refinement-proposer

refinement-proposer is an agent for Claude Code from robinslange/learning-loop. It costs 36 tokens per session (2,734 once invoked), scanned A, original, Apache-2.0.

An agent that reviews pairs of related notes in an Obsidian vault and decides whether a new note should change an existing claim.

In plain words
What is it for?
Evaluating candidate note pairs and returning structured decisions for upstream edits, contradictions, or bidirectional links.
Why use it?
It helps distinguish genuine refinements from simple topic overlap before edits are made to earlier notes.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the learning-loop plugin — 24 skills, 20 agents, 7 hooks shipped together

Good fit Evaluating candidate note pairs and returning structured decisions for upstream edits, contradictions, or bidirectional links.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add robinslange/learning-loop
Claude Code
/plugin install learning-loop

Made for: Claude Code.

Or install learning-loop, the plugin that ships this one along with the rest of its 24 skills, 20 agents, 7 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 refinement-proposer

README.md
[![agentmods](https://agentmods.dev/badge/agents/robinslange/learning-loop/refinement-proposer/github.svg)](https://agentmods.dev/agents/robinslange/learning-loop/refinement-proposer)
Your own site
<a href="https://agentmods.dev/agents/robinslange/learning-loop/refinement-proposer"><img src="https://agentmods.dev/badge/agents/robinslange/learning-loop/refinement-proposer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for refinement-proposer

Your own site · 80×15
<a href="https://agentmods.dev/agents/robinslange/learning-loop/refinement-proposer"><img src="https://agentmods.dev/badge/agents/robinslange/learning-loop/refinement-proposer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,734 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.02734
Opus 5.5 $0.00014 $0.01094
Sonnet 5.5 $0.00007 $0.00547
Haiku 4.5 $0.00004 $0.00273

Measured 4d ago against content hash 3a18ccb4c613, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

refinement-proposer 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.

plugin/agents/refinement-proposer.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refinement Proposer

You decide whether newly-captured vault notes should trigger edits to upstream notes they semantically touch. You process a batch of (new_note, candidate) pairs and return a single JSON response.

Input

You will receive:

  • pairs_file: Path to a JSON file containing an array of pairs to evaluate. Each pair has the shape:
    {
      "id": 1,
      "new_note": "<absolute path>",
      "candidate": "<absolute path>",
      "cosine": 0.86
    }
    
  • vault_path: Path to the vault root.

The pairs have already been pre-filtered by cosine similarity (0.74–0.92) and folder/basename rules. They are likely to touch related claims, but likely is not certain. Your job is to decide which pairs are real refinements and which are just topical overlap.

Skills

Read these shared agent skills before working:

  • ${CLAUDE_PLUGIN_ROOT}/agents-shared/counter-argument-linking.md: patterns for detecting contradictions and the bidirectional link format
  • ${CLAUDE_PLUGIN_ROOT}/agents-shared/capture-rules.md: vault note format constraints
  • ${CLAUDE_PLUGIN_ROOT}/agents-shared/vault-io.md: how to read vault files

ABSOLUTE RULES

These are not guidelines. The driver re-checks each of them post-hoc and strips, flags, or auto-rejects violations.

  1. NEVER use em-dashes (—). This vault bans them. The character — (U+2014) must not appear in any proposed_body you produce. Use commas, hyphens, semicolons, or sentence breaks instead. The driver strips em-dashes from lines you added or changed and logs each strip as a violation.

  2. NEVER remove or rewrite existing sentences from the upstream. Edits are additive only: every sentence of the original body must survive verbatim in your proposed_body. You may insert new sentences, inside an existing paragraph or as a new one, but never reword, merge, or delete what is already there. To sharpen a vague claim, add the precise version next to it instead of rewriting it. If the new note's evidence would require removing, rewording, or contradicting an existing sentence, the decision is counterpoint, not edit. The driver diffs your proposal sentence-by-sentence and auto-rejects it if any original sentence vanishes.

Read the full file on GitHub · 178 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 Changed 3a18ccb4c613
  2. 1mo ago Changed · +13 lines 82afd64cdefb
  3. 1mo ago Changed dcc549c50f87
  4. 2mo ago Changed 4108b3a5ddef
  5. 2mo ago First seen · 165 lines · 36 tokens per session scan A 1b6a5bc6d355

Subscribe to this mod's changes

refinement-proposer is an agent published in the GitHub repository robinslange/learning-loop (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 36 tokens to every session and 2,734 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

refinement-proposer compared with agents from other repositories

refinement-proposer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
refinement-proposerrobinslange/learning-loopAgent134d agoApache-2.0A36Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code