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/bartolli/kmd/to-issuesnpx skills add bartolli/kmd --skill to-issuesgit clone --depth 1 https://github.com/bartolli/kmdWrote 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/bartolli/kmd/to-issues)<a href="https://agentmods.dev/skills/bartolli/kmd/to-issues"><img src="https://agentmods.dev/badge/skills/bartolli/kmd/to-issues.svg" alt="Measured on agentmods" 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 | $0.00140 | $0.02035 |
| Opus 5 | $0.00070 | $0.01018 |
| Sonnet 5 | $0.00028 | $0.00407 |
| Haiku 4.5 | $0.00014 | $0.00203 |
Grade A, and why
to-issues 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 today.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
To Issues — Break Stories into Vertical Slices (and Optionally Mirror to GitHub/GitLab)
Take a wiki user story and decompose it into independently-grabbable vertical slices using tracer bullets. In GitHub/GitLab mode, also mirror ready-for-agent slices to the remote tracker.
Hand-off from /to-stories: /to-stories writes a rough slice draft (1-3 coarse slices) when synthesizing stories. /to-issues is the refinement pass — validates vertical-slice rules, splits coarse slices, sets blocked_by dependencies, and mirrors to GH/GitLab. Run /to-issues after /triage promotes a story to ready-for-agent, or earlier if the user wants to refine slicing before triage.
Prerequisites
WIKI_SCOPE: <scope>declared in the project instructions.- The target story file exists at
projects/<scope>/plan/<plan-name>/story-N-<slug>.md. WIKI_ISSUE_TRACKERdeclared in the project instructions (github,gitlab, orlocal).
What is a vertical slice (tracer bullet)?
A slice is a thin path that cuts through ALL integration layers end-to-end, NOT a horizontal slice of one layer.
- Each slice delivers a narrow but COMPLETE path through every layer (schema · API · UI · tests).
- A completed slice is independently demoable or verifiable.
- Prefer many thin slices over few thick ones.
Slices may be AFK (autonomous-runnable) or HITL (needs human interaction — architectural decision, design review, manual testing). Prefer AFK over HITL where possible.
Anti-pattern: "Slice 1: build the schema. Slice 2: build the API. Slice 3: build the UI." That's horizontal — none of those slices is independently demoable. Convert to vertical: "Slice 1: end-to-end happy path. Slice 2: validation rules. Slice 3: error handling."
Process
1. Gather context
- Read the target story file: frontmatter + body (User Story, Scenarios, existing Slices, References).
- Read the parent
plan/plan-{name}.mdfor context. - Read
glossary.mdfor vocabulary; ADRs and specs referenced by the story for technical constraints. - Check
WIKI_ISSUE_TRACKERto determine remote-mirror behavior.
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.
- today Changed 6a832ad988aa
- 4d ago First seen · 183 lines · 140 tokens per session scan A 574ca782435b
to-issues is a skill published in the GitHub repository bartolli/kmd (7 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 2,035 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
bmad-correct-course
Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change".
bmad-correct-course
Assess the impact of a significant change during sprint execution across the PRD, epics, architecture, and UX documents, and produce a sprint change proposal. Use when the user says "correct course" or "propose sprint change".
retrospective
Protocol for writing sprint retrospective lessons learned.
adev:retro
Analyze completed work over a time period to extract lessons, compute delivery metrics, identify improvement opportunities, and update context artifacts. Sprint retrospective for agentic development. Use when the user says 'run a retro', 'what went well', 'review the sprint', 'delivery metrics', or wants to reflect on…
zentao-tour
以轻松聊天的方式带用户上手禅道（ZenTao）与 zentao-cli，让用户顺着自己的角色（产品经理/项目经理/测试/开发/高管）在真实禅道环境里边聊边动手，熟悉产品、需求、计划、任务、Bug、测试用例等模块的增删改查与状态流转。当用户首次接触禅道、想上手 zentao-cli、希望了解禅道能做什么，或明确提出"带我了解禅道/给我一个禅道 tour/体验禅道"时使用本技能。.
project-retrospective
Generate a LESSONS.md from a finished project: what worked, what didn't, what to reuse, what to retire — formatted for next-project carry-over.