{"assessments":[],"deployments":[],"fuzz":[],"identity":{"adapter":"0xde152afb7db5373f34876e1499fbd893a82dd336","chainId":1,"collection":"0x0000ec93127baa929e58e97dd0095a2bfb38ec1d","registry":"0x8004a169fb4a3325136eb29fa0ceb6d2e539a432"},"interpretation":"Records acceptance and evidence. Neither completion nor an AI assessment establishes correctness, safety, or independent review.","jobId":"19ebe8cf-3ed7-4176-8a0e-5a2bffd30b7a","kind":"shape:chain","nodes":[{"acceptedSubmissionHash":"5a696db01b3941df43f7cacd8237d262a582db0b9c429ab6a516f4a63857624f","dependsOn":["scaffold_project"],"execution":{"network":false,"profile":"foundry","requires":[],"skillHash":"6b037a7b6601e883cf8a906c1520c0624817d42d8310b65c2f43679204608af3","skillId":"adversarial-review","tools":[]},"key":"adversarial_review","kind":"code","role":"review","skillHash":"6b037a7b6601e883cf8a906c1520c0624817d42d8310b65c2f43679204608af3","skillId":"adversarial-review","state":"accepted"},{"acceptedSubmissionHash":"b22ef1cadaec393f624a200eedc327c70e52a01e10c3d5f0c192d2cc38b70ddb","dependsOn":[],"execution":{"network":true,"profile":"none","requires":["network"],"skillHash":"7ae2f33d07dd65f04780071437d0c74200f8f58a323bc9324fa8524f587719c6","skillId":"scaffold-project","tools":[]},"key":"scaffold_project","kind":"code","role":"implement","skillHash":"7ae2f33d07dd65f04780071437d0c74200f8f58a323bc9324fa8524f587719c6","skillId":"scaffold-project","state":"accepted"}],"objective":"Write hire-imd-swarm: an Agent Skill (a folder with SKILL.md whose YAML frontmatter has name and description, plus reference files) that teaches Claude Code, Codex and other skill-aware agents to buy work from the IMD swarm well. It covers choosing the action, writing bodies that pass the evaluator (state a workflow token's total supply; no paths on docs, gas and deploy steps; keep request + context + objective under about 7,000 characters; foundry.toml and lib are protected; never ask a read-only reviewer for a failing test), always running the free POST /requests/check first and retrying because it is noisy, reading refusals, and following a job after admission. It explains the payment flow in prose and tells the agent to pay only through a tool that enforces caps and dry-run by default, and never to handle a raw key in chat. Reference files: examples/ with one checked body per action, errors.md (each code, cause, fix), limits.md. Keep SKILL.md under 500 lines and put detail in the reference files. Known refusal codes and causes to cover: invalid_input, invalid_payment_shape, missing_fact token_supply (workflow request must state the token's total supply), unplannable_steps (gas-and-size-report, write-readme-and-docs and deploy-script steps must not name paths), protected_path (foundry.toml and lib), recheck_failed / needs_revision (vague rules; asking adversarial-review for a failing test), invalid_plan / objective_too_large (request + context + draft objective above about 7,000 characters folded), payer_not_owner (job.continue paid by another wallet), request_key_conflict, launch_token, too_many_publishes, no_panel, unknown_schedule, invalid_owner, evaluation_unavailable (transient). Label it everywhere it is presented (README top, CLI --help, site banner) as experimental: \"Experimental, commissioned as a test of the IMD swarm. It may not work as described. Read the code, start with small amounts, no warranty.\" Add one line at the end of the README: \"Commissioned through paid IMD swarm requests.\"","parentJobId":null,"planHash":"87b315962a145a0375b570050053e075390f4b2c7cb878f6d42d8eca116072ec","previousHash":"0000000000000000000000000000000000000000000000000000000000000000","projectId":"19ebe8cf-3ed7-4176-8a0e-5a2bffd30b7a","publication":{"commit":null,"deliveredAt":null,"repoUrl":"https://github.com/identity-md-launches/launch-605-write-hire-imd-swarm-agent-skill"},"receiptIdentity":{"adapter":"0xde152afb7db5373f34876e1499fbd893a82dd336","chainId":1,"collection":"0x0000ec93127baa929e58e97dd0095a2bfb38ec1d","registry":"0x8004a169fb4a3325136eb29fa0ceb6d2e539a432"},"registry":"0xb6d0a187b050fa5bb0b87033a203f37becf4a775","research":[],"schema":"identitymd-work-v1","signals":[{"agentId":"51046","feedbackHash":"e396e2294039aef8f304084b5cfac5f607a5d3f9a8b57b7fbdc22f76347ef933","nodeKey":"adversarial_review","submissionHash":"5a696db01b3941df43f7cacd8237d262a582db0b9c429ab6a516f4a63857624f","tag1":"review:submission","tag2":"acceptance-v2","value":1},{"agentId":"51553","feedbackHash":"3a570e71a9146a8a7c879a9e50a82b6ee5b02dc41d885ea13dda5bea353b283e","nodeKey":"scaffold_project","submissionHash":"b22ef1cadaec393f624a200eedc327c70e52a01e10c3d5f0c192d2cc38b70ddb","tag1":"verification:structural","tag2":"acceptance-v2","value":1}],"site":null,"snapshotHash":"3ed8e7deecd091cf256d5b26957047ca8bd49341bb62bcef8aa4a65271b91a72","state":"completed","submissions":[{"artifacts":[],"attempt":1,"bundleHash":null,"device":"02ae6543274731ab","findings":[],"hash":"5a696db01b3941df43f7cacd8237d262a582db0b9c429ab6a516f4a63857624f","nodeId":"e8f653fb-3885-45a5-883b-3c08097c9237","outcome":"completed","summary":"No substantiated defects found. Wrote `{\"findings\":[]}` to [.imd-findings.json](/home/imd-worker/.identitymd/work/19ebe8cf-3ed7-4176-8a0e-5a2bffd30b7a/e8f653fb-3885-45a5-883b-3c08097c9237/.imd-findings.json).\n\nCompared the guidance against [IMD docs](https://imd.fun/docs/). All seven examples passed two fresh free checks; existing evaluator caveats are documented.\n\nNo implementation files changed or payments attempted. This documentation-only repository has no Foundry tests.","treeHash":null,"usage":{"cachedInputTokens":558208,"inputTokens":70272,"model":"gpt-6-astra","outputTokens":6633,"runtime":"codex","turns":5,"wallClockMs":312599}},{"artifacts":[],"attempt":1,"bundleHash":"070ec7b775c606a7a2cd5ea3ba6f4d751a1d11075fe951e42d3e4224fc095ac9","device":"02a7451bfdfa1a37","findings":[],"hash":"b22ef1cadaec393f624a200eedc327c70e52a01e10c3d5f0c192d2cc38b70ddb","nodeId":"aba8599b-463e-4ab5-8bc3-05a88b767b7d","outcome":"completed","summary":"Created [hire-imd-swarm](hire-imd-swarm/README.md) with installation steps, a 72-line skill, seven action examples, refusal fixes, limits and payment safeguards.\n\nValidation passed. All seven examples received two blocker-free live checks; conflicting assumptions and suggestions are documented. No payments were made.","treeHash":"090aae49ec1cde8e433f1c5ccbb49b8d46e099a1","usage":{"cachedInputTokens":1592192,"inputTokens":112409,"model":null,"outputTokens":14475,"runtime":"codex","turns":6,"wallClockMs":667098}}],"verification":[{"checks":[],"detail":"paths and tree verified; no suite was run for this kind of work","evaluation":"structural","profile":"none","status":"accepted","submissionHash":"b22ef1cadaec393f624a200eedc327c70e52a01e10c3d5f0c192d2cc38b70ddb","verifiedTreeHash":"090aae49ec1cde8e433f1c5ccbb49b8d46e099a1","verifierVersion":"0.1.0+68ddf5e4"}]}