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 skills add Mathews-Tom/armory --skill task-decomposergit clone --depth 1 https://github.com/Mathews-Tom/armoryWrote 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.
[](https://agentmods.dev/skills/mathews-tom/armory/task-decomposer)<a href="https://agentmods.dev/skills/mathews-tom/armory/task-decomposer"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/task-decomposer/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.
<a href="https://agentmods.dev/skills/mathews-tom/armory/task-decomposer"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/task-decomposer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 214 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.02368 |
| Opus 5 | $0.00041 | $0.01184 |
| Sonnet 5 | $0.00016 | $0.00474 |
| Haiku 4.5 | $0.00008 | $0.00237 |
Grade A, and why
task-decomposer 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 4d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Decomposer
Transforms ambiguous feature requests into concrete, implementable task sequences: identifies acceptance criteria, decomposes into tracer-bullet vertical slices with effort sizing, maps dependencies and parallelization, enumerates edge cases, plans testing, labels HITL/AFK readiness, and flags risks — producing a ready-to-execute task board.
When to use this skill vs native decomposition: The base model decomposes features well in an ad-hoc format. Use this skill specifically when you need the structured output: phased task tables with dependency mapping, parallelization flags, risk flags, and integrated test strategy. If you just need a quick list of steps, ask directly without invoking this skill.
Reference Files
| File | Contents | Load When |
|---|---|---|
references/decomposition-patterns.md |
Feature → task decomposition strategies, granularity guidelines | Always |
references/edge-case-checklist.md |
Common edge case categories by domain (web, API, data, CLI) | Edge case identification needed |
references/dependency-mapping.md |
Dependency graph construction, critical path identification | Multi-task breakdown |
references/sizing-guide.md |
Effort estimation guidance (S/M/L), complexity indicators | Effort sizing needed |
Prerequisites
- Feature description or requirements (can be vague — the skill handles ambiguity)
- Project context (tech stack, existing architecture, team size)
Project Context
Before decomposing, check for repo-local agent context:
docs/agents/domain.mdforCONTEXT.md,CONTEXT-MAP.md, and ADR lookup rulesdocs/agents/triage-labels.mdfor readiness labels when tasks become issuesCONTEXT.mdor relevant context-local glossary for task titles and acceptance criteria.out-of-scope/for durable rejections that may affect scope
What ships with it
5 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.
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.
- 4d ago First seen · 229 lines · 81 tokens per session scan A ca553c1937e3
task-decomposer is a skill published in the GitHub repository Mathews-Tom/armory (316 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 2,368 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
manager
A session-to-GitHub tracker that creates, updates, and reads issues across repositories, including their labels, parent epics, and project-board placement.
corp-doctor
A guided maintenance and setup tool for a Personal Corp system, meaning a business workflow built from AI agents, department repositories, and shared rules. It checks what exists before making changes.
pm-prioritize
Use when ranking a list of requirements, features, or backlog items using RICE / ICE / MoSCoW / Kano. Built-in decision tree picks the right framework based on data availability and decision context. Output is a transparent matrix, 2×2 Impact/Effort quadrant, and a Sprint allocation proposal. User-invoked only — do…
pm-roadmap
A roadmap update process that summarizes an iteration, a planned period of work, and its milestones, dependencies, and priorities.
retro
A structured weekly retrospective for a department. It reviews tasks and evidence from an ISO calendar week, then records findings and the next planning goal.
gh-issues
Use when creating, searching, updating, or managing GitHub issues via CLI. Triggers: "issue", "create issue", "gh issue", "task tracking", "context", "handoff", "resume task", "session context", "save progress", "active tasks", "in-progress", "my tasks", "open issues". Covers: gh commands, bulk operations, JSON/jq…