What is reasoning-trace-optimizer?

A guide for finding and improving problems in an AI agent's decision process. It examines the agent's reasoning history, instructions, tool use, and repeated failures.

Use it to investigate context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.

It helps explain why an agent gives poor results or loses focus over time. It turns those observations into prompt changes that can be tested again.

reasoning-trace-optimizer — Skill by muratcankoylan

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 skills/muratcankoylan/agent-skills-for-context-engineering/interleaved-thinking

Any agent

npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill interleaved-thinking

Clone the repo

git clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,373 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.

Model	Per session	Once invoked
Fable 5	$0.00035	$0.01373
Opus 5	$0.00017	$0.00687
Sonnet 5	$0.00007	$0.00275
Haiku 4.5	$0.00003	$0.00137

Measured yesterday against content hash 6d330b7afc13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reasoning-trace-optimizer 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 yesterday.

The scan reads SKILL.md. This mod also ships 11 executable files (examples/01_basic_capture.py, examples/02_tool_usage.py, examples/03_full_optimization.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

examples/interleaved-thinking/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reasoning Trace Optimizer

Debug and optimize AI agents by analyzing their reasoning traces. This skill uses MiniMax M2.1's interleaved thinking to provide deep insight into agent decision-making and generate concrete improvements.

When to Activate

Agent reasoning traces need debugging, analysis, or prompt optimization
Agent task fails and user wants to understand why
User mentions "context degradation", "tool confusion", or "instruction drift"
Request to improve agent performance or reduce errors
User wants to generate shareable learnings from debugging sessions
After repeated failures on similar tasks

Core Concepts

Interleaved Thinking

Unlike standard reasoning models that think once at the start, interleaved thinking allows reasoning BETWEEN each tool interaction. This is critical because:

Long-horizon tasks require maintaining focus across many turns
External perturbations (tool outputs, environment changes) need real-time adaptation
Debugging requires seeing HOW decisions were made, not just WHAT was output

The Optimization Loop

Execute Agent → Capture Traces → Analyze Patterns → Optimize Prompt → Re-run
                                                          ↑____________|

Each iteration improves the prompt based on detected patterns until convergence.

Pattern Detection

Common failure patterns the analyzer detects:

Pattern	Description
`context_degradation`	Model loses track of information over long contexts
`tool_confusion`	Model misunderstands tool capabilities or outputs
`instruction_drift`	Model gradually deviates from original instructions
`goal_abandonment`	Model stops pursuing the original goal
`circular_reasoning`	Model repeats similar actions without progress
`premature_conclusion`	Model concludes before completing the task

Usage Modes

Mode 1: M2.1 Agent Debugging

Run a task through M2.1 and analyze its reasoning:

Read the full file on GitHub · 222 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday First seen · 222 lines · 35 tokens per session scan A 6d330b7afc13

Subscribe to this mod's changes

reasoning-trace-optimizer is a skill published in the GitHub repository muratcankoylan/Agent-Skills-for-Context-Engineering (17,868 stars, last pushed 13d ago), licensed MIT. It adds 35 tokens to every session and 1,373 once invoked, about $0.0002 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.

Debugging Planning Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens