Borrowing it
Nothing to install: this file belongs to AsiaOstrich/EngramGraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AsiaOstrich/EngramGraph/main/.agents/skills/orchestrate/SKILL.mdgit clone --depth 1 https://github.com/AsiaOstrich/EngramGraphWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/asiaostrich/engramgraph/orchestrate)<a href="https://agentmods.dev/skills/asiaostrich/engramgraph/orchestrate"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/orchestrate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/asiaostrich/engramgraph/orchestrate"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.01510 |
| Opus 5.5 | $0.00031 | $0.00604 |
| Sonnet 5.5 | $0.00016 | $0.00302 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade C, and why
orchestrate scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
3. 安全掃描:檢查 `task.spec` 是否含危險指令(`rm -rf /`、`DROP DATABASE`、`git push --force`) How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orchestrate — 任務計畫編排 Skill
用法
/orchestrate <plan.json> # 執行計畫
/orchestrate <plan.json> --dry-run # 僅驗證,不執行
執行流程
Step 1: 讀取與解析計畫(Claude-native)
使用 Read tool 讀取 plan.json,直接由 Claude 解析:
- 讀取 JSON 檔案,解析為任務清單
- 驗證結構:
tasks非空、每個 task 含id、title、spec - 安全掃描:檢查
task.spec是否含危險指令(rm -rf /、DROP DATABASE、git push --force)- 若發現安全問題,列出所有問題並詢問使用者是否繼續
- 拓撲排序:依
depends_on欄位將 tasks 分組為執行層(layers)- Layer 0:沒有依賴的 tasks(可並行)
- Layer N:依賴全部在 Layer 0..N-1 中的 tasks
若 validation.valid 為 false,輸出錯誤訊息並停止。
Step 2: 呈現執行計畫
向使用者顯示解析結果:
計畫:<project> 品質:<quality>
──────────────────────────────────
Layer 0 (並行):T-001, T-002
Layer 1 (序列):T-003 (依賴 T-001)
Layer 2 (序列):T-004 (依賴 T-002, T-003)
──────────────────────────────────
共 4 個任務,3 個執行層
若使用 --dry-run:顯示以上摘要後立即停止,不啟動任何 Agent。
Step 3: 逐層執行
對 layers 陣列中的每一層:
- 同層並行:同一層的 tasks 在同一訊息中啟動多個 Agent tool
- Agent tool 參數:
prompt:task.spec + acceptance_criteria + user_intent 組合而成的執行提示isolation: "worktree":每個 task 在獨立 git worktree 執行description:"Task {task.id}: {task.title}"
- 等待完成:所有同層 agents 完成後,才進入下一層
Agent 提示範本:
Task: {task.title}
Spec:
{task.spec}
Acceptance Criteria:
{task.acceptance_criteria 逐條列出}
User Intent:
{task.user_intent}
After completing the task, run: {task.verify_command}
Step 4: 依賴失敗處理
如果某個 task 的 agent 回報失敗:
- 標記該 task 為
failed - 後續層中
depends_on包含該 task ID 的所有 tasks 標記為skipped - 繼續執行不受影響的 tasks
- 最終報告中標示失敗原因
Step 5: Quality Gate
每個 task 完成後,若 task 定義了 verify_command:
- 使用 Bash tool 執行
verify_command - 成功:記錄
status: "success" - 失敗:
- 若
quality為"strict"或"standard":啟動 Fix Loop - Fix Loop:將錯誤輸出回傳給 agent,重新執行(最多 3 次)
- 超過重試上限:標記為
failed
- 若
Step 6: Judge 審查(選用)
如果 task 定義了 judge: true:
- 啟動一個額外的 Agent tool 進行審查
- 提示:
審查 task {id} 的 git diff,依照 code-review 標準檢查 - Judge 結果附加到最終報告
Step 7: 產出報告
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 14d ago First seen · 169 lines · 78 tokens per session scan C 79f06d5f6b2c
orchestrate is a skill published in the GitHub repository AsiaOstrich/EngramGraph (3 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,510 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.
deliver-spec
Use when explicitly asked to deliver an approved GitHub or local spec through a reviewed pull request, or when a Project controller delegates one claimed implementation ticket.
stacking-prs
Create and manage GitHub native Stacked PRs in this repo with the gh stack CLI. Use when asked to stack PRs, split a large change into a stack, add a layer to a stack, restack or rebase a stack, adopt existing branches or PRs into a stack, check out someone else's stack, or land a stack. Covers creating and submitting…
friction-log
File contributor or agent papercuts as GitHub issues labeled friction, or investigate those issues as the daily friction-log Cloud Agent. Use when you hit repo friction, when asked to log friction, or when spawned to resolve open friction issues.