har: Skill for Claude Code

.claude/skills/factory-line/SKILL.md

factory-line is a skill for Claude Code from os-factory/har. It costs 101 tokens per session (1,880 once invoked), scanned A, original, Apache-2.0.

A coordinator for running one station of a predefined multi-station program, using isolated work areas and validation checks before human review.

In plain words
What is it for?
Use it to find an installed line, plan its work, run the station, perform quick or full checks, and prepare the result for review.
Why use it?
It organizes parallel work and keeps each station connected to the program's declared steps, instead of relying on loose files or an ad-hoc runner.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is os-factory/har's own configuration. It tells Claude Code how to work on har itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything har configures →

Reuse

Borrowing it

Nothing to install: this file belongs to os-factory/har. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/os-factory/har/main/.claude/skills/factory-line/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/os-factory/har

Made for: Claude Code.

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 factory-line

README.md
[![agentmods](https://agentmods.dev/badge/skills/os-factory/har/factory-line.svg)](https://agentmods.dev/skills/os-factory/har/factory-line)
Your own site
<a href="https://agentmods.dev/skills/os-factory/har/factory-line"><img src="https://agentmods.dev/badge/skills/os-factory/har/factory-line.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,880 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
SkillSpector: 1 finding, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • low Excessive Agency · line 3
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
How audits are shown
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 $0.00101 $0.01880
Opus 5 $0.00051 $0.00940
Sonnet 5 $0.00020 $0.00376
Haiku 4.5 $0.00010 $0.00188

Measured 8d ago against content hash 64a6c21e7c55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

factory-line 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 8d 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.

.claude/skills/factory-line/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Factory line

Execute one station of a declared program end-to-end:

sync → wave plan → parallel slots → cumulative gate → human handoff.

The program lives in an installed line bundle, not in this skill. Find it with har line status: installed lines live at .har/lines/<id>/line.json and are recorded in .har/lines.json. This skill is the orchestrator; station-specific how-to lives in other skills the program lists.

*.line.json files under examples/ are authoring templates, not the installed program. Read one to learn the shape or to seed a new bundle (har line create <id>); do not run a station off a loose file when a line is installed.

HAR already has the primitives. Work units, isolated slots, stages with quick/full tiers, validation records, the commit gate, plugins, Mission Control. A line is composition plus a manifest. Do not invent a second runner, a stack-specific MCP tool, or GitHub-shaped stations.

Contract: LINE.schema.md. Instances: examples/.

Inputs

Resolve these before doing anything (ask only if not inferable):

  1. Line — run har line status (or MCP har_line_status). One installed line: use it. Several: ask which. None installed: stop and offer har line create <id> (scaffold) or har line add <spec> (install a published bundle, e.g. github:os-factory/har-line). Authoring templates live in examples/: v1-milestone.line.json, new-plugin.line.json, docs-milestone.line.json — seeds, not installed programs.
  2. Station id — default: the first station whose bound work is not all closed / whose gate has not passed. Must be an id in stations[].
  3. Slot budget — how many concurrent HAR slots you may occupy (check har env status first). One slot per concurrent agent. Occupied slots always block — that is a feature.

If the user says "run the next v1 milestone", load examples/v1-milestone.line.json and prefer the existing v1-milestone playbook for station tactics (it remains the executable instance until 1.0 ships). This skill still owns the loop.

Read the full file on GitHub · 155 lines

Files

What ships with it

4 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. 8d ago First seen · 155 lines · 101 tokens per session scan A 64a6c21e7c55

Subscribe to this mod's changes

factory-line is a skill published in the GitHub repository os-factory/har (85 stars, last pushed today), licensed Apache-2.0. It adds 101 tokens to every session and 1,880 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 2026-08-30.

Related

Other skills, from other repositories

ctx

Codebase intelligence and evidence-driven governance with the indexed ctx CLI. Use when exploring an unfamiliar repository, locating symbols or callers, checking for existing implementations, estimating change impact, enforcing architecture rules, scoring a branch, finding hotspots or duplication, or analyzing…

agentis-tools/ctx · 60 tokens

ctx

Codebase intelligence and evidence-driven governance with the indexed ctx CLI. Use when exploring an unfamiliar repository, locating symbols or callers, checking for existing implementations, estimating change impact, enforcing architecture rules, scoring a branch, finding hotspots or duplication, or analyzing…

agentis-tools/ctx · 60 tokens

editing-cordis-compositions

Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted…

singula-ai/alego · 69 tokens

cordis-plugin-development

Create, modify, debug, or extend dynamic Cordis Plugins, including Host Services and Events, Client Slot and theme UI, Package-private Client-to-Host calls, dynamic Tools, version updates, approval failures, and runtime diagnostics. Use this Skill to route a user request to the correct platform and Inspect Provider…

singula-ai/alego · 80 tokens

last30Days

Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…

chaitanyagiri/munder-difflin · 83 tokens

thisWeek

Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…

chaitanyagiri/munder-difflin · 77 tokens