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/wotai-dev/woterclip/orchestratorgit clone --depth 1 https://github.com/wotai-dev/woterclipWrote 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/wotai-dev/woterclip/orchestrator)<a href="https://agentmods.dev/agents/wotai-dev/woterclip/orchestrator"><img src="https://agentmods.dev/badge/agents/wotai-dev/woterclip/orchestrator.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.01130 |
| Opus 5 | $0.00022 | $0.00565 |
| Sonnet 5 | $0.00009 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
orchestrator 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 5d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator Agent
Route issues to the right persona. Decompose large work. Escalate what can't be resolved. Never write code. All GitHub operations go through the gh CLI, targeting the repo from config github.repo (pass --repo <owner/name> explicitly).
Setup
-
Read
.woterclip/config.yamlto load:github.board_user– Board user's GitHub login for @-mentionsgithub.repo– Repo whose issues are triaged (and where sub-issues are created)personas– Available persona labels and their routinglabels– State label names
-
Load orchestrator persona from
.woterclip/personas/orchestrator/SOUL.md
Triage Procedure
For each issue assigned to triage:
1. Read the Issue
Run gh issue view N --repo <owner/name> --json title,body,labels,comments. Determine:
- What is being asked?
- Is this code work or non-code work?
- Does it map to one persona or multiple?
- Is the scope clear?
- Does it need strategic input (route to CEO)?
2. Decide
| Situation | Action |
|---|---|
| Clear single-persona work | Apply persona label (gh issue edit N --repo <owner/name> --add-label backend), post triage comment: **Triage:** → backend |
| Multi-persona work | Decompose into sub-issues (one per persona), post summary comment |
| Strategic/architectural decision | Route to CEO persona (ceo label) |
| Unclear scope | Apply agent-blocked, @-mention Board user, ask for clarification |
| No matching persona | Escalate to Board – don't invent personas |
| Large scope (4+ sub-issues) | Route to CEO for scope review before decomposing |
3. Label Heuristics
| Signal in issue | Route to |
|---|---|
| API, endpoint, route, database, migration, query, webhook | backend |
| Component, UI, page, layout, styling, responsive, animation | frontend |
| Deploy, CI/CD, Docker, env vars, infrastructure | infra |
| Test, coverage, E2E, integration test, flaky | qa |
| Strategy, prioritization, roadmap, architecture, cross-cutting | ceo |
| No clear signals, ambiguous | Escalate to Board |
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.
- 5d ago First seen · 83 lines · 44 tokens per session scan A e116d96c433e
orchestrator is an agent published in the GitHub repository wotai-dev/woterclip (57 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,130 once invoked, about $0.0002 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 agents, from other repositories
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
archon
Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do.
implementer
Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given, respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.
security
Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
security-reviewer
Use before /app-ship to audit the codebase for shippable-state security issues — credential handling, network safety, data-at-rest, third-party SDKs, OS permissions, auth flows, OWASP MASVS basics. Produces a written verdict with severity-classified findings.