issue-tree

issue-tree is a skill for Claude Code from mshadmanrahman/pm-pilot. It costs 104 tokens per session (1,643 once invoked), scanned A, original, MIT.

A method for breaking a messy problem into a clear tree of smaller questions or tasks. It separates finding causes, planning work, and choosing actions so those discussions do not get mixed together.

In plain words
What is it for?
Use it to investigate an unexplained metric change, plan a deliverable, or compare possible actions.
Why use it?
It helps teams agree on what they are trying to solve before jumping to solutions. This makes root-cause analysis, planning, and decision-making easier to follow.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pm-core plugin — 14 skills, 2 agents shipped together

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/mshadmanrahman/pm-pilot/issue-tree
Any agent
npx skills add mshadmanrahman/pm-pilot --skill issue-tree
Clone the repo
git clone --depth 1 https://github.com/mshadmanrahman/pm-pilot

Made for: Claude Code.

Or install pm-core, the plugin that ships this one along with the rest of its 14 skills, 2 agents.

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 issue-tree

README.md
[![agentmods](https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/issue-tree.svg)](https://agentmods.dev/skills/mshadmanrahman/pm-pilot/issue-tree)
Your own site
<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/issue-tree"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/issue-tree.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,643 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 $0.00104 $0.01643
Opus 5 $0.00052 $0.00822
Sonnet 5 $0.00021 $0.00329
Haiku 4.5 $0.00010 $0.00164

Measured 6d ago against content hash b1b06d29a2cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

issue-tree 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 6d 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/pm-core/skills/issue-tree/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Tree: Structure Before You Solve

A classic McKinsey-style tool for splitting one messy problem into three separate jobs: finding the cause, planning the work, and picking an action. Most problem discussions fail before anyone opens a doc, because the team never agreed which of those three jobs it was doing. Someone proposes a fix while another person is still arguing about the cause. Nobody notices, because both look like "talking about the problem."

When to activate

  • User says "issue tree", "why tree", "how tree", "structure this problem", "break this down", "root cause"
  • A metric is off and nobody has agreed on the cause yet ("activation is down, what do we do")
  • A deliverable needs a workplan and the pieces are still tangled ("we need a PRD but I don't know where to start")
  • Multiple options are on the table and none has been ranked ("should we do A or B or C")
  • Before invoking prioritize or prd on a problem that has not been framed yet

Step 1: Name the actual question first

Do not build a tree until this is answered. Ask the user directly if it is not obvious from context:

"Do you need to find a cause, build a plan, or pick an action?"

That question maps to exactly one tree. Building the wrong tree, or all three before deciding which is needed, is the failure this skill exists to prevent.

If the user needs to... Build a Root question shape Leaves are Output
Explain why a metric moved Why-tree "Why is X happening?" Candidate cause families Testable hypotheses, ranked by likelihood
Turn a deliverable into a workplan What-tree "What does producing X require?" Analyses, decisions, commitments, artifacts Sequenced workplan
Choose among possible actions How-tree "How might we achieve X?" Concrete interventions Ranked options

A How-tree only makes sense once a cause is confirmed or a goal is fixed. Building one before the Why-tree is settled just relabels guesses as options.

Read the full file on GitHub · 99 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. 6d ago First seen · 99 lines · 104 tokens per session scan A b1b06d29a2cb

Subscribe to this mod's changes

issue-tree is a skill published in the GitHub repository mshadmanrahman/pm-pilot (19 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 1,643 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

work-pipeline

Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.

davepoon/buildwithclaude · 52 tokens

feature-spec

Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.

davepoon/buildwithclaude · 32 tokens

sdd-pipeline

파이프라인 에이전트(specifier, planner, scheduler, builder, verifier, committer)가 참조하는 규칙/스키마 문서 모음.

davepoon/buildwithclaude · 0 tokens

gmgn-dev-score

Decide whether a token creator's NEXT launch is safe to buy. Scores a dev address 0-100 on two separate axes — CONDUCT (will he dump on you at open) and POWER (has he ever actually built anything big) — from his full launch history and every trade he made in his own coins, then returns a buy / don't-buy call with a…

GMGNAI/gmgn-skills · 529 tokens

decided-import

Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…

asdecided/core · 98 tokens

orch

AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.

oxgeneral/ORCH · 71 tokens