Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add closedloop-ai/claude-plugins/plugin install codeWrote 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/closedloop-ai/claude-plugins/orchestrator-sequences)<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/orchestrator-sequences"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/orchestrator-sequences/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/closedloop-ai/claude-plugins/orchestrator-sequences"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/orchestrator-sequences.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 | $0.00130 | $0.00741 |
| Opus 5.5 | $0.00052 | $0.00296 |
| Sonnet 5.5 | $0.00026 | $0.00148 |
| Haiku 4.5 | $0.00013 | $0.00074 |
Grade A, and why
orchestrator-sequences scanned grade A with 0 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator Reusable Procedures
These two procedures are referenced by name throughout the orchestrator prompts (prompt.md, plan-prompt.md, execute-prompt.md). They live here as the single source of truth so a change propagates to all three orchestrators at once. Substitute $CLOSEDLOOP_WORKDIR with the literal resolved workdir path in any subagent prompt (never the literal string $CLOSEDLOOP_WORKDIR).
PLAN_VALIDATION_SEQUENCE
Use this sequence whenever a phase needs full plan validation (structural + semantic):
- Activate
code:plan-validateskill (runs Python script against $CLOSEDLOOP_WORKDIR) - If
FORMAT_ISSUES: launch @code:plan-writer to fix format issues, then re-activatecode:plan-validate - If
VALID: launch @code:plan-validator with prompt: "WORKDIR=$CLOSEDLOOP_WORKDIR. SEMANTIC ONLY: Check semantic consistency of $CLOSEDLOOP_WORKDIR/plan.json — verify storage/query alignment and task/architecture decision consistency. Skip structural validation (already passed)." - If semantic check finds issues: launch @code:plan-writer to fix, then re-activate
code:plan-validate
AWAITING_USER_SEQUENCE
Use this sequence at any hard-stop that requires user action before continuing. The caller supplies the per-site phase, reason, file (path or null), and command (the resume command — built from the resolved CLOSEDLOOP_ORIGINAL_ARGS value, never the literal string $ARGUMENTS):
- FIRST — Write state.json with AWAITING_USER status:
echo '{"phase": "<current phase>", "status": "AWAITING_USER", "reason": "<why>", "userAction": {"description": "<what user should do>", "file": "<path or null>", "command": "<resume command>"}, "timestamp": "'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' > $CLOSEDLOOP_WORKDIR/state.json - Record the native-command terminal iteration once:
bash "$CLAUDE_PLUGIN_ROOT/scripts/record_native_iteration_once.sh" "$CLOSEDLOOP_WORKDIR" 2>/dev/null || true - ONLY AFTER state.json is written: Output your command's completion promise:
<promise>PLAN_COMPLETE</promise>for/code:create-plan,<promise>IMPLEMENTATION_COMPLETE</promise>for/code:execute-implementation, or<promise>COMPLETE</promise>for/code:code. Use the single promise token defined by your own prompt. - Tell the user what to do (review file, fix issues, run command)
- HARD STOP — Do not continue even if the user asks
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 Changed · +1 tokens per session 0942df26c671
- 1mo ago First seen · 33 lines · 129 tokens per session scan A 3aa510952187
orchestrator-sequences is a skill published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 130 tokens to every session and 741 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
grounded-citations
Ground answers and documents in cited, verifiable sources.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
mcporter
List, auth, and call MCP servers/tools from the terminal.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.