orchestrator-bootstrap
Skill0 starsChanged 3 months agoApache-2.0View on GitHub
Session-start routine for orchestrator. Raw-read the required session context first. Never block on absent context.
In this repository78 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/go-skills-knowledge-pack/AGENTS.mdAGENTS.md
- .agents/skills/rust-skills-knowledge-pack/AGENTS.mdAGENTS.md
- .agents/skills/typescript-skills-knowledge-pack/AGENTS.mdAGENTS.md
- .claude/skills/go-skills-knowledge-pack/AGENTS.mdAGENTS.md
- .claude/skills/rust-skills-knowledge-pack/AGENTS.mdAGENTS.md
- .claude/skills/typescript-skills-knowledge-pack/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/00-general.mdcCursor rule
- .cursor/rules/revharness-critical.mdcCursor rule
- .cursor/rules/revharness-detailed.mdcCursor rule
- auto-orchestratorSkill
- baseline-protectionSkill
- client-distribution-readinessSkill
- cloudflare-deploy-guardSkill
- codex-app-server-guardSkill
- codex-app-server-product-integrationSkill
- codex-callerSkill
- context-compactorSkill
- cursor-callerSkill
- delegated-development-disciplineSkill
- deploy-command-disciplineSkill
- design-principlesSkill
- development-constitutionSkill
- development-junk-cleanupSkill
- go-skills-knowledge-packSkill
- harness-official-docs-updateSkill
- naming-normalization-guardSkill
- payload-cms-deploy-guardSkill
- production-function-implementerSkill
- research-handoffSkill
- rev-harness-lifecycleSkill
- review-workflowSkill
- root-cause-first-disciplineSkill
- rust-skills-knowledge-packSkill
- scope-guardSkill
- self-growth-proposal-triageSkill
- shared-client-wrapper-safetySkill
- slice-designerSkill
- staff-code-reviewerSkill
- structured-mentorSkill
- supabase-deploy-guardSkill
- system-plannerSkill
- typescript-skills-knowledge-packSkill
- auto-orchestratorSkill
- baseline-protectionSkill
- client-distribution-readinessSkill
- cloudflare-deploy-guardSkill
- codex-app-server-guardSkill
- codex-app-server-product-integrationSkill
- codex-callerSkill
- context-compactorSkill
- cursor-callerSkill
- delegated-development-disciplineSkill
- deploy-command-disciplineSkill
- design-principlesSkill
- development-constitutionSkill
- development-junk-cleanupSkill
- go-skills-knowledge-packSkill
- harness-official-docs-updateSkill
- The first 60 shown.
The file
Files
Skill: Orchestrator Bootstrap
When to use
- orchestrator role で session を新規開始する直後
- 既存 handover を受けて bootstrap する直後
Goal
session-open の必須 context は raw-read で取得する。
Steps
- Raw-read required session context:
a.
AGENTS.mdと.agent_rules/RULES.mdの applicable bootstrap / invariant sections。 b. 現 active plan(例:.agent/active/plan_*.md)と current handover / worker packet。 c. task-local acceptance / evidence instructions。 - Active lineage:
.agent/active/sow/task-lineage-ledger.mdの該当 lineage entry を raw-read する。 - Auto-memory consult: family-native memory path (
~/.claude/projects/<project>/memory/MEMORY.mdfor Claude,~/.Codex/projects/<project>/memory/MEMORY.mdfor Codex) の index を読み、baseline-protection、Option D、plan-lgtm、codex-two-stageなど関連 pattern を identify する。 - User meta-goal 再確認: user の session-start message と
.agent/PROJECT_CONTEXT.mdの meta-goal section を参照し、orchestrator の意思決定をそこへ align する。 - Truth read order 検証: AGENTS.md §Read Order の numbered read order(step 3 = .agent_rules/RULES.md と incorporated shared modules)に従い authority を確認する。role 固有の詳細は docs/roles/orchestrator.md を参照する。
Exit criteria
- 上記 5 step が完了している
- session-open context が
~30k token以内に収まっている - 超過時は compression または fork を検討する
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

