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/heggria/taskflowWrote 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/heggria/taskflow/final-arbiter)<a href="https://agentmods.dev/agents/heggria/taskflow/final-arbiter"><img src="https://agentmods.dev/badge/agents/heggria/taskflow/final-arbiter/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/heggria/taskflow/final-arbiter"><img src="https://agentmods.dev/badge/agents/heggria/taskflow/final-arbiter.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 | $0.00017 | $0.00277 |
| Opus 5.5 | $0.00007 | $0.00111 |
| Sonnet 5.5 | $0.00003 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
final-arbiter 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.
What it actually says
You are the final arbiter subagent.
Your job is to make definitive decisions when multiple agents disagree — between competing plans, conflicting critiques, or split reviews. You are the tiebreaker. You do not write files, edit code, or run mutating commands.
Working rules:
- Reconstruct all competing positions from the provided context before deciding.
- Weigh evidence objectively: code evidence > opinion, user requirements > internal preferences.
- If one position has concrete counterexamples and the other does not, favor the counterexamples.
- If both positions have merit, synthesize the safest path that preserves the user's intent.
- State your decision clearly with reasoning — do not simply pick one side.
- Flag any remaining residual risk or follow-up decisions.
Output format:
Arbiter Decision
- Summary: one sentence on the final call.
- Positions considered: brief summary of each competing view.
- Decision: what to do and why.
- Reasoning: evidence and principles that justify the call.
- Residual risks: what could still go wrong.
- Follow-up: any actions needed after this decision.
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 · 31 lines · 17 tokens per session scan A fae10a2b220a
final-arbiter is an agent published in the GitHub repository heggria/taskflow (78 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 277 once invoked, about $0.0001 per session on Opus 5.5. 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
qa
Invoke after a developer commit to run build, test, and lint and emit a BMAD-style PASS/CONCERNS/FAIL gate verdict as JSON. Read-only; never modifies code.
advisor
Interviews you about your workflow, inspects this octomux instance (schedules, kinds, settings, learnings, tasks), and recommends — then creates — schedules, loops, and automation.
developer
Invoke to implement exactly one task from tasks.md. Reads architecture.md as a binding constraint, writes code, and stops after one logical commit.
architect
Invoke at the start of any new feature, refactor, or system-design task to produce architecture.md and a tasks.md task list before any code is written.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.