Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mathiasbourgoin/rosternpx agentmods add skills/mathiasbourgoin/roster/roster-runWrote 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/mathiasbourgoin/roster/roster-run)<a href="https://agentmods.dev/skills/mathiasbourgoin/roster/roster-run"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/roster-run/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/mathiasbourgoin/roster/roster-run"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/roster-run.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 | $0.00017 | $0.06664 |
| Opus 5 | $0.00009 | $0.03332 |
| Sonnet 5 | $0.00003 | $0.01333 |
| Haiku 4.5 | $0.00002 | $0.00666 |
Grade A, and why
roster-run 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 9d 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 — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roster Run
You are the entry point of the roster pipeline. Your only job is to detect context and route to the appropriate skill — not to do the work yourself.
Three modes — pick before anything else
Read the task first. Classify it. Then route.
| Mode | When | Pipeline |
|---|---|---|
| Express | No spec/KB impact — typo, rename, formatting, config tweak, doc fix, pure refactor with no behaviour change | implement → review → ship |
| Fast | Quick task with potential spec/KB impact — bug fix, small behaviour change, adding a missing case, performance fix | implement → review → qa → (update KB/specs/friction log) → ship |
| Full | New capability, API change, design decisions, multi-file refactor with trade-offs, anything the user asks to spec first | question → research → intake → spec → plan → implement → review → qa → ship |
When in doubt between Express and Fast, pick Fast. When in doubt between Fast and Full, ask one question: "Does this require deciding what to build, or just how?" — if only how, stay Fast.
Express and Fast are not shortcuts on quality — review is always mandatory. What changes is the upfront discovery and downstream documentation overhead.
Express signals (all must apply)
- No new behaviour — same inputs produce same outputs after the change
- No spec, KB, or friction log update needed
- Change is self-evident from the task description alone
- Dependency bumps → Fast minimum (they may introduce behaviour changes, break tests, or require KB updates)
Fast signals (any one is enough)
- Fix to existing behaviour (bug, edge case, missing guard)
- Small addition that doesn't change the overall design
- User says "quickly", "fast", "small", "just fix"
- Task ≤ 20 words and unambiguous but has some spec/KB impact
Full signals (any one is enough)
- New capability that doesn't exist yet
- API or interface change affecting callers
- Multiple design trade-offs to resolve
- User says "feature", "spec", "design", "plan", "implement from scratch", or asks a question about what to build
What ships with it
1 file 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.
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.
- 9d ago First seen · 459 lines · 17 tokens per session scan A dc86e04cbfa9
roster-run is a skill published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 6,664 once invoked, about $0.0001 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…