{"id":"3544962d-c926-47c2-a07d-2e42c657d319","shortId":"czNHwc","kind":"skill","title":"workbench-token-context-discipline","tagline":"Compact context, cache-aware execution, scoped evidence reads, and role-specific skill attachment discipline.","description":"# Workbench Token Context Discipline\n\nUse this skill when a task may pull large docs, long issue histories, many skills, big logs, or expensive model context.\n\n## Context Budget Rules\n\n- Start with indexes, file lists, IDs, summaries, and targeted searches.\n- Read the smallest slice that can answer the current question.\n- Prefer `rg`, `jq`, concise table output, and explicit IDs over dumping entire histories.\n- Summarize large sources before passing them to another agent.\n- Attach only role-relevant skills; more skills are not automatically better.\n- Stop and report if two consecutive reads are too large or mostly irrelevant.\n\n## SDD Handoff Compact Mode\n\nWhen entering an SDD-gated issue:\n\n1. Check whether the prior stage comment includes `HANDOFF_SUMMARY`.\n2. If it exists, read the summary header and the listed `SCOPED_EVIDENCE` before reading any wider history.\n3. If no handoff exists, read at most the latest three relevant comments, request or create a compact handoff, then stop broad scanning.\n4. Never read full issue lists, full agent rosters, or unrelated repo docs for a single-stage task unless the stage explains why.\n5. Output must fit in one reviewable comment. If it does not, compress rather than split.\n\n## Cache And Quota Awareness\n\n- Distinguish fresh input, output, cache read, and cache write when usage is under investigation.\n- Do not assume dashboard usage is wrong without local/request-level evidence.\n- Avoid repeated full-context reruns when a comment ID, file path, or artifact can be cited instead.\n- Keep Workbench Max and existing private agents out of broad binding changes unless explicitly assigned.\n\n## Output Contract\n\nReturn:\n\n- `CONTEXT_USED`: exact files, comments, commands, or IDs read.\n- `SKIPPED`: intentionally avoided broad reads and why.\n- `SUMMARY`: compact facts needed for the next step.\n- `NEXT_SMALL_READ`: the next targeted evidence query, if any.\n- `TOKEN_RISK`: normal / elevated / blocked.","tags":["workbench","token","context","discipline","multica","ultimate","fearvox","agent-skills","ai-agents","claude-code","codex","hermes-agent"],"capabilities":["skill","source-fearvox","skill-workbench-token-context-discipline","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-token-context-discipline","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 (1,958 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":"2026-05-18T19:07:15.002Z","embedding":null,"createdAt":"2026-05-13T01:05:05.056Z","updatedAt":"2026-05-18T19:07:15.002Z","lastSeenAt":"2026-05-18T19:07:15.002Z","tsv":"'1':128 '2':138 '3':156 '4':179 '5':203 'agent':91,186,271 'anoth':90 'answer':66 'artifact':260 'assign':279 'assum':239 'attach':20,92 'automat':102 'avoid':247,294 'awar':10,222 'better':103 'big':41 'bind':275 'block':321 'broad':177,274,295 'budget':48 'cach':9,219,227,230 'cache-awar':8 'chang':276 'check':129 'cite':263 'command':288 'comment':134,168,210,255,287 'compact':6,119,173,300 'compress':215 'concis':73 'consecut':109 'context':4,7,24,46,47,251,283 'contract':281 'creat':171 'current':68 'dashboard':240 'disciplin':5,21,25 'distinguish':223 'doc':35,191 'dump':80 'elev':320 'enter':122 'entir':81 'evid':13,150,246,313 'exact':285 'execut':11 'exist':141,160,269 'expens':44 'explain':201 'explicit':77,278 'fact':301 'file':53,257,286 'fit':206 'fresh':224 'full':182,185,250 'full-context':249 'gate':126 'handoff':118,136,159,174 'header':145 'histori':38,82,155 'id':55,78,256,290 'includ':135 'index':52 'input':225 'instead':264 'intent':293 'investig':236 'irrelev':116 'issu':37,127,183 'jq':72 'keep':265 'larg':34,84,113 'latest':165 'list':54,148,184 'local/request-level':245 'log':42 'long':36 'mani':39 'max':267 'may':32 'mode':120 'model':45 'most':115 'must':205 'need':302 'never':180 'next':305,307,311 'normal':319 'one':208 'output':75,204,226,280 'pass':87 'path':258 'prefer':70 'prior':132 'privat':270 'pull':33 'queri':314 'question':69 'quota':221 'rather':216 'read':14,60,110,142,152,161,181,228,291,296,309 'relev':96,167 'repeat':248 'repo':190 'report':106 'request':169 'rerun':252 'return':282 'review':209 'rg':71 'risk':318 'role':17,95 'role-relev':94 'role-specif':16 'roster':187 'rule':49 'scan':178 'scope':12,149 'sdd':117,125 'sdd-gate':124 'search':59 'singl':195 'single-stag':194 'skill':19,28,40,97,99 'skill-workbench-token-context-discipline' 'skip':292 'slice':63 'small':308 'smallest':62 'sourc':85 'source-fearvox' 'specif':18 'split':218 'stage':133,196,200 'start':50 'step':306 'stop':104,176 'summar':83 'summari':56,137,144,299 'tabl':74 'target':58,312 'task':31,197 'three':166 'token':3,23,317 'topic-agent-skills' 'topic-ai-agents' 'topic-claude-code' 'topic-codex' 'topic-hermes-agent' 'topic-multica' 'topic-sdd' 'topic-skills-sh' 'two':108 'unless':198,277 'unrel':189 'usag':233,241 'use':26,284 'whether':130 'wider':154 'without':244 'workbench':2,22,266 'workbench-token-context-disciplin':1 'write':231 'wrong':243","prices":[{"id":"3f6e744c-add4-4795-8b8d-7eeaf1f1275b","listingId":"3544962d-c926-47c2-a07d-2e42c657d319","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":"2026-05-13T01:05:05.056Z"}],"sources":[{"listingId":"3544962d-c926-47c2-a07d-2e42c657d319","source":"github","sourceId":"Fearvox/multica-ultimate-workbench/workbench-token-context-discipline","sourceUrl":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-token-context-discipline","isPrimary":false,"firstSeenAt":"2026-05-13T01:05:05.056Z","lastSeenAt":"2026-05-18T19:07:15.002Z"}],"details":{"listingId":"3544962d-c926-47c2-a07d-2e42c657d319","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Fearvox","slug":"workbench-token-context-discipline","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":"7a3c562360ea5475315bcf05c9ebaf65004e5d9e","skill_md_path":"skills/workbench-token-context-discipline/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-token-context-discipline"},"layout":"multi","source":"github","category":"multica-ultimate-workbench","frontmatter":{"name":"workbench-token-context-discipline","description":"Compact context, cache-aware execution, scoped evidence reads, and role-specific skill attachment discipline."},"skills_sh_url":"https://skills.sh/Fearvox/multica-ultimate-workbench/workbench-token-context-discipline"},"updatedAt":"2026-05-18T19:07:15.002Z"}}