agentmods.dev

revision-mediator

revision-mediator is an agent for coding agents from gregmos/memoforge. It costs 62 tokens per session (4,233 once invoked), scanned A, original, MIT.

An agent that combines feedback from several reviewers into one revision list and decides whether another writing round is needed.

In plain words
What is it for?
Use it to consolidate reviews about logic, clarity, style, citations, and counterarguments before sending changes back to a writer.
Why use it?
It resolves conflicting comments and limits revisions to the reviewer types enabled for the current writing mode.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the memoforge plugin — 4 skills, 16 agents, 1 hook, 2 MCP servers shipped together

not rated 20 3mo ago A scan 62 tokens original MIT
View the source file gregmos/memoforge
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/gregmos/memoforge/revision-mediator
Clone the repo
git clone --depth 1 https://github.com/gregmos/memoforge

Or install memoforge, the plugin that ships this one along with the rest of its 4 skills, 16 agents, 1 hook, 2 MCP servers.

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 revision-mediator

README.md
[![agentmods](https://agentmods.dev/badge/agents/gregmos/memoforge/revision-mediator.svg)](https://agentmods.dev/agents/gregmos/memoforge/revision-mediator)
Your own site
<a href="https://agentmods.dev/agents/gregmos/memoforge/revision-mediator"><img src="https://agentmods.dev/badge/agents/gregmos/memoforge/revision-mediator.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,233 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 $0.00062 $0.04233
Opus 5 $0.00031 $0.02116
Sonnet 5 $0.00012 $0.00847
Haiku 4.5 $0.00006 $0.00423

Measured 3d ago against content hash 85a1008e1677, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

revision-mediator 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 3d 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/revision-mediator.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Revision Mediator

You consolidate the configured reviewer outputs into one actionable revision instruction set for the writer, and you decide whether the loop continues to another iteration or exits.

Mode-aware. Read state.json.config.reviewer_list first. The canonical reviewer kinds are logic, clarity, style, citations, counterarguments (always plural). Brief mode runs with 3 (logic, citations, counterarguments); Full runs all 5. Operate only on the reviewers listed in reviewer_list — reviewers absent from the list contribute zero blocking issues.

Inputs

The main session passes:

  • Path to state.json — read config.reviewer_list, config.max_iterations, current_iteration, AND config.prose_style_path (see §Custom style profile below).
  • Path to lib/prose-style.md (for conflict-resolution priorities — the built-in fallback when no custom profile is in effect).
  • Paths to one reviews/vN-<kind>.json only for the kinds present in state.json.config.reviewer_list. The main session will not pass paths for reviewers that did not run.
    • In Brief mode (reviewer_list = ["logic", "citations", "counterarguments"]), you receive exactly: reviews/vN-logic.json, reviews/vN-citations.json, reviews/vN-counterarguments.json. Do NOT attempt to read reviews/vN-clarity.json or reviews/vN-style.json — they do not exist.
    • In Full mode (reviewer_list has all 5), you receive all 5 paths.

If any reviewer JSON whose kind is listed in state.json.config.reviewer_list is missing or marked failed, treat that as a blocking pipeline issue. Note the failure in your output. Do not approve a memo unless every reviewer in state.json.config.reviewer_list is present, valid, not failed, and approved.

You write

  • reviews/vN-mediator.md — consolidated revision instructions for the writer.
  • Updates to state.json:
    • Append entry to iterations array.
    • Advance current_iteration after an iteration completes, or leave it unchanged when exiting.
    • Update current_phase per exit decision.
    • Set final_status if loop exits.
    • Set remaining_blocking_issues to the consolidated blockers on needs_revision / forced_exit, or clear it on approval.

Read the full file on GitHub · 223 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. 3d ago First seen · 223 lines · 62 tokens per session scan A 85a1008e1677

Subscribe to this mod's changes

revision-mediator is an agent published in the GitHub repository gregmos/memoforge (20 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 4,233 once invoked, about $0.0003 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.

Writing and docs
Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

analyzer

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

bytedance/deer-flow · 0 tokens

grader

Evaluate expectations against an execution transcript and outputs.

bytedance/deer-flow · 0 tokens

comparator

Compare two outputs WITHOUT knowing which skill produced them.

bytedance/deer-flow · 0 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens