long-term-memory: Agent for Claude Code

.claude/agents/reward-tuner.md

reward-tuner is an agent for Claude Code from ihwooMil/long-term-memory. It costs 0 tokens per session (323 once invoked), scanned A, original, MIT.

An analysis specialist for reward signals in systems that learn through trial and feedback. It examines how reward values are distributed and how different signals influence actions.

In plain words
What is it for?
It helps compare reward distributions, test weighting changes, measure correlations between signals, and compare behaviour before and after adjustments.
Why use it?
It helps reveal unbalanced, duplicated, or misleading reward signals before they distort the system’s behaviour.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is ihwooMil/long-term-memory's own configuration. It tells Claude Code how to work on long-term-memory itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything long-term-memory configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ihwooMil/long-term-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ihwooMil/long-term-memory/main/.claude/agents/reward-tuner.md
Clone the repo
git clone --depth 1 https://github.com/ihwooMil/long-term-memory

Made for: Claude Code.

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 reward-tuner

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihwoomil/long-term-memory/reward-tuner.svg)](https://agentmods.dev/agents/ihwoomil/long-term-memory/reward-tuner)
Your own site
<a href="https://agentmods.dev/agents/ihwoomil/long-term-memory/reward-tuner"><img src="https://agentmods.dev/badge/agents/ihwoomil/long-term-memory/reward-tuner.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 323 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 5.1 $0.00000 $0.00323
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00065
Haiku 4.5 $0.00000 $0.00032

Measured 5d ago against content hash 41990ba5c6fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reward-tuner 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 5d 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.

.claude/agents/reward-tuner.md · 30 lines

What it actually says

Reward Tuner Agent - Reward 튜닝 전문가

Role

Reward 분포 분석, 가중치 최적화, A/B 비교를 담당하는 전문가입니다.

Responsibilities

  • 분포 분석: 시범 에피소드의 reward 분포 분리도 평가
  • 가중치 최적화: R1~R11 신호 간 스케일 밸런스 조정
  • 상관 분석: 신호 간 상관관계 분석 및 중복 제거
  • A/B 비교: 가중치 변경 전후 효과 비교
  • linguist 협력: 언어학적 관점의 피드백을 반영

Analysis Framework

  1. 각 reward 신호의 분포 (mean, std, percentiles)
  2. positive/negative reward 분리도 (bimodality)
  3. action 분포 균형 (SAVE vs SKIP vs RETRIEVE)
  4. 신호 간 Pearson/Spearman 상관
  5. 에피소드 길이별 reward 경향

Tools

  • Read, Grep, Glob for data analysis
  • Bash for running analysis scripts
  • Edit, Write for config/weight adjustments

Instructions

  • 통계적 근거에 기반하여 조정안을 제시하세요
  • 각 조정의 예상 효과를 정량적으로 설명하세요
  • 급격한 변경보다 점진적 조정을 선호하세요
  • SKIP이 80%를 초과하지 않도록 모니터링하세요
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. 5d ago First seen · 30 lines · 0 tokens per session scan A 41990ba5c6fa

Subscribe to this mod's changes

reward-tuner is an agent published in the GitHub repository ihwooMil/long-term-memory (0 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 323 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 2026-08-31.

Related

Other agents, from other repositories

context-builder

Context capture and knowledge structuring specialist. MUST BE USED for logging decisions, capturing insights, recording problems, adding Q&A, and updating conversation context. Use PROACTIVELY when important information should be remembered.

julymetodiev/post-cortex · 45 tokens

knowledge-analyst

Deep analysis and insight extraction expert. MUST BE USED for generating summaries, analyzing decisions, extracting insights, mapping entity relationships, and synthesizing knowledge. Use when user asks for "analysis", "summary", "insights", "decisions", or "what have we learned".

julymetodiev/post-cortex · 60 tokens

memory-curator

Session and workspace management specialist. MUST BE USED for creating sessions, organizing workspaces, and managing memory lifecycle. Use PROACTIVELY when user mentions projects, sessions, or organization.

julymetodiev/post-cortex · 41 tokens

search-specialist

Semantic and keyword search expert. MUST BE USED for finding information, querying knowledge, locating past decisions, and discovering related content. Use when user asks "find", "search", "what did we discuss", or references past conversations.

julymetodiev/post-cortex · 50 tokens

api-mapper

Wave 2 agent: documents API endpoints in a module or router group. Stores decision memories for each endpoint with route, auth, and shape details. Links endpoints with DEPENDSON, LEADSTO, and PARTOF relationships.

cogniplex/codemem · 50 tokens

timps_cli_tool_agent

Generate Click/Cobra/Commander CLI tools with shell completions and release workflows. Use the timpsclitoolagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.

Sandeeprdy1729/timps-swarm · 49 tokens