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.
curl -O https://raw.githubusercontent.com/os-factory/har/main/.claude/skills/factory-line/SKILL.mdgit clone --depth 1 https://github.com/os-factory/harWrote 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/os-factory/har/factory-line)<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>- NVIDIA SkillSpector pass
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.
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 | $0.00101 | $0.01880 |
| Opus 5 | $0.00051 | $0.00940 |
| Sonnet 5 | $0.00020 | $0.00376 |
| Haiku 4.5 | $0.00010 | $0.00188 |
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.
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):
- Line — run
har line status(or MCPhar_line_status). One installed line: use it. Several: ask which. None installed: stop and offerhar line create <id>(scaffold) orhar line add <spec>(install a published bundle, e.g.github:os-factory/har-line). Authoring templates live inexamples/:v1-milestone.line.json,new-plugin.line.json,docs-milestone.line.json— seeds, not installed programs. - Station id — default: the first station whose bound work is not all
closed / whose gate has not passed. Must be an id in
stations[]. - Slot budget — how many concurrent HAR slots you may occupy (check
har env statusfirst). 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.
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.
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.
- 8d ago First seen · 155 lines · 101 tokens per session scan A 64a6c21e7c55
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.
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…
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…
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…
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…
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…
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…