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/hoavdc/codexkit/codexkit-backlog-refinernpx skills add hoavdc/CodexKit --skill codexkit-backlog-refinergit clone --depth 1 https://github.com/hoavdc/CodexKitWhat 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 | $0.00068 | $0.00932 |
| Opus 5 | $0.00034 | $0.00466 |
| Sonnet 5 | $0.00014 | $0.00186 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
codexkit-backlog-refiner 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog Refiner
Purpose
Transform raw backlog items into sprint-ready User Stories that meet INVEST criteria, with clear Acceptance Criteria and reliable estimates.
When to use
- mid-sprint refinement sessions (preparing items for the next sprint)
- when backlog items are vague, oversized, or lack acceptance criteria
- when the team needs help decomposing epics into estimable stories
- when onboarding a new Product Owner who needs story-writing structure
When not to use
- prioritizing backlog order (Product Owner responsibility)
- strategic roadmap discussions or feature discovery
- items already refined and ready for sprint planning
Inputs
- raw backlog items (titles, rough descriptions, business context)
- product goal or current product increment theme
- team's story point calibration reference (what does 1 point mean?)
- known technical constraints or dependencies
- Definition of Done for the product
Procedure
- Review each item against INVEST checklist:
- I — Independent: not blocked by other stories
- N — Negotiable: details can be discussed with PO
- V — Valuable: delivers clear value to user or business
- E — Estimable: team can estimate the effort
- S — Small: completable within one sprint
- T — Testable: has verifiable acceptance criteria
- Write User Story using 3C template:
- Card: "As a [persona], I want [action] so that [benefit]"
- Conversation: context, questions for clarification
- Confirmation: Acceptance Criteria in Given/When/Then
- Estimate effort using Planning Poker reference scale:
- 1 pt ≈ 4h | 2 pt ≈ 1 day | 3 pt ≈ 1.5 days | 5 pt ≈ 3 days
- 8 pt = needs breakdown | 13+ pt = Epic, must split
- Flag items that are too large — recommend split strategies.
- Identify dependencies on other teams, services, or external parties.
- Document risks or unknowns that could block the story.
Output
- refined User Stories with INVEST checklist scores
- Acceptance Criteria (3–5 per story, Given/When/Then format)
- Story Point estimates with rationale
- split recommendations for oversized items
- dependency and risk flags
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 · 101 lines · 68 tokens per session scan A d04b01ebcf7d
codexkit-backlog-refiner is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 932 once invoked, about $0.0003 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
claude_code_delegation
Delegate coding, review, and refactor tasks to Claude Code CLI through Row-Bot's approval-gated shell workflow.
developer_review
Code-review workflow for Developer Studio repositories.
ppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Has TWO workflows: (1) Primary — AI-generated full-slide images composed via scripts/generate.py; (2) Fallback — python-pptx programmatic slides (all text editable, better for reports/project management). The fallback…
kanban-orchestrator
Kanban orchestrator: decompose, route, verify. No executing.
kanban-worker
Kanban worker lifecycle: claim, work, heartbeat, complete.
reducing-aigc-detection
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.