{"id":"95662812-9dfa-46df-85c4-e4d282338eb9","shortId":"Q3TBcW","kind":"skill","title":"workbench-goal-mode","tagline":"Goal-persistence execution wrapper for autonomous work that must continue across turns until the stated objective is actually satisfied.","description":"# Workbench Goal Mode\n\nUse this skill when an issue contains `/goal`, `GOAL_MODE: yes`, asks for full\nautonomous completion, or asks an agent to keep working until a concrete outcome\nis achieved.\n\nGoal Mode is an execution wrapper, not a permission override. It keeps the\nobjective alive across turns, reruns, local fixes, and partial evidence, while\npreserving existing approval, safety, and review gates.\n\n## Activation\n\nBefore changing files or live resources, post a compact lock:\n\n```text\nGOAL_LOCK:\nobjective:\nowner:\nnon_goals:\ncloseout_gates:\noperator_call_conditions:\n```\n\n- `objective` is the user-visible outcome, not a task list.\n- `owner` is one assigned agent or human owner.\n- `non_goals` prevents the agent from expanding into adjacent work.\n- `closeout_gates` names the evidence required before claiming done.\n- `operator_call_conditions` names the few cases where human input is needed.\n\n## Execution Rules\n\n1. Build a checklist from the locked goal, then execute it.\n2. Do not stop after a local fix if the broader goal remains unverified.\n3. When a command, build, test, or smoke fails, investigate and repair before\n   asking for help.\n4. Treat repeated identical failures as a mechanism problem: change the probe or\n   report the exact blocker instead of retrying the same action.\n5. Use fresh reruns when context is stale, repo state changed, auth changed, or\n   the previous run was bound to the wrong repo/resource.\n6. Preserve issue-level scope, approval gates, secrets boundaries, and runtime\n   ownership. `/goal` does not permit destructive cleanup, force pushes, hidden\n   live mutations, broad repo reads, or credential handling.\n\n## Required Closeout Gates\n\nFor code, ops, or workflow-changing tasks, address every relevant gate before\nclaiming completion:\n\n- `build`: documented build or closest real startup/build smoke.\n- `test`: targeted tests plus the smallest meaningful regression check.\n- `help_smoke`: CLI help, startup, UI load, or endpoint smoke when command/user\n  surfaces changed.\n- `docs_report`: docs, changelog, handoff, or explicit \"not needed\" rationale.\n- `git_status`: clean state or intentionally explained dirty state.\n- `evidence`: exact commands, files, links, screenshots, issue IDs, run IDs, or\n  artifact paths.\n\nIf a gate does not apply, say why. A skipped gate without rationale is `FLAG`.\n\n## Operator Call Conditions\n\nCall the operator only for true external blockers:\n\n- missing credentials or approval that cannot be inferred from the issue;\n- unavailable third-party service or remote host;\n- destructive or irreversible operation approval;\n- repo/resource access failure that cannot be fixed inside the assigned context;\n- requirement conflict where continuing would change the user's goal.\n\nThe blocker report must include attempted fixes, exact evidence, and the smallest\noperator action needed.\n\n## Closeout Contract\n\nUse this scaffold:\n\n```text\nGOAL_LOCK:\nWHAT_CHANGED:\nVERIFICATION:\nDOCS_REPORT:\nGIT_STATUS:\nRESIDUAL_RISK:\nOPERATOR_NEEDED: yes/no\nVERDICT: PASS | FLAG | BLOCK\n```\n\n`PASS` means the locked objective is achieved and every relevant closeout gate\nhas evidence. `FLAG` means useful progress remains reviewable but a gate or risk\nis unresolved. `BLOCK` means the objective cannot be safely completed without an\noperator or upstream fix.","tags":["workbench","goal","mode","multica","ultimate","fearvox","agent-skills","ai-agents","claude-code","codex","hermes-agent","sdd"],"capabilities":["skill","source-fearvox","skill-workbench-goal-mode","topic-agent-skills","topic-ai-agents","topic-claude-code","topic-codex","topic-hermes-agent","topic-multica","topic-sdd","topic-skills-sh"],"categories":["multica-ultimate-workbench"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/Fearvox/multica-ultimate-workbench/workbench-goal-mode","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add Fearvox/multica-ultimate-workbench","source_repo":"https://github.com/Fearvox/multica-ultimate-workbench","install_from":"skills.sh"}},"qualityScore":"0.456","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 12 github stars · SKILL.md body (3,319 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:07:13.620Z","embedding":null,"createdAt":"2026-05-13T01:05:02.846Z","updatedAt":"2026-05-18T19:07:13.620Z","lastSeenAt":"2026-05-18T19:07:13.620Z","tsv":"'/goal':35,263 '1':163 '2':174 '3':188 '4':204 '5':227 '6':250 'access':412 'achiev':56,477 'across':16,72 'action':226,445 'activ':88 'actual':23 'address':291 'adjac':138 'agent':47,126,134 'aliv':71 'appli':366 'approv':83,256,390,410 'artifact':359 'ask':39,45,201 'assign':125,420 'attempt':437 'auth':238 'autonom':11,42 'block':470,498 'blocker':220,386,433 'bound':245 'boundari':259 'broad':274 'broader':184 'build':164,192,298,300 'call':109,150,377,379 'cannot':392,415,502 'case':155 'chang':90,213,237,239,289,328,427,456 'changelog':332 'check':314 'checklist':166 'claim':147,296 'clean':341 'cleanup':268 'cli':317 'closeout':106,140,281,447,481 'closest':302 'code':284 'command':191,350 'command/user':326 'compact':97 'complet':43,297,505 'concret':53 'condit':110,151,378 'conflict':423 'contain':34 'context':232,421 'continu':15,425 'contract':448 'credenti':278,388 'destruct':267,406 'dirti':346 'doc':329,331,458 'document':299 'done':148 'endpoint':323 'everi':292,479 'evid':79,144,348,440,484 'exact':219,349,439 'execut':8,61,161,172 'exist':82 'expand':136 'explain':345 'explicit':335 'extern':385 'fail':196 'failur':208,413 'file':91,351 'fix':76,181,417,438,511 'flag':375,469,485 'forc':269 'fresh':229 'full':41 'gate':87,107,141,257,282,294,363,371,482,493 'git':339,460 'goal':3,6,26,36,57,100,105,131,170,185,431,453 'goal-persist':5 'handl':279 'handoff':333 'help':203,315,318 'hidden':271 'host':405 'human':128,157 'id':355,357 'ident':207 'includ':436 'infer':394 'input':158 'insid':418 'instead':221 'intent':344 'investig':197 'irrevers':408 'issu':33,253,354,397 'issue-level':252 'keep':49,68 'level':254 'link':352 'list':121 'live':93,272 'load':321 'local':75,180 'lock':98,101,169,454,474 'mean':472,486,499 'meaning':312 'mechan':211 'miss':387 'mode':4,27,37,58 'must':14,435 'mutat':273 'name':142,152 'need':160,337,446,465 'non':104,130 'object':21,70,102,111,475,501 'one':124 'op':285 'oper':108,149,376,381,409,444,464,508 'outcom':54,117 'overrid':66 'owner':103,122,129 'ownership':262 'parti':401 'partial':78 'pass':468,471 'path':360 'permiss':65 'permit':266 'persist':7 'plus':309 'post':95 'preserv':81,251 'prevent':132 'previous':242 'probe':215 'problem':212 'progress':488 'push':270 'rational':338,373 'read':276 'real':303 'regress':313 'relev':293,480 'remain':186,489 'remot':404 'repair':199 'repeat':206 'repo':235,275 'repo/resource':249,411 'report':217,330,434,459 'requir':145,280,422 'rerun':74,230 'residu':462 'resourc':94 'retri':223 'review':86,490 'risk':463,495 'rule':162 'run':243,356 'runtim':261 'safe':504 'safeti':84 'satisfi':24 'say':367 'scaffold':451 'scope':255 'screenshot':353 'secret':258 'servic':402 'skill':30 'skill-workbench-goal-mode' 'skip':370 'smallest':311,443 'smoke':195,305,316,324 'source-fearvox' 'stale':234 'startup':319 'startup/build':304 'state':20,236,342,347 'status':340,461 'stop':177 'surfac':327 'target':307 'task':120,290 'test':193,306,308 'text':99,452 'third':400 'third-parti':399 'topic-agent-skills' 'topic-ai-agents' 'topic-claude-code' 'topic-codex' 'topic-hermes-agent' 'topic-multica' 'topic-sdd' 'topic-skills-sh' 'treat':205 'true':384 'turn':17,73 'ui':320 'unavail':398 'unresolv':497 'unverifi':187 'upstream':510 'use':28,228,449,487 'user':115,429 'user-vis':114 'verdict':467 'verif':457 'visibl':116 'without':372,506 'work':12,50,139 'workbench':2,25 'workbench-goal-mod':1 'workflow':288 'workflow-chang':287 'would':426 'wrapper':9,62 'wrong':248 'yes':38 'yes/no':466","prices":[{"id":"5f84218b-bbec-4e40-aaca-3655031d8390","listingId":"95662812-9dfa-46df-85c4-e4d282338eb9","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"Fearvox","category":"multica-ultimate-workbench","install_from":"skills.sh"},"createdAt":"2026-05-13T01:05:02.846Z"}],"sources":[{"listingId":"95662812-9dfa-46df-85c4-e4d282338eb9","source":"github","sourceId":"Fearvox/multica-ultimate-workbench/workbench-goal-mode","sourceUrl":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-goal-mode","isPrimary":false,"firstSeenAt":"2026-05-13T01:05:02.846Z","lastSeenAt":"2026-05-18T19:07:13.620Z"}],"details":{"listingId":"95662812-9dfa-46df-85c4-e4d282338eb9","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Fearvox","slug":"workbench-goal-mode","github":{"repo":"Fearvox/multica-ultimate-workbench","stars":12,"topics":["agent-skills","ai-agents","claude-code","codex","hermes-agent","multica","sdd","skills-sh"],"license":null,"html_url":"https://github.com/Fearvox/multica-ultimate-workbench","pushed_at":"2026-05-14T23:12:50Z","description":"Public multi-agent workbench skill pack for SDD, review gates, context discipline, VM lanes, Sanity context, and autonomous agent coordination.","skill_md_sha":"eeca50856400890e3939f5930d6169d7d25c2854","skill_md_path":"skills/workbench-goal-mode/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-goal-mode"},"layout":"multi","source":"github","category":"multica-ultimate-workbench","frontmatter":{"name":"workbench-goal-mode","description":"Goal-persistence execution wrapper for autonomous work that must continue across turns until the stated objective is actually satisfied."},"skills_sh_url":"https://skills.sh/Fearvox/multica-ultimate-workbench/workbench-goal-mode"},"updatedAt":"2026-05-18T19:07:13.620Z"}}