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 fabriqaai/specs.md --skill work-item-decomposegit clone --depth 1 https://github.com/fabriqaai/specs.mdWrote 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/fabriqaai/specs.md/work-item-decompose)<a href="https://agentmods.dev/skills/fabriqaai/specs.md/work-item-decompose"><img src="https://agentmods.dev/badge/skills/fabriqaai/specs.md/work-item-decompose.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00021 | $0.01300 |
| Opus 5 | $0.00010 | $0.00650 |
| Sonnet 5 | $0.00004 | $0.00260 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
work-item-decompose 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 8d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<degrees_of_freedom> MEDIUM — Follow decomposition patterns but adapt to the specific intent. </degrees_of_freedom>
<guidelines>
- Prefer vertical slices over horizontal layers
- Start with foundation pieces (models, schemas)
- End with integration pieces (API, UI)
- Keep each item focused on ONE concern
</guidelines>
<complexity level="low">
- Single file or few files
- Well-understood pattern
- No external dependencies
- Examples: bug fix, config change, simple utility
</complexity>
<complexity level="medium">
- Multiple files
- Standard patterns with some decisions
- May touch existing code
- Examples: new endpoint, new component, feature addition
</complexity>
<complexity level="high">
- Architectural decisions required
- Security or data implications
- Core system changes
- Examples: auth system, payment flow, database migration
</complexity>
<bias_table>
| Raw Complexity | autonomous | balanced | controlled |
|----------------|------------|----------|------------|
| low | autopilot | autopilot| confirm |
| medium | autopilot | confirm | validate |
| high | confirm | validate | validate |
</bias_table>
<note>
This allows user preference to shift thresholds:
- autonomous: trusts AI more, fewer checkpoints
- balanced: standard behavior (default)
- controlled: more human oversight
</note>
<check if="circular dependency detected">
<output>
Warning: Circular dependency detected between {item-a} and {item-b}.
Suggest splitting into smaller items or reordering.
</output>
</check>
**Total**: {count} work items
**Estimated**: {low} autopilot, {medium} confirm, {high} validate
**Work Item Details**:
{for each item}
{n}. **{title}** ({mode}) — {description}
{/for}
---
Approve this plan? [Y/n/edit]
</output>
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.
- 8d ago First seen · 167 lines · 21 tokens per session scan A 3b4d1df44e58
work-item-decompose is a skill published in the GitHub repository fabriqaai/specs.md (206 stars, last pushed 15d ago), licensed MIT. It adds 21 tokens to every session and 1,300 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 2026-08-30.
Other skills, from other repositories
acceptance-orchestrator-v2
Acceptance Orchestrator workflow skill. Use this skill when the user needs a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention and the operator should preserve the upstream workflow, copied support files…
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
start-task
Create a feature branch for a backlog task, switch to it, and start implementation. Use when the user says "start task-123", "work on task-123", "implement task-123", or invokes /start-task with a task ID.
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
kn-handoff
Use when a feature crosses repository boundaries and one side must hand work to the other - generates a self-contained frontend-to-backend brief or backend-to-frontend API contract.