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/dapi/claude-code-marketplacenpx agentmods add skills/dapi/claude-code-marketplace/long-running-harnessWrote 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/dapi/claude-code-marketplace/long-running-harness)<a href="https://agentmods.dev/skills/dapi/claude-code-marketplace/long-running-harness"><img src="https://agentmods.dev/badge/skills/dapi/claude-code-marketplace/long-running-harness.svg" alt="Measured on agentmods" 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 | $0.00474 | $0.04411 |
| Opus 5 | $0.00237 | $0.02205 |
| Sonnet 5 | $0.00095 | $0.00882 |
| Haiku 4.5 | $0.00047 | $0.00441 |
Grade B, and why
long-running-harness scanned grade B with 2 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 6d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
│ 4. ☐ cat .claude/progress.md → что было сделано │ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Для API: используй curl/httpie для smoke tests How it starts
The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Long-Running Agent Harness
Skill для управления долгосрочными проектами, которые требуют работы через множество сессий Claude. Основан на исследовании Anthropic.
** Источник**: Effective harnesses for long-running agents (Anthropic Engineering, Nov 2025)
Проблема, которую решает этот skill
AI-агенты работают в дискретных сессиях без памяти о предыдущей работе. Это приводит к:
- ❌ Попыткам сделать всё за раз (one-shotting)
- ❌ Преждевременному объявлению проекта завершённым
- ❌ Потере контекста между сессиями
- ❌ Багам и недокументированному прогрессу
Решение: Два типа агентов + структурированные артефакты для передачи контекста.
Архитектура оркестрации
┌─────────────────────────────────────────────────────────────────┐
│ ORCHESTRATION FLOW │
├─────────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────────────┐ FIRST RUN ONLY │
│ │ INITIALIZER │─────────────────────────────┐ │
│ │ AGENT │ │ │
│ │ │ Creates: │ │
│ │ (Claude + this │ • features.json │ │
│ │ skill in init │ • progress.md │ │
│ │ mode) │ • init.sh │ │
│ └──────────────────┘ • Initial git commit │ │
│ │ ▼ │
│ │ ┌─────────────────────────────────┐ │
│ │ │ PROJECT ARTIFACTS │ │
│ │ │ ┌─────────────────────────┐ │ │
│ │ │ │ .claude/ │ │ │
│ │ │ │ ├── features.json │ │ │
│ │ │ │ ├── progress.md │ │ │
│ │ │ │ └── architecture.md │ │ │
│ │ │ │ scripts/init.sh │ │ │
│ │ │ └─────────────────────────┘ │ │
│ │ └─────────────────────────────────┘ │
│ │ ▲ │ │
│ │ │ │ │
│ │ ┌───────────────┘ │ │
│ ▼ │ ▼ │
│ ┌──────────────────┐ ┌──────────────────┐ │
│ │ CODING AGENT │───────────────▶│ CODING AGENT │ │
│ │ Session 1 │ │ Session 2 │ ... │
│ │ │ Reads: │ │ │
│ │ (Claude + this │ • progress.md │ │ │
│ │ skill in │ • features.json │ │
│ │ continue mode) │ • git log │ │ │
│ │ │ │ │ │
│ │ Updates: │ Updates: │ │ │
│ │ • 1 feature │ • 1 feature │ │ │
│ │ • progress.md │ • progress.md │ │ │
│ │ • git commit │ • git commit │ │ │
│ └──────────────────┘ └──────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────┘
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.
- 6d ago First seen · 505 lines · 474 tokens per session scan B 010a23e6cc91
long-running-harness is a skill published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 6d ago), licensed MIT. It adds 474 tokens to every session and 4,411 once invoked, about $0.0024 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.