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 randommonicle/claude-skills --skill commission-the-rostergit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/commission-the-roster)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/commission-the-roster"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/commission-the-roster/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/randommonicle/claude-skills/commission-the-roster"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/commission-the-roster.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 | $0.00123 | $0.04039 |
| Opus 5 | $0.00062 | $0.02020 |
| Sonnet 5 | $0.00025 | $0.00808 |
| Haiku 4.5 | $0.00012 | $0.00404 |
Grade A, and why
commission-the-roster 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 12d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commission the roster
A single PropOS session appointed a lead plus five senior agents, each with two interns, plus a merge sitter. Roughly eighteen identities. The surfaced ledger came to about 4.6M tokens over 16 agent-run-segments, averaging 290k a segment, and it emptied a five-hour usage window well before the wave finished. It delivered five merged PRs, so it was not a failure. It was three or four times dearer than the same five PRs needed to be, and none of the excess was visible while it happened.
Where it actually went, largest first:
- The orientation tax. Every fresh agent loaded the project skills, read the project instructions, grepped migrations for the live schema, and read a handover before producing a line. Call it 60k to 120k each. Across 16 segments that is roughly 1.5M tokens spent re-deriving facts the lead already held in front of it.
- Tier misallocation. Opus seniors were assigned a seventeen-site comment pass, test scaffolding, docs mechanics, evidence capture and git chores. Every one of those is Sonnet work. The comment pass did not need judgement, it needed care.
- An agent with no artifact. The merge sitter cost 315k, about 7% of the session, and twice
reported "continuing to watch" after it had gone idle. A blocking
gh run watchin a background command costs approximately nothing and cannot lie about being awake.
Headcount was not the variable. Cutting the roster from eighteen to three, with each segment still costing 290k and the work still needing 16 segments, would have saved nothing.
The two dials, which are constantly confused
Total burn = scope x context-per-agent-turn x model rate. Every tool result a subagent receives is re-sent with the next call, so an agent holding 120k of context and making 40 tool calls is not a 120k agent. Context size per agent is the multiplier on everything it does. Fix total burn with briefs, tiers and tight scope.
How fast the window empties = concurrency. Three agents in parallel cost the same tokens as three in series; they just front-load the spend into a rolling window. Fix that, and only that, with a concurrency cap.
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.
- 12d ago First seen · 280 lines · 123 tokens per session scan A 67eaf26d5f9d
commission-the-roster is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 6d ago), licensed Apache-2.0. It adds 123 tokens to every session and 4,039 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…