{"id":"8ed2994e-fa20-4205-b5cb-6c3f5ed828dc","shortId":"VCnmEB","kind":"skill","title":"executing-plans","tagline":"Use when you have a written implementation plan to execute in a separate session with review checkpoints","description":"# Executing Plans\n\n## Overview\n\nLoad plan, review critically, execute all tasks, report when complete.\n\n**Announce at start:** \"I'm using the executing-plans skill to implement this plan.\"\n\n**Note:** Tell your human partner that Aegis works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use aegis:subagent-driven-development instead of this skill.\n\n## The Process\n\n### Step 1: Load and Review Plan\n1. Read plan file\n2. Review critically - identify any questions or concerns about the plan\n3. If concerns: Raise them with your human partner before starting\n4. If no concerns: Create TodoWrite and proceed\n\n### Step 1.5: Long-Task Checkpoint Setup\n\nIf the plan has multiple tasks, may span sessions, or includes architecture / contract / workflow changes:\n\n1. Announce: \"I'm using the long-task-continuation skill to keep this plan checkpointed and drift-aware.\"\n2. Load aegis:long-task-continuation.\n3. Create the initial checkpoint from the plan:\n   - current todo\n   - active task\n   - completed tasks\n   - evidence refs\n   - blockers\n   - next step\n4. Before each task, restate the current checkpoint.\n5. After each task, update checkpoint, evidence refs, and drift check.\n\n### Step 2: Execute Tasks\n\nFor each task:\n1. Mark as in_progress\n2. Follow each step exactly (plan has bite-sized steps)\n3. Run verifications as specified\n4. Update `TodoCheckpointDraft` and `DriftCheckDraft` before marking the task completed\n5. Mark as completed\n\n### Step 3: Complete Development\n\nAfter all tasks complete and verified:\n- Announce: \"I'm using the finishing-a-development-branch skill to complete this work.\"\n- **REQUIRED SUB-SKILL:** Use aegis:finishing-a-development-branch\n- Follow that skill to verify tests, present options, execute choice\n\n## When to Stop and Ask for Help\n\n**STOP executing immediately when:**\n- Hit a blocker (missing dependency, test fails, instruction unclear)\n- Plan has critical gaps preventing starting\n- You don't understand an instruction\n- Verification fails repeatedly\n\n**Ask for clarification rather than guessing.**\n\n## When to Revisit Earlier Steps\n\n**Return to Review (Step 1) when:**\n- Partner updates the plan based on your feedback\n- Fundamental approach needs rethinking\n\n**Don't force through blockers** - stop and ask.\n\n## Remember\n- Review plan critically first\n- Follow plan steps exactly\n- Don't skip verifications\n- Reference skills when plan says to\n- Stop when blocked, don't guess\n- Never start implementation on main/master branch without explicit user consent\n\n## Integration\n\n**Required workflow skills:**\n- **aegis:using-git-worktrees** - REQUIRED: Set up isolated workspace before starting\n- **aegis:writing-plans** - Creates the plan this skill executes\n- **aegis:finishing-a-development-branch** - Complete development after all tasks","tags":["executing","plans","aegis","ganyuanran","add","agent-skills","ai-agents","ai-coding","baseline-first","claude-code","codex","coding-agents"],"capabilities":["skill","source-ganyuanran","skill-executing-plans","topic-add","topic-agent-skills","topic-ai-agents","topic-ai-coding","topic-baseline-first","topic-claude-code","topic-codex","topic-coding-agents","topic-evidence-driven","topic-first-principles","topic-opencode","topic-software-architecture"],"categories":["Aegis"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/GanyuanRan/Aegis/executing-plans","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add GanyuanRan/Aegis","source_repo":"https://github.com/GanyuanRan/Aegis","install_from":"skills.sh"}},"qualityScore":"0.581","qualityRationale":"deterministic score 0.58 from registry signals: · indexed on github topic:agent-skills · 262 github stars · SKILL.md body (2,932 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":"2026-05-18T18:54:49.237Z","embedding":null,"createdAt":"2026-05-04T19:05:08.100Z","updatedAt":"2026-05-18T18:54:49.237Z","lastSeenAt":"2026-05-18T18:54:49.237Z","tsv":"'1':103,108,164,236,367 '1.5':143 '2':112,184,230,241 '3':123,191,252,272 '4':134,210,257 '5':218,267 'access':60 'activ':201 'aegi':55,91,186,301,428,440,450 'announc':34,165,281 'approach':378 'architectur':160 'ask':321,352,388 'avail':89 'awar':183 'base':373 'better':58 'bite':249 'bite-s':248 'block':410 'blocker':207,330,385 'branch':290,306,419,455 'chang':163 'check':228 'checkpoint':20,147,179,195,217,223 'choic':316 'clarif':354 'claud':82 'code':83 'codex':85 'complet':33,203,266,270,273,278,293,456 'concern':119,125,137 'consent':423 'continu':173,190 'contract':161 'creat':138,192,444 'critic':27,114,339,392 'current':199,216 'depend':332 'develop':95,274,289,305,454,457 'drift':182,227 'drift-awar':181 'driftcheckdraft':261 'driven':94 'earlier':361 'evid':205,224 'exact':245,397 'execut':2,13,21,28,42,231,315,325,449 'executing-plan':1,41 'explicit':421 'fail':334,350 'feedback':376 'file':111 'finish':287,303,452 'finishing-a-development-branch':286,302,451 'first':393 'follow':242,307,394 'forc':383 'fundament':377 'gap':340 'git':431 'guess':357,413 'help':323 'higher':71 'hit':328 'human':52,130 'identifi':115 'immedi':326 'implement':10,46,416 'includ':159 'initi':194 'instead':96 'instruct':335,348 'integr':424 'isol':436 'keep':176 'load':24,104,185 'long':145,171,188 'long-task':144 'long-task-continu':170,187 'm':38,167,283 'main/master':418 'mark':237,263,268 'may':155 'miss':331 'much':57 'multipl':153 'need':379 'never':414 'next':208 'note':49 'option':314 'overview':23 'partner':53,131,369 'plan':3,11,22,25,43,48,107,110,122,151,178,198,246,337,372,391,395,405,443,446 'platform':76 'present':313 'prevent':341 'proceed':141 'process':101 'progress':240 'qualiti':64 'question':117 'rais':126 'rather':355 'read':109 'ref':206,225 'refer':402 'rememb':389 'repeat':351 'report':31 'requir':296,425,433 'restat':214 'rethink':380 'return':363 'review':19,26,106,113,365,390 'revisit':360 'run':73,253 'say':406 'separ':16 'session':17,157 'set':434 'setup':148 'signific':70 'size':250 'skill':44,99,174,291,299,309,403,427,448 'skill-executing-plans' 'skip':400 'source-ganyuanran' 'span':156 'specifi':256 'start':36,133,342,415,439 'step':102,142,209,229,244,251,271,362,366,396 'stop':319,324,386,408 'sub':298 'sub-skil':297 'subag':62,78,87,93 'subagent-driven-develop':92 'support':79 'task':30,146,154,172,189,202,204,213,221,232,235,265,277,460 'tell':50 'test':312,333 'todo':200 'todocheckpointdraft':259 'todowrit':139 'topic-add' 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-baseline-first' 'topic-claude-code' 'topic-codex' 'topic-coding-agents' 'topic-evidence-driven' 'topic-first-principles' 'topic-opencode' 'topic-software-architecture' 'unclear':336 'understand':346 'updat':222,258,370 'use':4,39,90,168,284,300,430 'user':422 'using-git-worktre':429 'verif':254,349,401 'verifi':280,311 'without':420 'work':56,67,295 'workflow':162,426 'workspac':437 'worktre':432 'write':442 'writing-plan':441 'written':9","prices":[{"id":"24060b57-83dd-4e5c-be2c-ee8c3c88b4c9","listingId":"8ed2994e-fa20-4205-b5cb-6c3f5ed828dc","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"GanyuanRan","category":"Aegis","install_from":"skills.sh"},"createdAt":"2026-05-04T19:05:08.100Z"}],"sources":[{"listingId":"8ed2994e-fa20-4205-b5cb-6c3f5ed828dc","source":"github","sourceId":"GanyuanRan/Aegis/executing-plans","sourceUrl":"https://github.com/GanyuanRan/Aegis/tree/main/skills/executing-plans","isPrimary":false,"firstSeenAt":"2026-05-04T19:05:08.100Z","lastSeenAt":"2026-05-18T18:54:49.237Z"}],"details":{"listingId":"8ed2994e-fa20-4205-b5cb-6c3f5ed828dc","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"GanyuanRan","slug":"executing-plans","github":{"repo":"GanyuanRan/Aegis","stars":262,"topics":["add","agent-skills","ai-agents","ai-coding","architecture-driven-development","baseline-first","claude-code","codex","coding-agents","evidence-driven","first-principles","opencode","software-architecture","tdd","tlref"],"license":"mit","html_url":"https://github.com/GanyuanRan/Aegis","pushed_at":"2026-05-18T11:05:01Z","description":"Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.","skill_md_sha":"dfc4b7f96f801a6f3dad280b3e3e0a6affd3162c","skill_md_path":"skills/executing-plans/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/GanyuanRan/Aegis/tree/main/skills/executing-plans"},"layout":"multi","source":"github","category":"Aegis","frontmatter":{"name":"executing-plans","description":"Use when you have a written implementation plan to execute in a separate session with review checkpoints"},"skills_sh_url":"https://skills.sh/GanyuanRan/Aegis/executing-plans"},"updatedAt":"2026-05-18T18:54:49.237Z"}}