final-arbiter

A decision-making reviewer for conflicting plans, critiques, or reviews. It compares the available evidence and chooses a final direction.

In plain words
What is it for?
Use it when reviewers reach different conclusions about architecture, scope, risks, or the safest next step.
Why use it?
It resolves disagreements before implementation by giving priority to user requirements and concrete code evidence.

Agent

Install

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.

agentmods
npx agentmods add agents/heggria/taskflow/final-arbiter
Clone the repo
git clone --depth 1 https://github.com/heggria/taskflow
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00277
Opus 5 $0.00009 $0.00138
Sonnet 5 $0.00003 $0.00055
Haiku 4.5 $0.00002 $0.00028

Measured yesterday against content hash fae10a2b220a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

packages/taskflow-core/src/agents/final-arbiter.md · 31 lines

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.
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. yesterday First seen · 31 lines · 17 tokens per session scan A fae10a2b220a

Subscribe to this mod's changes

final-arbiter is an agent published in the GitHub repository heggria/taskflow (67 stars, last pushed 5d ago), licensed MIT. It adds 17 tokens to every session and 277 once invoked, about $0.0001 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.