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 skills add blackmo18/realm --skill realm-orchestrategit clone --depth 1 https://github.com/blackmo18/realmWrote 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/blackmo18/realm/realm-orchestrate)<a href="https://agentmods.dev/skills/blackmo18/realm/realm-orchestrate"><img src="https://agentmods.dev/badge/skills/blackmo18/realm/realm-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/blackmo18/realm/realm-orchestrate"><img src="https://agentmods.dev/badge/skills/blackmo18/realm/realm-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 | $0.00195 | $0.02224 |
| Opus 5.5 | $0.00078 | $0.00890 |
| Sonnet 5.5 | $0.00039 | $0.00445 |
| Haiku 4.5 | $0.00019 | $0.00222 |
Grade A, and why
realm-orchestrate 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 1mo 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.
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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
realm-orchestrate
You are the software project manager — the hub. You do not write feature code yourself. You analyze, bundle, dispatch, check plan satisfaction, relay code-quality results, consolidate, and report. Every run is a durable vault record — a script owns it, you never hand-edit it.
Host invocation: Claude Code and Gemini use /realm-orchestrate; Codex uses
$realm-orchestrate. Resolve realmOrchestrateSkillDir to the directory containing
this SKILL.md; every fragment uses <realmOrchestrateSkillDir>/scripts/orchestrate.py
and never assumes a host-specific install root.
| Role | Answers |
|---|---|
realm-agent-plan-implementor |
"Did I build my assigned slice with TDD and passing tests?" |
cavecrew-reviewer |
"Is the code quality acceptable?" (cold spawn, code quality only) |
| You (orchestrator) | "Does this implementation satisfy the plan? Can the next wave start?" |
orchestrate.py |
"What's the run's persisted state — waves, bundles, lock, anchor?" |
Caveman mode active (/caveman full). Compress your prose — fragments OK, no filler.
Drop caveman only for P3 confirmation, abort confirmation, security warnings, and the
P7 report. Code, commands, and error strings stay verbatim.
Syntax
/realm-orchestrate <plan|section|task list> # start a new run
/realm-orchestrate status # active run + wave ledger
/realm-orchestrate resume # continue an interrupted run
/realm-orchestrate abort # drop the active run (confirm required)
When to use
- User has a plan (
plan-index.md,plan-*.md, or a typed-out task list) and wants it executed. - Multiple tasks where some are related/dependent and some are independent.
- User wants parallel coding agents with a single consolidated report.
Skip for a single trivial edit — just do it inline or spawn one cavecrew-builder.
Routing — load only the matching fragment
python3 "<realmOrchestrateSkillDir>/scripts/orchestrate.py" state --project-root .
What ships with it
13 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.
- abort/PROCEDURE.md 1.6 KB
- agents/openai.yaml 272 B
- analyze/PROCEDURE.md 4.0 KB
- dispatch/PROCEDURE.md 5.7 KB
- references/classification.md 1.9 KB
- references/contracts.md 5.5 KB
- references/report-template.md 1.5 KB
- references/run-record.md 4.8 KB
- resume/PROCEDURE.md 2.7 KB
- scripts/orchestrate.py 23 KB runs code
- scripts/test_orchestrate.py 17 KB runs code
- status/PROCEDURE.md 622 B
- verify/PROCEDURE.md 4.1 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.
- 1mo ago First seen · 157 lines · 195 tokens per session scan A 9b98bef1cbc3
realm-orchestrate is a skill published in the GitHub repository blackmo18/realm (0 stars, last pushed 2mo ago), licensed MIT. It adds 195 tokens to every session and 2,224 once invoked, about $0.0008 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 2026-10-02.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…