Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/choiyounggi/dev-loop/orchestratenpx skills add choiyounggi/dev-loop --skill orchestrategit clone --depth 1 https://github.com/choiyounggi/dev-loopWhat 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 | $0.00071 | $0.16972 |
| Opus 5 | $0.00036 | $0.08486 |
| Sonnet 5 | $0.00014 | $0.03394 |
| Haiku 4.5 | $0.00007 | $0.01697 |
Grade D, and why
orchestrate scanned grade D with 2 findings 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
pre-approve the three worker-management scripts in ~/.claude/settings.json?" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
routine in-worktree work (`rm -rf ./build`, `git checkout .`) turns into a How it starts
The opening of the file, as written. The whole thing — 1,010 lines — stays where its author put it; the contents beside it link to each section on GitHub.
orchestrate — multi-session orchestrator
You are the orchestrator. You do not implement — sessions do. You clarify, decompose, distribute, review, integrate, and merge. Autonomy lives inside the implementation loop; two human gates bracket it (task-split, pre-merge).
Scripts referenced below live in ${CLAUDE_PLUGIN_ROOT}/skills/orchestrate/scripts/.
Communication: session→orchestrator via .orchestration/status/<task>.json;
orchestrator→session via launch-session.sh (the first prompt) then
send-prompt.sh (every later one), carrying templates/session-prompt.md §1–§4 on
tmux, or the Task --spec (same file, §O1–§O4) on Orca.
Asking the user — every question is a chooser (REQUIRED)
Every question this skill puts to the user is delivered with the AskUserQuestion tool, so they answer by selecting an option instead of typing a reply. Prose in the turn is the briefing (task list, graph, slot count, cost note, diff); the decision is always the tool call. This covers Phase 0 frontier rounds, Gate 1 (task split and substrate), Gate 2, a Phase 3 deadlock, and any worker escalation that needs a human verdict.
Required shape
- One call per round, up to 4 questions in it. A frontier wider than 4 → back-to-back calls of ≤4 questions, numbering continuous across them; never one question per turn.
- Each question carries 2–4 options; the recommended answer is option 1, its
label suffixed
(Recommended).header≤12 chars. - Options are the concrete outcomes ("approve as proposed", "drop task 3", "Orca"), not a yes/no restatement of the prose.
multiSelect: truewhen the items are independent (e.g. which optional tasks to include).- Free-text is already available to the user as "Other" — never author an "Other" option.
Predicate-keyed
| Situation | Ask |
|---|---|
| Phase 0, frontier of open decisions | one question per frontier item, ≤4 per call, each with its recommended answer |
Gate 1, orca-detect.sh non-zero (no Orca) |
Q1 task split: approve as proposed / revise / abort. Say nothing about substrates |
Gate 1, orca-detect.sh exit 0 (Orca present) |
the SAME call carries Q1 task split and Q2 substrate: Orca / tmux |
| Gate 2, after showing the integration diff | Q1: merge / send back for rework / abort |
| Phase 3 deadlock, or an escalation needing a human | options = the concrete resolutions available, not "how should I proceed?" |
| You are a worker session (templates/session-prompt.md) | never AskUserQuestion — escalate via ask-coordinator.sh; only the coordinator asks the user |
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/ask-coordinator.sh 2.0 KB runs code
- scripts/escalation-dir.sh 1.2 KB runs code
- scripts/graph-add.sh 4.7 KB runs code
- scripts/graph-drop.sh 3.9 KB runs code
- scripts/install-permission-rules.sh 5.0 KB runs code
- scripts/launch-session.sh 16 KB runs code
- scripts/orca-detect.sh 1.1 KB runs code
- scripts/orca-spawn.sh 5.1 KB runs code
- scripts/orca-wait.sh 14 KB runs code
- scripts/orca-worker-stalled.sh 4.7 KB runs code
- scripts/orca-worker-start.sh 16 KB runs code
- scripts/orca-worktree-alive.sh 1.5 KB runs code
- scripts/ready-set.sh 6.7 KB runs code
- scripts/safe-cleanup.sh 22 KB runs code
- scripts/send-prompt.sh 22 KB runs code
- scripts/setup-worktrees.sh 3.0 KB runs code
- scripts/status-update.sh 2.8 KB runs code
- scripts/test-floor.sh 7.7 KB runs code
- scripts/tmux-worker-stalled.sh 5.8 KB runs code
- scripts/token-report.sh 7.6 KB runs code
- scripts/watch-status.sh 13 KB runs code
- scripts/worker-guardrails.sh 3.4 KB runs code
- templates/brief.md 5.4 KB
- templates/review-report.md 1.3 KB
- templates/session-prompt.md 17 KB
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.
- yesterday First seen · 1,010 lines · 71 tokens per session scan D 486f0e036911
orchestrate is a skill published in the GitHub repository choiyounggi/dev-loop (4 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 16,972 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
kb-create
Operator procedure to declare and provision a new Knowledge Base GitOps-style, so it survives pod restarts.
kb-import
Agent-guided procedure to import an existing non-OKF wiki or knowledge base (Obsidian vault, markdown folder, wiki export) into a Cartographer KB, incrementally and without big-bang LLM rewriting.
deploy
Rilascia una nuova versione di Cartographer — merge della release PR di release-please, attesa della pipeline GitHub (binari, brew, ghcr), bump del manifest homelab, verifica rollout Flux e update del client locale via brew. Usare quando l'utente chiede di deployare/rilasciare una nuova versione di server e/o client.
implement-plan
Orchestrates implementation of one or more approved plan issues (label plan) into merged PRs through wave planning, delegation to dev subagents in isolated worktrees, coordinator review, and ordered squash-merge with topic-owned documentation conflict resolution. Use when the user asks to implement, ship, or land open…
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.