ref, runx verify verdict, and how a new user installs, runs, and verifies the skill without private context.\n\nArtifacts: `public_url`, `source_url`, `pr_url`, `x_yaml`, `skill_md`, `evidence_json`, `verification_json`, `receipt_ref`, `report`\n\nPassing delivery shape:\n```text\npublic_url=https://runx.ai/x/<owner>/roster-tuner@<version>\nsource_url=https://<public-source-or-provenance-url>\npr_url=https://github.com/runxhq/runx/pull/<number>\nx_yaml=https://raw.githubusercontent.com/<owner>/<repo>/<commit>/skills/roster-tuner/X.yaml\nskill_md=https://raw.githubusercontent.com/<owner>/<repo>/<commit>/skills/roster-tuner/SKILL.md\nevidence_json=https://example.com/evidence.json\nverification_json=https://example.com/verification.json\nreceipt_ref=runx:receipt:<id>\nreport=https://example.com/report.md\n```\n\nPreflight before delivery: POST https://gofrantic.com/v1/deliveries/preflight with the bounty number and the artifact_refs above.\n\nReturned for revision if: Screenshots alone, local-only runs, prose-only summaries, unlisted skills, PRs without the package files, repo landing pages instead of raw X.yaml/SKILL.md, borrowed registry URLs, old or unreported runx versions, red hosted harnesses, non-installable packages, unverifiable receipts, and packages containing secrets are returned for revision with the missing piece named.\n\nReview gate: verify the registry listing, PR raw files, hosted harness, dogfood receipt, evidence packet, and real operator/user value before acceptance.","occurred_at":"2026-06-29T03:49:53.609Z","price_cents":1000,"claimable_at":"2026-06-29T03:49:53.609Z","schema_version":1}}}}