methodology-driven-thinking

methodology-driven-thinking is a skill for Claude Code from gagharutyunyan1993/methodology-toolkit. It costs 136 tokens per session (2,530 once invoked), scanned A, original, MIT.

A skill for applying structured analysis to difficult questions, such as planning, diagnosis, research, and choices with trade-offs.

In plain words
What is it for?
Use it to compare options, find root causes, plan under uncertainty, choose an architecture, or decide what to prioritise.
Why use it?
It gives the agent a defined way to break down non-trivial problems instead of answering with an unstructured approach.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

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 methodology-toolkit plugin — 1 skill, 1 command, 1 agent shipped together

Good fit Use it to compare options, find root causes, plan under uncertainty, choose an architecture, or decide what to prioritise.

Compare 6 skills 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 gagharutyunyan1993/methodology-toolkit
Claude Code
/plugin install methodology-toolkit

Made for: Claude Code.

Or install methodology-toolkit, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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 methodology-driven-thinking

README.md
[![agentmods](https://agentmods.dev/badge/skills/gagharutyunyan1993/methodology-toolkit/methodology-driven-thinking/github.svg)](https://agentmods.dev/skills/gagharutyunyan1993/methodology-toolkit/methodology-driven-thinking)
Your own site
<a href="https://agentmods.dev/skills/gagharutyunyan1993/methodology-toolkit/methodology-driven-thinking"><img src="https://agentmods.dev/badge/skills/gagharutyunyan1993/methodology-toolkit/methodology-driven-thinking/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 methodology-driven-thinking

Your own site · 80×15
<a href="https://agentmods.dev/skills/gagharutyunyan1993/methodology-toolkit/methodology-driven-thinking"><img src="https://agentmods.dev/badge/skills/gagharutyunyan1993/methodology-toolkit/methodology-driven-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,530 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 $0.00136 $0.02530
Opus 5 $0.00068 $0.01265
Sonnet 5 $0.00027 $0.00506
Haiku 4.5 $0.00014 $0.00253

Measured 9d ago against content hash ad9dde2535ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

methodology-driven-thinking 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 9d 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.

plugins/methodology-toolkit/skills/methodology-driven-thinking/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Methodology-Driven Thinking

This skill activates structured analytical methods when a task is non-trivial. The output of the skill is the reasoning produced by the methods, not the names of the methods.

Operating Protocol

Step 1 — Read the methodology index

Open ${CLAUDE_PLUGIN_ROOT}/skills/methodology-driven-thinking/methodology.md. This is the authoritative library with use_when, avoid_when, steps, and output for each method. Do not rely on memory — the index may have been updated.

Step 2 — Classify the problem (Cynefin as dispatcher)

Before selecting any other methodology, place the problem in a Cynefin domain:

  • Clear / Simple — known cause-effect, best practice exists. → Exit the skill. Answer directly. Methodologies are tax, not insurance, on trivial tasks.
  • Complicated — knowable through analysis/expertise. → Analytical methods fit (First Principles, ACH, 5 Whys, ToC, Porter, PMESII).
  • Complex — cause-effect only visible in hindsight; requires probes. → Iteration methods fit (OODA, PDCA, Double Diamond, JTBD).
  • Chaotic — no clear cause-effect. → Act first to stabilize, then re-classify.

State the classification in one line. If you can't classify, that itself is a signal — say so.

Step 2.5 — Evidence gate (load-bearing code claims)

This step runs after the Clear/Simple exit and before method selection — trivial tasks never reach it. If the task survived Step 2 and rests on a load-bearing claim about code — what a function returns, where a defect lives, what a command does, what the backend sends — gate the claim before any method consumes it:

  1. Name the claim explicitly: "This conclusion depends on X being true."
  2. Tag its current source tier — Primary (code you read, command output, git, test results), Secondary (.d.ts, prose docs, comments — subject to drift), or Inferred (memory, assumption, analogy).
  3. Promote every load-bearing claim to Primary before it enters a method: run the command, read the file, check git. A claim that stays Secondary/Inferred is a hypothesis, not an input.

Read the full file on GitHub · 108 lines

Files

What ships with it

2 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.

  1. 9d ago First seen · 108 lines · 136 tokens per session scan A ad9dde2535ef

Subscribe to this mod's changes

methodology-driven-thinking is a skill published in the GitHub repository gagharutyunyan1993/methodology-toolkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 136 tokens to every session and 2,530 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

devils-advocate

Utiliser avant toute décision importante pour faire jouer à l'IA le rôle d'un sceptique professionnel. Produit les trois meilleures raisons de ne pas faire ce qui est proposé, classées par force décroissante.

Ludovic33Fr/product-ai-toolbox · 48 tokens

thinking-theory-of-constraints

When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.

tjboudreaux/cc-thinking-skills · 37 tokens

docs-drift

Documentation-drift audit for this plugin monorepo. Audit either each scoped plugin's unreleased changelog claims or its latest shipped release from the previous reachable plugin-name--v tag, then verify that plugin READMEs, docs, CLAUDE.md or AGENTS.md files, and root documentation tell the truth for the matching…

gtapps/claude-code-hermit · 170 tokens

cco-tools

Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.

egorfedorov/claude-context-optimizer · 27 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens

test-run

Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.

gtapps/claude-code-hermit · 35 tokens