long-running-harness

long-running-harness is a skill for Claude Code from dapi/claude-code-marketplace. It costs 474 tokens per session (4,411 once invoked), scanned B, original, MIT.

A workflow for managing software projects that continue across many AI-agent sessions. It uses separate setup and implementation work, plus saved project records that carry context forward.

In plain words
What is it for?
Use it to start, continue, and manage long-running development projects that need structured handoffs between sessions.
Why use it?
It prevents lost context, rushed one-session work, undocumented progress, and premature claims that a project is finished.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is │ 6. ☐ ./scripts/init.sh → setup environment + smoke test │.

Part of the long-running-harness plugin — 1 skill shipped together

Good fit Use it to start, continue, and manage long-running development projects that need…

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace
agentmods
npx agentmods add skills/dapi/claude-code-marketplace/long-running-harness

Made for: Claude Code.

Or install long-running-harness, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for long-running-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/dapi/claude-code-marketplace/long-running-harness.svg)](https://agentmods.dev/skills/dapi/claude-code-marketplace/long-running-harness)
Your own site
<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>
Per session 474 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,411 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 010a23e6cc91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 2 executable files (examples/init-nodejs.sh, examples/init-rails.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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
long-running-harness/skills/long-running-harness/SKILL.md · 505 lines

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  │                  │      │
│  └──────────────────┘                └──────────────────┘      │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 505 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 505 lines · 474 tokens per session scan B 010a23e6cc91

Subscribe to this mod's changes

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.