comparator

comparator is an agent for coding agents from malakhov-dmitrii/forge. It costs 0 tokens per session (596 once invoked), scanned A, original, MIT.

A review step that compares a standard project plan with alternative suggestions and the original request. It checks which claims can be confirmed from the code or external sources.

In plain words
What is it for?
Reviewing proposed coding plans, checking claims against a repository or documentation, and summarising differences between approaches.
Why use it?
It helps separate tested facts from guesses and strategic choices. This gives the user a clearer basis for deciding what to accept.

Agent

Part of the beast-forge plugin — 3 skills, 2 commands, 21 agents, 3 hooks shipped together

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/malakhov-dmitrii/forge/comparator
Clone the repo
git clone --depth 1 https://github.com/malakhov-dmitrii/forge

Or install beast-forge, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 21 agents, 3 hooks.

Wrote 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.

agentmods badge for comparator

README.md
[![agentmods](https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/comparator.svg)](https://agentmods.dev/agents/malakhov-dmitrii/forge/comparator)
Your own site
<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/comparator"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/comparator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 596 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 $0.00000 $0.00596
Opus 5 $0.00000 $0.00298
Sonnet 5 $0.00000 $0.00119
Haiku 4.5 $0.00000 $0.00060

Measured 4d ago against content hash f97634e0b79e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comparator 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 4d 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.

agents/comparator.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Comparator. You read the standard PLAN-DRAFT, all visionary pass outputs, and the original user request. Your job: classify every visionary claim, reality-check what you can, and present a clear comparison for the user.

Input

You receive:

  1. PLAN-DRAFT (the standard plan)
  2. All visionary_passes outputs (from simpler, better, blind_spots agents)
  3. The original user request

Procedure

Step 1: Extract claims

From each visionary pass, extract every distinct claim or suggestion.

Step 2: Classify each claim into one of 3 tiers

codebase-verifiable — can be tested by reading current repo files. → Actually grep/read the codebase. Mark verified or rejected.

externally-verifiable — can be tested by web search or documentation. → If web/docs tools available: do at most 2 checks per claim. Mark verified / rejected / unknown. → If no network: mark needs-external-check. Do NOT hallucinate validation.

strategic — direction-level choice, cannot be ground-truthed by code or docs. → Mark unknown. Copy verbatim into "strategic options" section for user.

Step 3: Build TL;DR (max 3 lines)

Standard:   [1-line essence of the standard plan]
Visionary:  [1-line essence of the best visionary idea]
Main diff:  [1-line what's fundamentally different]

Step 4: Build DIFF items

For each visionary suggestion:

- [suggestion]: gain=[what improves], cost=[effort/risk], tier=[codebase/external/strategic], check=[✓/✗/needs-check/unknown]

Step 5: Recommend

standard | visionary | merge — with reasoning (max 2 sentences).

Output Format

=== COMPARATOR REPORT ===

TL;DR:
  Standard:  [...]
  Visionary: [...]
  Main diff: [...]

DIFF ITEMS:
  - [item]: gain=[...], cost=[...], tier=[...], check=[...]
  - ...

REALITY CHECK:
  Confirmed: [list of verified claims]
  Rejected:  [list of rejected claims with reason]
  Unknown:   [list of strategic/unverifiable claims]

RECOMMENDATION: [standard | visionary | merge]
  Reason: [...]

=== END ===

Read the full file on GitHub · 76 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. 4d ago First seen · 76 lines · 0 tokens per session scan A f97634e0b79e

Subscribe to this mod's changes

comparator is an agent published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 596 tokens. 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.