EngramGraph: Skill for Claude Code

.agents/skills/orchestrate/SKILL.md

orchestrate is a skill for Claude Code from AsiaOstrich/EngramGraph. It costs 78 tokens per session (1,510 once invoked), scanned C, original, MIT.

A tool that executes a plan.json file as dependent tasks, running independent tasks in parallel and later tasks only after their prerequisites finish.

In plain words
What is it for?
Use it to carry out multi-step development plans, preview them without running changes, and isolate tasks in separate Git worktrees.
Why use it?
It removes the need to coordinate task order manually and checks the plan for structural and potentially dangerous commands before execution.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is AsiaOstrich/EngramGraph's own configuration. It tells Claude Code how to work on EngramGraph itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything EngramGraph configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/AsiaOstrich/EngramGraph/main/.agents/skills/orchestrate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AsiaOstrich/EngramGraph

Made for: Claude Code.

Wrote 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.

agentmods badge for orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/asiaostrich/engramgraph/orchestrate/github.svg)](https://agentmods.dev/skills/asiaostrich/engramgraph/orchestrate)
Your own site
<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.

agentmods 80×15 button for orchestrate

Your own site · 80×15
<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>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,510 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 14d ago against content hash 79f06d5f6b2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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`)
.agents/skills/orchestrate/SKILL.md · 169 lines

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:

  1. 讀取 JSON 檔案,解析為任務清單
  2. 驗證結構:tasks 非空、每個 task 含 id、title、spec
  3. 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
  4. 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:

  1. 同層並行:同一層的 tasks 在同一訊息中啟動多個 Agent tool
  2. 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}"
  3. 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:

  1. 使用 Bash tool 執行 verify_command
  2. 成功:記錄 status: "success"
  3. 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

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

Read the full file on GitHub · 169 lines

Changes

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.

  1. 14d ago First seen · 169 lines · 78 tokens per session scan C 79f06d5f6b2c

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

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.

makecindy/cindy · 57 tokens

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.

automateyournetwork/netclaw · 62 tokens

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.

chrisbanes/skills · 33 tokens

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…

PostHog/posthog · 136 tokens

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.

educlopez/ui-craft · 52 tokens