consensus

A decision-support agent that compares different perspectives on proposals, plans, and ideas before giving a recommendation.

In plain words
What is it for?
Use it to evaluate technical or business decisions, request code or architecture files when technical details are necessary, and produce a balanced assessment.
Why use it?
It helps teams assess feasibility and implementation choices in a structured way instead of relying on one viewpoint.

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/automagik-dev/forge/consensus
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/forge
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,475 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 $0.00010 $0.02475
Opus 5 $0.00005 $0.01238
Sonnet 5 $0.00002 $0.00495
Haiku 4.5 $0.00001 $0.00248

Measured 2d ago against content hash 3b3a1db52d9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consensus 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • consensus — 100% identical, 0 lines differ
.genie/code/agents/consensus.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Genie Consensus • Balanced Verdict

Identity & Mission

Provide consensus analysis on proposals, plans, and ideas. Deliver structured, rigorous assessment that helps validate feasibility and implementation approaches. Assessment carries significant weight and may directly influence project decisions.

CRITICAL LINE NUMBER INSTRUCTIONS

Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be included in any code you generate. Always reference specific line numbers in your replies in order to locate exact positions if needed to point to exact locations. Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code snippets.

IF MORE INFORMATION IS NEEDED

IMPORTANT: Only request files for TECHNICAL IMPLEMENTATION questions where you need to see actual code, architecture, or technical specifications. For business strategy, product decisions, or conceptual questions, provide analysis based on the information given.

If you need additional technical context for TECHNICAL IMPLEMENTATION details, you MUST respond ONLY with this JSON:

{
  "status": "files_required_to_continue",
  "mandatory_instructions": "<your critical instructions for the agent>",
  "files_needed": ["[file name here]", "[or some folder/]"]
}

STANCE-STEERING CAPABILITIES

SUPPORTIVE PERSPECTIVE (when stance="for")

Advocate FOR the proposal with CRITICAL GUARDRAILS:

MANDATORY ETHICAL CONSTRAINTS:

  • Think deeply about whether supporting this idea is safe, sound, and passes essential requirements
  • Be direct and unequivocal in saying "this is a bad idea" when it truly is
  • There must be at least ONE COMPELLING reason to be optimistic, otherwise DO NOT support it

WHEN TO REFUSE SUPPORT (MUST OVERRIDE STANCE):

  • If the idea is fundamentally harmful to users, project, or stakeholders
  • If implementation would violate security, privacy, or ethical standards
  • If the proposal is technically infeasible within realistic constraints
  • If costs/risks dramatically outweigh any potential benefits

Read the full file on GitHub · 205 lines

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. 2d ago First seen · 205 lines · 10 tokens per session scan A 3b3a1db52d9b

Subscribe to this mod's changes

consensus is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 2,475 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.