operate

operate is a skill for Claude Code from vasuag09/harness-claude. It costs 98 tokens per session (1,355 once invoked), scanned A, original, MIT.

A supervisor for long-running or scheduled agent work. It records progress and checks each work cycle for drift, test or lint problems, too many failures, and time or iteration limits.

In plain words
What is it for?
Use it for autonomous coding runs or scheduled work that must checkpoint progress and stop when limits or problems are reached.
Why use it?
It prevents an unattended agent from running indefinitely, losing track of the goal, or quietly moving away from the repository's checks.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/operate/step.js --id <run-id> [--spec <path>] [--cmd '<check>' ...] \.

Part of the harness-claude plugin — 32 skills, 8 agents, 6 hooks, 3 MCP servers shipped together

Good fit Use it for autonomous coding runs or scheduled work that must checkpoint progress and stop when limits or problems are reached.

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/vasuag09/harness-claude
agentmods
npx agentmods add skills/vasuag09/harness-claude/operate

Made for: Claude Code.

Or install harness-claude, the plugin that ships this one along with the rest of its 32 skills, 8 agents, 6 hooks, 3 MCP servers.

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 operate

README.md
[![agentmods](https://agentmods.dev/badge/skills/vasuag09/harness-claude/operate/github.svg)](https://agentmods.dev/skills/vasuag09/harness-claude/operate)
Your own site
<a href="https://agentmods.dev/skills/vasuag09/harness-claude/operate"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/operate/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.

agentmods 80×15 button for operate

Your own site · 80×15
<a href="https://agentmods.dev/skills/vasuag09/harness-claude/operate"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/operate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,355 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.
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 $0.00098 $0.01355
Opus 5 $0.00049 $0.00678
Sonnet 5 $0.00020 $0.00271
Haiku 4.5 $0.00010 $0.00136

Measured 8d ago against content hash a9ca47362386, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

operate 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.

skills/operate/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/operate — run long, without silent drift

Goal: let an agent work unattended across many iterations (or wake on a schedule) and guarantee it halts rather than drifting — spinning on a dead end, burning budget, or quietly breaking the repo. This skill is the discipline layer: the platform /loop and /schedule are the engine; /harness-claude:operate adds guardrails, durable state, and a drift check wired to the harness's own eval skills.

Opt-in. No default-pipeline skill or hook starts a run. Running long is always explicit. Git boundary: a run never commits or pushes unless you explicitly arm it for that in the objective; branch creation for the run's non-trivial work follows rules/git.md (branch-at-first-write).

How it works

Each iteration the operator does one increment of work, then runs a checkpoint:

node scripts/operate/step.js --id <run-id> [--spec <path>] [--cmd '<check>' ...] \
     [--max-iterations <n>] [--max-fails <n>] [--budget-ms <n>]

step.js loads the durable run state (.claude/runs/<id>.json), runs the drift check — harness-claude:health (test/lint pulse) and, when --spec is set, harness-claude:eval (acceptance-criteria gate) — updates and persists state, evaluates the guardrails, and exits:

  • 0 = continue — schedule the next iteration.
  • 1 = halt — a guardrail tripped (drift | budget | iteration-cap); stop and report.
  • 2 = usage/error — fix the invocation (e.g. missing --id).

The state file is the sole source of truth across firings — each /loop firing may be a fresh context, so iteration count, budget spent, and the consecutive-fail counter persist there and resume automatically. Config flags are honored only when the run is first created; later firings ignore them so counts accumulate rather than reset.

Do this

  1. Frame the run. Name a one-line objective, a --max-iterations ceiling, a drift threshold --max-fails (default 2 — one failure can be transient, two is a trend), and a --budget-ms wall-clock cap. Point --spec at the spec the run must keep satisfying when one exists (that arms the harness-claude:eval half of the drift check).
  2. Pick a trigger.
    • Interval / autonomous: drive iterations with the platform /loop (fixed interval) or let the model self-pace; each firing advances the work one increment, then calls step.js.
    • Scheduled / cron: use the platform /schedule to wake on a cadence; each wake runs one checkpointed iteration.
  3. Supervise by exit code. Continue on 0; on 1, stop the loop, read the printed summary, and surface the halt reason and the failing criterion — never restart blindly past a drift halt. Delegate the per-iteration work to the harness-claude:loop-operator agent.
  4. Report on halt. Always end with the run summary: iterations run, budget spent, last verdict, halt reason. (step.js prints it; relay it.)

Read the full file on GitHub · 81 lines

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 · 81 lines · 98 tokens per session scan A a9ca47362386

Subscribe to this mod's changes

operate is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 1,355 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.

Related

Other skills, from other repositories

pr-triage

4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…

FlorianBruniaux/claude-code-plugins · 86 tokens

audit-agents-skills

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.

FlorianBruniaux/claude-code-plugins · 41 tokens

eval-agents

Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…

FlorianBruniaux/claude-code-plugins · 93 tokens

check-cache-bugs

Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.

FlorianBruniaux/claude-code-plugins · 38 tokens

issue-triage

3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.

FlorianBruniaux/claude-code-plugins · 81 tokens

git-ai-archaeology

Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.

FlorianBruniaux/claude-code-plugins · 47 tokens