mtk-agent-toolkit: Skill for Claude Code

.claude/skills/golden-path-capture/SKILL.md

golden-path-capture is a skill for Claude Code from moberghr/mtk-agent-toolkit. It costs 43 tokens per session (2,877 once invoked), scanned B, original, MIT.

A workflow that records a reusable solution after the agent has failed at the same sub-problem at least twice and then solved it with a different approach.

In plain words
What is it for?
Use it to capture the failed approaches and the working method when the agent solves a recurring technical problem on its own.
Why use it?
It preserves useful lessons from trial and error instead of leaving future sessions to repeat the same dead ends.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md; mentions Codex.

This is moberghr/mtk-agent-toolkit's own configuration. It tells Claude Code how to work on mtk-agent-toolkit 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 mtk-agent-toolkit configures →

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 mtk plugin — 45 skills, 6 agents, 7 hooks, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. 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/moberghr/mtk-agent-toolkit/main/.claude/skills/golden-path-capture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code.

Or install mtk, the plugin that ships this one along with the rest of its 45 skills, 6 agents, 7 hooks, 1 MCP server.

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 golden-path-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/golden-path-capture/github.svg)](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/golden-path-capture)
Your own site
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/golden-path-capture"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/golden-path-capture/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 golden-path-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/golden-path-capture"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/golden-path-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,877 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00043 $0.02877
Opus 5 $0.00022 $0.01438
Sonnet 5 $0.00009 $0.00575
Haiku 4.5 $0.00004 $0.00288

Measured today against content hash f210d0788291, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

golden-path-capture scanned grade B with 1 finding 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 today.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -i "<keyword>" .claude/lessons/personal.md tasks/lessons.md 2>/dev/null
.claude/skills/golden-path-capture/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Golden Path Capture

Overview

The moment of highest lesson-density is when you — not the engineer — get stuck. You try the same sub-problem, hit the same failure signature 2+ times, then switch to a materially different approach that works. That struggle-then-success arc contains exactly the knowledge a future session needs: the dead ends to avoid and the golden path that resolved them. Left uncaptured, it is lost until a later mining sweep happens to notice it — if it ever does. Capture it immediately, in-session.

This skill sits between two siblings; keep the three distinct:

  • correction-capture — engineer-driven. Fires when the human says "no", "stop", "not like that", or redirects your approach. The knowledge originates from a person.
  • golden-path-capture (this skill) — self-driven. Fires when you resolve your own repeated failure through trial and error, with no engineer correction involved. The knowledge originates from your own struggle.
  • lesson-mining — after-the-fact. A periodic sweep of past session transcripts, reject-by-default, suggest-only. It is the safety net that catches what live capture missed; this skill is the live capture that means the sweep rarely has to.

The capture reuses correction-capture's destinations and the same scripts/learnings.sh add structured path — do not invent a new storage format. Frame the lesson around wrong_turns (the failed attempts) and time_cost (minutes the loop cost), because those are precisely what this trigger produces.

When To Use

  • The same file, error message, or failure signature has failed 2+ times this session, then a materially different approach succeeded
  • You looped on a build/test/config error, changed strategy, and it finally passed
  • You discovered a non-obvious constraint the hard way (an API shape, an ordering requirement, a hidden dependency) after repeated attempts
  • The resolution is durable — a future session hitting the same signature would benefit from knowing the golden path up front

Read the full file on GitHub · 153 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. today Changed f210d0788291
  2. yesterday Changed 1208551e34c3
  3. 9d ago First seen · 153 lines · 43 tokens per session scan B a3a7fae74888

Subscribe to this mod's changes

golden-path-capture is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 2,877 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens