slice-the-spec

slice-the-spec is a skill for Claude Code, Codex from kambleakash0/agent-skills. It costs 30 tokens per session (1,253 once invoked), scanned A, original, MIT.

A tool that turns a product requirements document (PRD) into a backlog of GitHub issues. It breaks work into vertical slices: small tasks that deliver a complete path through the needed parts of a product.

In plain words
What is it for?
Use it to prepare a Kanban-ready backlog from a clarified PRD, with independently workable issues and human-review or autonomous-work flags.
Why use it?
It makes a broad specification easier to plan, assign, and work on in parallel. It also identifies task dependencies and whether a person must review or decide something.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare a Kanban-ready backlog from a clarified PRD, with independently workable issues and human-review or autonomous-work flags.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kambleakash0/agent-skills/slice-the-spec
Install

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.

Any agent
npx skills add kambleakash0/agent-skills --skill slice-the-spec
Clone the repo
git clone --depth 1 https://github.com/kambleakash0/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for slice-the-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/kambleakash0/agent-skills/slice-the-spec/github.svg)](https://agentmods.dev/skills/kambleakash0/agent-skills/slice-the-spec)
Your own site
<a href="https://agentmods.dev/skills/kambleakash0/agent-skills/slice-the-spec"><img src="https://agentmods.dev/badge/skills/kambleakash0/agent-skills/slice-the-spec/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.

agentmods 80×15 button for slice-the-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/kambleakash0/agent-skills/slice-the-spec"><img src="https://agentmods.dev/badge/skills/kambleakash0/agent-skills/slice-the-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,253 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01253
Opus 5 $0.00015 $0.00626
Sonnet 5 $0.00006 $0.00251
Haiku 4.5 $0.00003 $0.00125

Measured 10d ago against content hash 298bd8ec3b58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

slice-the-spec 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 10d 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.

skills/slice-the-spec/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turn a PRD into Issues

This skill takes a clarified PRD and turns it into a small, sharp backlog of vertically sliced GitHub issues. Each issue should be an independently grabbable “tracer bullet” that cuts through all relevant layers end‑to‑end, flushing out unknown unknowns as early as possible.

When to Use

Use this skill when the user:

  • Has a PRD or similar spec (possibly created via /spec-writer) and now wants concrete issues.
  • Wants to turn “destination” docs into a Kanban board of tasks.
  • Needs to break work down so multiple engineers or agents can work in parallel without stepping on each other.

If there is no PRD yet or the requirements are fuzzy, suggest using /grill-me and /spec-writer first.

Concepts

  • Vertical slice / tracer bullet: A thin, end‑to‑end piece of functionality that goes through all necessary layers (data, domain, API, UI, etc.), not just one layer in isolation.
  • HITL issue: Requires Human‑In‑The‑Loop decisions (design review, stakeholder sign‑off, risky refactor, etc.).
  • AFK issue: “Away‑From‑Keyboard” for the human; safe enough for an autonomous agent to implement and merge without human intervention.

Prefer AFK slices where possible, but mark HITL clearly where human judgment is essential.

Workflow

You may compress or skip steps if the context already provides the answer (e.g., the PRD is already loaded and clearly scoped).

  1. Locate and understand the PRD

    • Find the PRD from the conversation or repository (issue, doc, file).
    • Skim to understand: goals, user stories, functional requirements, and explicit non‑goals.
    • If multiple PRDs are present, confirm with the user which one to use.
  2. Explore the codebase

    • Inspect relevant parts of the repo to understand current architecture, major modules, and likely integration points.
    • Note any existing patterns you should respect (e.g., existing feature flags, background jobs, notification systems).
  3. Draft vertical slices (tracer bullets)

    • Break the PRD into a small set of vertical slices, each of which delivers end‑to‑end value and exercises multiple layers of the system.
    • Avoid horizontal slices like “set up database tables” or “build all UI components” unless truly necessary; fold those into end‑to‑end slices instead.
    • For each slice, decide whether it is HITL or AFK, preferring AFK when risk is low.

Read the full file on GitHub · 113 lines

Changes

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.

  1. 10d ago First seen · 113 lines · 30 tokens per session scan A 298bd8ec3b58

Subscribe to this mod's changes

slice-the-spec is a skill published in the GitHub repository kambleakash0/agent-skills (9 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,253 once invoked, about $0.0002 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.