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 pbc-os/smb-starter-kit --skill long-running-agentgit clone --depth 1 https://github.com/pbc-os/smb-starter-kitWrote 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/pbc-os/smb-starter-kit/long-running-agent)<a href="https://agentmods.dev/skills/pbc-os/smb-starter-kit/long-running-agent"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/long-running-agent/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/pbc-os/smb-starter-kit/long-running-agent"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/long-running-agent.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 | $0.00093 | $0.02209 |
| Opus 5 | $0.00046 | $0.01104 |
| Sonnet 5 | $0.00019 | $0.00442 |
| Haiku 4.5 | $0.00009 | $0.00221 |
Grade A, and why
long-running-agent 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 10d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Long-Running Agent Setup
Turn a spec into a working long-running agent — phases, tasks, verification, and the operating prompt — in one shot.
This skill converts planning documents and specs into the file structure a long-running Claude agent uses to execute multi-session work: a claude-task.json task tracker, a claude-prompt.md operating manual, and a preserved SPEC.md. Before generating files it asks how autonomous the agent should be, so the prompt and task structure match.
Triggers
- "set up a long-running agent for..."
- "convert this spec into phases"
- "I have a spec, build out the agent task structure"
- "make a claude-task.json for this plan"
- "break this plan into phases with verification"
- "spin up an autonomous build of..."
Source of Truth
Before doing anything, fetch and read this blog post for the core patterns:
https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents
The blog defines the effective patterns for long-running coding agents. Apply them directly. Key takeaways: phase-based work with verification checkpoints, granular task enumeration, JSON task tracking, git checkpointing per task, never weaken/remove tests to make a phase pass.
Core Workflow
1. Gather Inputs
Request from the user:
- Spec / planning doc — the document to convert (required). Will be preserved as
SPEC.md. - Project name — short identifier; used in headings and the JSON
projectfield. - Output location — where to create files (default: a new directory at the user's choice).
If the user has the spec inline in chat or pointed at a file path, read it. If multiple files together form the spec (e.g., a SPEC.md + a data_model.md + a workflows.md), read all of them.
2. Read the Blog
Fetch the Anthropic blog post above. The patterns to apply:
- Phase-based work with verification checkpoints — verification is required before advance, in either operating mode
- Explicit feature/task enumeration — granular, single-task focus
- Task file as progress tracker — JSON, not markdown (the model is less likely to corrupt it)
- Git checkpointing after each task —
task-XXX: brief description - Strong constraints — never delete or weaken tests/verification
What ships with it
3 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.
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.
- 10d ago First seen · 196 lines · 93 tokens per session scan A a4efd28f659f
long-running-agent is a skill published in the GitHub repository pbc-os/smb-starter-kit (10 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 2,209 once invoked, about $0.0005 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…