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/biggora/claude-plugins-registry/slice-verticalnpx skills add biggora/claude-plugins-registry --skill slice-verticalgit clone --depth 1 https://github.com/biggora/claude-plugins-registryWrote 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/biggora/claude-plugins-registry/slice-vertical)<a href="https://agentmods.dev/skills/biggora/claude-plugins-registry/slice-vertical"><img src="https://agentmods.dev/badge/skills/biggora/claude-plugins-registry/slice-vertical.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 | $0.00086 | $0.00795 |
| Opus 5 | $0.00043 | $0.00398 |
| Sonnet 5 | $0.00017 | $0.00159 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
slice-vertical 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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slice Work Vertically
Convert approved outcomes into the smallest reviewable increments that prove user value end to end.
Establish the Baseline
- Locate the approved specification and its acceptance criteria.
- Stop and request definition or approval when either is missing, ambiguous, or still disputed. Do not silently invent product intent.
- Read the repository instructions, architecture, tests, and current task state. Read
AGENTS.mdandCLAUDE.mdwhen present, but never overwrite them automatically. - Reuse the repository's task-state convention. If none exists, write the slice plan to
.agent/tasks/<slug>.md. - State assumptions, competing interpretations, constraints, and unresolved risks before choosing slices.
Build the Slice Map
- Trace each acceptance criterion through the relevant data, domain, API, UI, integration, and operations boundaries. Include only layers the outcome actually needs.
- Select the thinnest capability a user or stakeholder can demonstrate independently. Prefer delivered user value and risk reduction over minimum file count.
- Carry the minimum required work across relevant layers inside the same slice. Do not create horizontal phases such as "all database work," then "all APIs," then "all UI."
- Put dependency blockers and high-impact unknowns into the earliest slice that can test them through a real end-to-end path. If a standalone investigation is unavoidable, mark it as an enabling checkpoint rather than completed product value.
- Order the remaining slices by dependency, risk, and incremental user value. Keep each slice independently reviewable as one PR-sized checkpoint.
- Keep exactly one slice
Active; mark all othersPending,Blocked, orDone.
Define Every Slice
Record all of these fields:
- User outcome: the observable value or learned constraint.
- Scope: behavior included in this slice.
- Not in scope: behavior deliberately deferred.
- Dependencies: prior slices, decisions, services, or data required.
- Likely paths: repository areas expected to change; label uncertainty instead of fabricating paths.
- Done when: fresh executable checks and observable assertions that prove the outcome.
- Demo method: exact user or stakeholder path for showing the increment.
- Status:
Pending,Active,Blocked, orDone.
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.
- 4d ago First seen · 51 lines · 86 tokens per session scan A c4c9b2908c3a
slice-vertical is a skill published in the GitHub repository biggora/claude-plugins-registry (2 stars, last pushed 7d ago), licensed MIT. It adds 86 tokens to every session and 795 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…