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 ShaftHQ/SHAFT_ENGINE --skill work-itemgit clone --depth 1 https://github.com/ShaftHQ/SHAFT_ENGINEWrote 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/shafthq/shaft_engine/work-item)<a href="https://agentmods.dev/skills/shafthq/shaft_engine/work-item"><img src="https://agentmods.dev/badge/skills/shafthq/shaft_engine/work-item/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/shafthq/shaft_engine/work-item"><img src="https://agentmods.dev/badge/skills/shafthq/shaft_engine/work-item.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00429 |
| Opus 5.5 | $0.00014 | $0.00172 |
| Sonnet 5.5 | $0.00007 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
work-item 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.
What it actually says
Work item
Load this skill when the deliverable is open or rewrite a work item. Do not
vendor Spec Kit or create .specify/. Keep GitHub PR delivery on
work-github-playbook.md. One GitHub issue tracks the full plan. When the owner names a currently active PR, deliver the plan and the user-issue fix in that same PR.
Contract and adapters: work-item.md.
One item, one problem
One work item owns one actionable problem. Trackers list children; they do not absorb them. Preserve existing acceptance when rewriting.
Required Spec Kit sections
Every body must include:
- User Scenarios & Testing
- Edge Cases
- Functional Requirements
- Success Criteria
- Assumptions or Out of scope
Keep adopter template headings (for example bug or feature fields) so existing validators still match.
When rewriting an existing item for Spec Kit hygiene, specialize User Story,
FR-*, and SC-* from that issue's own acceptance (see
scripts.agents.issue_filing.rewrite_body_spec_kit). Keep the shared heading
checklist; never paste the generic stamp Deliver the stated acceptance onto
unrelated tickets. Trackers may keep a campaign-level story.
Taxonomy
Exactly one primary type, exactly one lifecycle, at least one subsystem or module. Missing taxonomy fails closed with a named reason. Ready needs a proof plan; blocked needs at least one https dependency URL.
Adapter selection
Detect the live CLI from the adopter environment. Do not assume GitHub. Command maps live in the adapters reference named from the contract. Live create/edit remains whatever CLI the adopter already runs; dry-run and fake runners prove the other maps.
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.
- 6d ago Changed · +3 lines bd008131fef0
- 1mo ago Changed 9cd5717ea30e
- 1mo ago Changed 324a5c31e130
- 2mo ago First seen · 53 lines · 35 tokens per session scan A 15dd0993c97c
work-item is a skill published in the GitHub repository ShaftHQ/SHAFT_ENGINE (418 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 429 once invoked, about $0.0001 per session on Opus 5.5. 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.
work-item compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| work-itemShaftHQ/SHAFT_ENGINE | Skill | 418 | yesterday | MIT | A | 35 | Claude Code, Codex |
| Framework Architectanhtester/antigravity-testing-kit | Skill | 152 | 3mo ago | MIT | A | 40 | Claude Code, Codex |
| Smart Locator Agentanhtester/antigravity-testing-kit | Skill | 152 | 3mo ago | MIT | A | 28 | Claude Code, Codex |
| QA Automation Engineeranhtester/antigravity-testing-kit | Skill | 152 | 3mo ago | MIT | A | 41 | Claude Code, Codex |
| Locator Healer Agentanhtester/antigravity-testing-kit | Skill | 152 | 3mo ago | MIT | A | 27 | Claude Code, Codex |
| release-notesAzure/azure-sdk-for-java | Skill | 2.6k | yesterday | MIT | A | 50 | Claude Code, Codex |
| feature-workflowapache/tika | Skill | 4.1k | yesterday | Apache-2.0 | A | 77 | Claude Code, Codex |