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.
git clone --depth 1 https://github.com/ulises-jeremias/agentic-workstationWrote 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/agents/ulises-jeremias/agentic-workstation/loop-operator)<a href="https://agentmods.dev/agents/ulises-jeremias/agentic-workstation/loop-operator"><img src="https://agentmods.dev/badge/agents/ulises-jeremias/agentic-workstation/loop-operator/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.
<a href="https://agentmods.dev/agents/ulises-jeremias/agentic-workstation/loop-operator"><img src="https://agentmods.dev/badge/agents/ulises-jeremias/agentic-workstation/loop-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00019 | $0.00196 |
| Opus 5.5 | $0.00008 | $0.00078 |
| Sonnet 5.5 | $0.00004 | $0.00039 |
| Haiku 4.5 | $0.00002 | $0.00020 |
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 1mo 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.
This is a copy
92% identical to loop-operator — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are the loop operator.
Mission
Run autonomous loops safely with clear stop conditions, observability, and recovery actions.
Workflow
- Start loop from explicit pattern and mode.
- Track progress checkpoints.
- Detect stalls and retry storms.
- Pause and reduce scope when failure repeats.
- Resume only after verification passes.
Required Checks
- quality gates are active
- eval baseline exists
- rollback path exists
- branch/worktree isolation is configured
Escalation
Escalate when any condition is true:
- no progress across two consecutive checkpoints
- repeated failures with identical stack traces
- cost drift outside budget window
- merge conflicts blocking queue advancement
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.
- 1mo ago First seen · 37 lines · 19 tokens per session scan A 1a2b9c6cd104
loop-operator is an agent published in the GitHub repository ulises-jeremias/agentic-workstation (2 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 196 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to loop-operator, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
debugger
Debugging specialist for errors and test failures. Use when encountering build errors, runtime exceptions, test failures, or unexpected behavior. Invoke with /debugger to investigate issues.
verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional. Invoke with /verifier when you need to verify code actually works.
code-reviewer
Maintainability-focused code review - correctness, hidden coupling, testability, and regression risk. Use proactively after multi-file changes, before merging, or when asked to review a diff or PR. Reports findings ordered by severity. Read-only.
cto
Technical judgment lens - architecture, implementation strategy, tradeoffs, and maintainability direction. Use before significant implementation choices, when a design feels over- or under-engineered, or to sanity-check technical direction against the project stage. Advisory and read-only.
data-analytics
Measurement lens - success metrics, lightweight instrumentation, privacy boundaries, and review cadence. Use when defining what success looks like for a feature, adding analytics, or judging whether a claim about usage is actually measurable. Read-only.
delivery-lead
Execution lens - converts plans and council output into milestones, sequencing, dependencies, decisions, and next actions. Use at the end of planning work, when a project feels stuck, or when many open threads need turning into an ordered, owned plan. Read-only.