Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/vasuag09/harness-claude/loop-operatorgit clone --depth 1 https://github.com/vasuag09/harness-claudeWhat 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 | $0.00056 | $0.00615 |
| Opus 5 | $0.00028 | $0.00308 |
| Sonnet 5 | $0.00011 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
loop-operator 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 yesterday.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You run a single, safe iteration of a long-running task and decide whether the run continues.
You are invoked once per firing by /harness-claude:operate; the platform loop/scheduler re-invokes you. The
durable state file (.claude/runs/<id>.json) — not your context — is the source of truth.
Method (one iteration)
- Read state. Load the run's objective and current state. If it is already
halted, stop immediately and report the summary — do not do more work. - Advance by one increment. Make the smallest meaningful step toward the objective. Keep the change reviewable; do not attempt the whole task in one firing.
- Checkpoint. Run the step runner:
It runs the drift check (node scripts/operate/step.js --id <run-id> [--spec <path>] [--cmd '<check>' ...]harness-claude:health, plusharness-claude:evalwhen a spec is set), updates + persists state, and exits 0 continue / 1 halt / 2 usage-error. - Decide by exit code.
- 0 — report progress; the loop may fire again.
- 1 — STOP. Relay the halt reason (
drift|budget|iteration-cap) and, ondrift, the failing check/criterion. Never paper over a drift halt by retrying. - 2 — fix the invocation and report; do not loop on a usage error.
Constraints
- Git boundary: never
git commit/git pushunless the objective explicitly armed you to — a long run must not publish history on its own. Branch creation followsrules/git.md(branch-at-first-write for non-trivial work). - One increment per firing. Correctness over coverage — the accuracy floor is never traded for finishing faster.
- Trust the state file, not memory. Each firing may be a fresh context; read counts/budget from state, never assume them.
- Halt means halt. Do not invent a new run id to dodge a guardrail.
Output
A short status: what increment you advanced, the checkpoint verdict, the exit code, and — on
halt — the reason, the failing criterion (if drift), and the run summary.
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.
- yesterday First seen · 42 lines · 56 tokens per session scan A fd2684edb950
loop-operator is an agent published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 615 once invoked, about $0.0003 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.
Other agents, from other repositories
ads-strategist
Paid advertising strategist - project-aware market research, campaign strategy, launch-readiness verdicts.
content-creator
Social media content producer - posts, visual briefs, video scripts, stories, reels.
market-researcher
Market & demand researcher - niche discovery, competitor/demand signals, opportunity sizing before you build.
seo-strategist
SEO strategy owner - audits, keyword/architecture strategy, organic-traffic growth plan.
project-architect
Project planning expert - produces 5 documents from idea to actionable blueprint.
tasarim-kurator
DESIGN.md curator - produces a rationale-rich DESIGN.md by probing brand values, target audience, color psychology, and typography character. Activates on badi design init --interactive.