slice-spec

slice-spec is a command for coding agents from JobsHwang/skills. It costs 22 tokens per session (274 once invoked), scanned A, original, MIT.

A command for splitting a large delivery specification into independently verifiable, end-to-end slices. Each slice is a vertical piece of work with observable behavior and stated dependencies.

In plain words
What is it for?
Use it to divide a multi-part feature into implementation slices, document dependency order, preserve cross-layer responsibilities, and write the slices beside the parent specification.
Why use it?
It makes large work easier to deliver and check by identifying useful boundaries, validating risky assumptions early, and showing which pieces must wait for others.

Command

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.

agentmods
npx agentmods add commands/jobshwang/skills/slice-spec
Clone the repo
git clone --depth 1 https://github.com/JobsHwang/skills

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-spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/jobshwang/skills/slice-spec.svg)](https://agentmods.dev/commands/jobshwang/skills/slice-spec)
Your own site
<a href="https://agentmods.dev/commands/jobshwang/skills/slice-spec"><img src="https://agentmods.dev/badge/commands/jobshwang/skills/slice-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 274 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00274
Opus 5 $0.00011 $0.00137
Sonnet 5 $0.00004 $0.00055
Haiku 4.5 $0.00002 $0.00027

Measured 4d ago against content hash 379aa083526b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slice-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 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.

adapters/opencode/commands/slice-spec.md · 23 lines

What it actually says

The user explicitly invoked /slice-spec.

Invocation arguments: $ARGUMENTS

Slice Spec

Split only when splitting increases delivery speed or feedback quality.

  1. Read the parent spec and inspect enough of the repository to understand real seams.
  2. If the work is one coherent deliverable that fits a single implementation session, say that slicing is unnecessary and stop without creating files.
  3. Otherwise create end-to-end vertical slices. Each slice should produce observable behavior and its own verification signal.
  4. Prefer risk-first tracer bullets that validate uncertain contracts early. Do not default to separate frontend, backend, database, or test-only slices.
  5. Declare blocking edges explicitly and keep independent slices parallelizable.
  6. Preserve cross-layer contract ownership and compatibility in every affected slice.

Write files beside the parent spec, normally .scratch/<feature>/slices/01-<slug>.md, using references/slice-template.md. Follow an existing local convention when one exists. Do not create an issue tracker, task state machine, journal, or implementation.

Report the dependency order, why each boundary is useful, and the recommended first slice. The next action is direct implementation unless the user explicitly chooses another workflow.

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. 4d ago First seen · 23 lines · 22 tokens per session scan A 379aa083526b

Subscribe to this mod's changes

slice-spec is a command published in the GitHub repository JobsHwang/skills (2 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 274 once invoked, about $0.0001 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.