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 yale-som-hpc/claude-code-marketplace --skill task-runnergit clone --depth 1 https://github.com/yale-som-hpc/claude-code-marketplaceWrote 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/yale-som-hpc/claude-code-marketplace/task-runner)<a href="https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/task-runner"><img src="https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/task-runner/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/yale-som-hpc/claude-code-marketplace/task-runner"><img src="https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/task-runner.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 | $0.00069 | $0.01101 |
| Opus 5 | $0.00034 | $0.00550 |
| Sonnet 5 | $0.00014 | $0.00220 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
task-runner 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Runner
Rule: capture a project's commands as named, rerunnable recipes in one file, so a future you — and the agent — can rerun any analysis step without re-deriving the incantation. This is about reproducibility, not convenience.
A research pipeline is a sequence of steps (prepare → estimate → tables). If those commands live only in shell history or someone's head, the work isn't reproducible and the agent can't reliably rerun it. Put them in one discoverable file with named recipes; the agent will read that file and reuse the commands instead of guessing.
Pick a tool — what's installed on the cluster matters
- Shell script (
run.sh) — zero dependencies, always present. Best for a short linear pipeline; acase "$1" in ... esacdispatch gives you named steps. - Makefile —
makeis installed on the cluster by default. Good when steps have dependencies or you want skip-if-already-built behavior. Mind the tab indentation and declare.PHONYtargets. - justfile — the nicest ergonomics (
just --list, parameters, dotenv), butjustis NOT installed on the cluster and is not a module — you must install it yourself (cargo install just, or drop a static binary in~/.local/bin; see installing software). Use it only if you'll install it.
Default for someone new: a Makefile or run.sh — they work the moment you log in. Reach for just once you've installed it and want the ergonomics.
Cluster integration
- Keep Slurm resources in
slurm/*.sbatch, not in the runner. The runner only submits (sbatch slurm/run.sbatch); never hide--mem/--cpus-per-task/--timewhere a reader won't see them. - Read the allocation, don't hardcode it:
${SLURM_CPUS_PER_TASK:-1}in shell,env_var_or_default("SLURM_CPUS_PER_TASK", "1")in just,$(or $(SLURM_CPUS_PER_TASK),1)in make. - Recipes should call the project env / lockfiles (
.venv/bin/python,Rscript), not global state.
Shell script (always available)
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 · 100 lines · 69 tokens per session scan A a1053a1d9521
task-runner is a skill published in the GitHub repository yale-som-hpc/claude-code-marketplace (5 stars, last pushed 2mo ago), licensed Unlicense. It adds 69 tokens to every session and 1,101 once invoked, about $0.0003 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…