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/dmoskov/sharedskills/task-decompositionnpx skills add dmoskov/sharedskills --skill task-decompositiongit clone --depth 1 https://github.com/dmoskov/sharedskillsWhat 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 | $0.00024 | $0.01219 |
| Opus 5 | $0.00012 | $0.00609 |
| Sonnet 5 | $0.00005 | $0.00244 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
task-decomposition 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 2d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Decomposition Skill
Break large, module-level, or vague tasks into concrete file-level subtasks that agents (or humans) can execute independently. Each subtask targets specific files, has clear acceptance criteria, and is scoped to 30 min - 2 hr of work.
Subtasks are created as Asana subtasks of the parent task, with custom fields (execution status, effort, project, task type, validation status) populated from your workspace configuration — no GIDs are hardcoded in this skill.
Setup (one-time)
- Install the Asana client from this repo:
cd asana && ./setup.sh, setASANA_ACCESS_TOKEN - Create your workspace config:
Seepython3 asana/asana_config_loader.py template > ~/.config/ai-dev-tools/asana_config.yaml # Fill in your workspace's GIDs, then: python3 asana/asana_config_loader.py validateasana/asana_config.example.yamlfor a fully annotated example, including how to discover the GIDs for your workspace, projects, custom fields, and enum options. - To invoke this skill from other projects, symlink it into
~/.claude/skills/(or a project's.claude/skills/) and tell it where this repo lives:
Allln -s /path/to/ai-dev-tools/skills/task-decomposition ~/.claude/skills/task-decomposition export AI_DEV_TOOLS_DIR=/path/to/ai-dev-tools # add to your shell profileasana/...paths in this skill resolve against$AI_DEV_TOOLS_DIR(falling back to the current directory, which works when your session is inside this repo or a checkout that vendors it, e.g. as a git submodule).
When to Use
- A task touches multiple files or modules and is too broad for a single work session
- A task description is vague and needs concrete file targets before execution
- An XL or L effort task needs splitting into S/M subtasks
- A task has failed or timed out repeatedly — recurring failure usually means it's too large, not that execution keeps getting unlucky
Should You Decompose? (pre-flight checks)
What ships with it
1 file 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.
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.
- 2d ago First seen · 119 lines · 24 tokens per session scan A 998dad6876f7
task-decomposition is a skill published in the GitHub repository dmoskov/sharedskills (2 stars, last pushed 11d ago), licensed MIT. It adds 24 tokens to every session and 1,219 once invoked, about $0.0001 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.