Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/majiayu000/claude-skill-registry --skill session-bootstrap명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据,按主题分组汇总"我都做了什么",并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
SOC 직업 분류 기준
SKILL.md 표시 중
| name | session-bootstrap |
| description | Agent init prompt. |
ao session bootstrap — the universal init promptOne-line value: every agent in the swarm starts with the same orientation report, regardless of model.
Every agent spawned into an AgentOps repository runs this first. No exceptions. The bootstrap is the contract that makes the future fungibility charter (soc-vuu6.29) operational: identical starting frames let you swap Claude for Codex (or vice versa) on any bead without re-orienting.
Triggers:
ao session bootstrap.hooks-authoring skill, it can fail-open auto-fire ao session bootstrap --robot and discard the exit code.agentopsd and headless CI agents call ao session bootstrap --json before claiming work.If you spawned without running it: stop, run it, then resume.
Four fail-open substeps, each producing a field in the session-bootstrap.v1 schema:
AGENTS.md and the post-soc-vuu6.3 siblings (AGENTS-WORKFLOW.md, AGENTS-CI.md, AGENTS-CODEX.md, AGENTS-RUNTIME.md). Reports which exist. The agent reads them itself once oriented; the bootstrap just confirms presence.onboard --auto — the future task-routed reading list subcommand under soc-vuu6.9. Currently P3 / not yet implemented: bootstrap falls back to phase="skipped:not-implemented" and continues without blocking.bd ready --json length. Surfaces what's immediately claimable. Fails to null if bd is missing or errors.null. Skipped with --no-mail or env MCP_AGENT_MAIL_DISABLED=1.| Flag | Effect |
|---|---|
--json | Emit the full status object (machine-readable, matches the v1 schema) |
--robot | Same as --json plus a tight exit-code contract for SessionStart hooks |
--no-mail | Skip the mcp-agent-mail probe even when the MCP server is reachable |
Default (no flags): one-line human summary on stdout, plus a stderr warning if AGENTS.md is missing.
{
"agents_md_read": true,
"agents_siblings_read": ["AGENTS-WORKFLOW.md", "AGENTS-CI.md", "AGENTS-CODEX.md", "AGENTS-RUNTIME.md"],
"onboard_phase": "skipped:not-implemented",
"ready_beads_count": 12,
"mail_unread_count": null,
"runtime": "codex",
"started_at": "2026-05-21T01:50:00Z",
"bootstrap_version": "v1"
}
Schema at schemas/session-bootstrap.v1.schema.json — every field is required; nullable fields carry null when the substep was skipped or errored.
The agent-fungibility-philosophy mandates: one init prompt for every agent regardless of type. Today every operator hand-rolls orientation: "read AGENTS.md, check bd ready, register with the mail server, then start." Two agents spawned by two different operators don't have the same starting frame. That's anti-fungibility — the swarm can't safely swap them mid-bead.
ao session bootstrap is the operational primitive that closes the gap. It's deliberately tiny: ~50 LOC Go + a JSON schema. It does the same four things every time, in the same order, with the same fail-open semantics. Then the agent reads the orientation tier-split itself.
AGENTS.md themselves.bd binary, an unavailable MCP server, or a deferred onboard produces a null/skipped marker and the command still exits 0. The agent decides what to do with degraded orientation.onboard --auto subcommand) — when implemented, bootstrap's onboard substep wires through automatically via subprocess shellout.cli/cmd/ao/session_bootstrap_test.go — 8 cases (full status, missing AGENTS.md, partial split, no-mail flag, runtime detection, human summary, JSON round-trip).validate-skill-frontmatter keeps the SKILL.md frontmatter contract intact.validate-session-bootstrap-schema if schema-drift becomes a concern.AGENTS.md — orientation entry-point that points here.AGENTS-WORKFLOW.md — what to do after bootstrap reports.schemas/session-bootstrap.v1.schema.json — full output contract.