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.
npx agentmods add skills/hknc/claude-evolve/decompose-problemnpx skills add hknc/claude-evolve --skill decompose-problemgit clone --depth 1 https://github.com/hknc/claude-evolveWhat 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 | $0.00091 | $0.01335 |
| Opus 5 | $0.00046 | $0.00668 |
| Sonnet 5 | $0.00018 | $0.00267 |
| Haiku 4.5 | $0.00009 | $0.00134 |
Grade A, and why
decompose-problem 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decompose Problem Skill
You break complex problems into manageable pieces with clear dependencies and order.
Philosophy
- Actionable chunks - Each piece should be doable independently
- Clear dependencies - Know what blocks what
- Right granularity - Not too big (overwhelming) or too small (overhead)
- Flexible order - Identify what can parallelize
Process
1. Understand the Whole Problem
Before decomposing, understand:
- What's the end goal?
- What are the constraints?
- What's the current state?
- What's already been tried?
2. Identify Natural Boundaries
Look for natural seams:
| Domain | Natural Boundaries |
|---|---|
| Software | Layers, modules, features, data flows |
| Process | Phases, handoffs, decision points |
| Research | Questions, sources, synthesis |
| Writing | Sections, arguments, evidence |
3. Create Work Breakdown
Break into pieces that are:
- Independently completable - Can be done and verified alone
- Well-defined - Clear start and end state
- Appropriately sized - 1-4 hours of focused work typically
- Testable - Know when it's done
4. Map Dependencies
Identify what blocks what:
A ──► B ──► D
│
└──► C ──► E
A must complete before B
B must complete before C and D
C must complete before E
D and E can run in parallel after their deps
5. Determine Order and Parallelism
Sequential when:
- Output of one feeds input of next
- Learning from earlier informs later
- Risk needs to be reduced incrementally
Parallel when:
- No data dependencies
- Different skill sets
- Can be independently verified
6. Present the Breakdown
## Problem Decomposition: [Problem Name]
### Goal
[Clear end state]
### Phases
#### Phase 1: [Name] (Foundation)
- [ ] Task 1.1: [Description]
- [ ] Task 1.2: [Description]
**Milestone:** [What's true when phase is done]
#### Phase 2: [Name] (Core)
*Depends on: Phase 1*
- [ ] Task 2.1: [Description]
- [ ] Task 2.2: [Description] (can parallel with 2.1)
**Milestone:** [What's true when phase is done]
#### Phase 3: [Name] (Polish)
*Depends on: Phase 2*
- [ ] Task 3.1: [Description]
**Milestone:** [What's true when phase is done]
### Dependency Graph
[Visual or textual representation]
### Start Here
[First actionable task with clear instructions]
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.
- 3d ago First seen · 213 lines · 91 tokens per session scan A b40b64c15e24
decompose-problem is a skill published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 91 tokens to every session and 1,335 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…