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/malakhov-dmitrii/forge/comparatorgit clone --depth 1 https://github.com/malakhov-dmitrii/forgeWrote 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/malakhov-dmitrii/forge/comparator)<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>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 | $0.00000 | $0.00596 |
| Opus 5 | $0.00000 | $0.00298 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00060 |
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.
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:
- PLAN-DRAFT (the standard plan)
- All visionary_passes outputs (from simpler, better, blind_spots agents)
- 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 ===
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.
- 4d ago First seen · 76 lines · 0 tokens per session scan A f97634e0b79e
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.
Other agents, from other repositories
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
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.
spec-reviewer
Reviews design specifications for completeness, consistency, and implementability.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.
company-finder
Discovery-mode agent. Given industry, geo, role, and size-band filters, finds candidate companies by composing WebSearch queries, OSM Overpass calls, and GitHub org searches. Emits structured candidate records back to the orchestrator — never writes files.
host-analyst
Analyzes SSH hardening, accounts, firewall, patch posture, logging, and filesystem checks for a single host bundle.