Guides the design and review of agent startup context, including role files and links to authoritative records. It helps identify stale guidance, missing updates, overloaded startup files, and instructions that lose the purpose of the work.
中文简介正在准备中。当前显示英语简介。
Use when designing or auditing how an agent becomes useful after launch — AGENTS.md overlays, role files, skills, rig specs, workflow specs, startup checklists, refocus messages, "rig context" surface. Covers the 4 failure modes that make startup context fail (old rig spec misses current operating mode; current agents never told about new guidance; startup file as dumping ground; orchestrator transmits implementation without preserving product intent).
安装前可以查看交给 AI 代理的指令内容。
How an agent becomes useful after launch: AGENTS.md overlays, role
files, skills, rig specs, workflow specs, startup checklists, refocus
messages, and the current rig context retrieval and profile surface.
It is the current concrete startup path inside the broader context-engineering-and-retrieval primitive. Startup gets a seat into the right initial shape; context engineering is the larger question of how a seat gets the right context for the work it is doing right now.
Most coordination failures are not tool failures; they are context failures. Agents need to know their role, operating mode, coordination convention, boundaries, and current product intent. If startup context is scattered or stale, agents execute the wrong thing very efficiently.
session-compaction-and-restoreRun rig whoami --json, then resolve project.yaml -> mission.yaml -> active slice.yaml -> selected component or wave map -> addressed context. The complete
lookup and precedence rule is docs/reference/product-journey-sdlc.md#resolve-the-selected-path
(installed: $OPENRIG_HOME/reference/product-journey-sdlc.md#resolve-the-selected-path).
Read the selected addresses and source needed for this task; skills available in
your profile are capabilities, not a mandatory reading list. No composition means
light Part A. Role names and idle seats add no gates. Explicit rigor and authored
wave boundaries retain their named checks.
Startup files are address maps, not universal reading mandates. Do not preload unrelated planning/review doctrine or require per-file ACKs and quizzes. Skill availability is distinct from loading its full body. An old packet does not choose the current work. Missing selected context is a named gap to resolve.
In a disposable fresh session, observe the actual reads and resulting next action. Test no-selection, explicit rigor, and wave-boundary cases. An edit is not evidence that an already-running seat adopted it; adoption needs an authorized refresh or next-launch observation. Do not clear or re-prime a live seat merely to test prose.
When a seat's startup is artifact-backed mental-model rebuild (active-work reentry case, distinct from reusable Agent Starters / priming packs):
rig whoami > target rigspec > bounded latest transcript > full transcript > touched-files > restore-summary.jsonInventory the selected startup inputs: AGENTS/role/CULTURE overlays, replay context, and any declared restore packet or starter. Record where each comes from, whether it is current, and why this task needs it. An available skill or old packet does not select the work.
Use the task-scoped startup path above to resolve current authority. Permission
to read an input is not permission to rewrite its source; writes follow the
active project/rig policy and assignment. Load
skills/openrig-operating-model/SKILL.md with rig context get when deciding
where durable context belongs.
Per agent-startup-guide.md (product reference doc) and the team handbook:
| Startup files | Skills |
|---|---|
| Rig-specific, role-specific identity | Reusable SOPs / methodology / knowledge |
| Tell agent WHO it is, WHAT it's working on, HOW this team operates | Tell agent HOW to do something (transferable across rigs) |
Examples: role.md, CULTURE.md, startup/context.md | Examples: openrig-user, test-driven-development, vault-user |
| Authored per-rig | Authored once, used everywhere |
Don't put skill content in startup files. Don't put identity content in skills. The 7-layer additive startup model (agent / profile / rig / culture / pod / member / operator) handles the layering.
mission-slice-sop — load when starting assigned mission/slice work; the light artifact and handoff procedure for SPEC.md, NOTES.md, PROGRESS.md and proof. It does not choose the SDLC for the task.forming-an-openrig-mental-model skill — orientation for new agentssession-compaction-and-restore skill — restore-time startup ingestionagent-starters skill — reusable starter manifests that compose startup contextopenrig-operating-model skill — placement and authority of durable contextopenrig/docs/reference/agent-startup-guide.md (product reference doc; not a skill) — the 7-layer additive startup model + delivery hints还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Automate website interactions through a command-line browser tool. Navigate pages, fill forms, extract text, save screenshots or PDFs, reuse login sessions, and compare page states to check the effects of actions or website changes.
中文简介正在准备中。当前显示英语简介。
Design and maintain applications where OpenRig agents help run the system. Organize instructions, shared state, and artifact checks, then trace unexpected behavior to the code, skill, or schema that needs repair.
中文简介正在准备中。当前显示英语简介。
Design and run bounded procedures in environments where current conditions are uncertain. The skill separates agent judgment from precise tool actions, verifies each effect, and records checkpoints so interrupted work can resume from observed evidence.
中文简介正在准备中。当前显示英语简介。
Create reusable starting configurations that combine an agent’s role, startup context, and source history. The skill guides registry entries, checks whether their sources are current, and manages their progression from initial capture to recommendation or retirement.
中文简介正在准备中。当前显示英语简介。
Configure selected OpenRig command permissions in Claude Code or Codex at the agreed project or user scope. Preserve existing restrictions, verify that settings load and behave as intended, and record additions so they can be removed later.
中文简介正在准备中。当前显示英语简介。
Turn rough meeting notes, customer requests, and product ideas into structured backlog entries, a list of possible improvements. Capture who needs each idea and why, categorize it, and update matching entries with new evidence.
中文简介正在准备中。当前显示英语简介。