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 Kaddo-kdd/kaddo --skill work-item-refinementgit clone --depth 1 https://github.com/Kaddo-kdd/kaddoWrote 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/kaddo-kdd/kaddo/work-item-refinement)<a href="https://agentmods.dev/skills/kaddo-kdd/kaddo/work-item-refinement"><img src="https://agentmods.dev/badge/skills/kaddo-kdd/kaddo/work-item-refinement/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/kaddo-kdd/kaddo/work-item-refinement"><img src="https://agentmods.dev/badge/skills/kaddo-kdd/kaddo/work-item-refinement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00049 | $0.00800 |
| Opus 5.5 | $0.00020 | $0.00320 |
| Sonnet 5.5 | $0.00010 | $0.00160 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
work-item-refinement 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- lateral-thinking — 88% identical, 158 lines differ
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Item Refinement Skill
Purpose
Standardize how a Work Item is sharpened from a rough idea into a ready, implementable item.
When to use
When improving a draft Work Item, or turning a backlog idea / roadmap candidate into a ready item.
Inputs
The context pack and the Work Item (draft or candidate).
Output
An improved Work Item with: actor and outcome, current behavior, target behavior, entry points, end-to-end flow, impact analysis, module coverage, scope unknowns, scope confidence, problem, expected result, scope, out of scope, acceptance criteria (including end-to-end criteria for user-facing changes), validation (how to test it), definition of done, open questions and dependencies.
Steps
- Outcome framing — identify actor, current behavior, target behavior, observable completion.
- Journey reconstruction — map entry point, interaction, service/API, state change, response, final outcome.
- Surface review — evaluate: product/UI, frontend, backend, database, configuration, feature flags, content/copy, authentication/authorization, notifications, analytics, documentation, operations/release — as affected, reviewed-not-affected, unknown, or not-applicable.
- Module review — for multirepo, evaluate each mapped module with the same statuses.
- Resource review — ask: does this change need to observe, modify, validate or deliver against a
known external resource of the project (a Project Resource under
knowledge/tech/resources/— database, cloud, API, queue, storage…)? If so, declare it in the WI front matterresources:with a role (affected,implementation,validation,delivery). Resources are external systems, distinct fromaffected_modules(code). Not every WI needs resources (e.g. a CSS change does not). - Completeness review — confirm: outcome covered, journey covered, modules assessed, resources assessed, unknowns visible, acceptance criteria end-to-end, scope and out-of-scope coherent.
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.
- 1mo ago Changed · +7 lines b97b2358eb1b
- 1mo ago First seen · 70 lines · 49 tokens per session scan A 5cadd569cb3b
work-item-refinement is a skill published in the GitHub repository Kaddo-kdd/kaddo (71 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 800 once invoked, about $0.0002 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 2026-09-25.
work-item-refinement compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| work-item-refinementKaddo-kdd/kaddo | Skill | 71 | yesterday | MIT | A | 49 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |