break-spec

break-spec is a skill for Claude Code, Codex from sandsower/beislid. It costs 62 tokens per session (1,989 once invoked), scanned A, original, MIT.

A planning guide that turns an approved product specification or work agreement into phases of implementation. Each phase covers a complete slice of the feature from start to finish.

In plain words
What is it for?
Use it to break down features, product requirements, or project work into phased vertical slices. It helps create an implementation plan from an approved specification or project document.
Why use it?
It makes large work easier to schedule and review by dividing it into usable stages. It also avoids building one technical layer at a time without producing a working part.

Skill for Claude CodeCodex

Part of the beislid plugin — 22 skills shipped together

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

Made for: Claude Code, Codex.

Or install beislid, the plugin that ships this one along with the rest of its 22 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 break-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandsower/beislid/break-spec.svg)](https://agentmods.dev/skills/sandsower/beislid/break-spec)
Your own site
<a href="https://agentmods.dev/skills/sandsower/beislid/break-spec"><img src="https://agentmods.dev/badge/skills/sandsower/beislid/break-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,989 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 $0.00062 $0.01989
Opus 5 $0.00031 $0.00994
Sonnet 5 $0.00012 $0.00398
Haiku 4.5 $0.00006 $0.00199

Measured 4d ago against content hash e94531a6b720, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

break-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.

skills/break-spec/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Break Spec

Takes an approved spec/PRD or Work Contract and produces a phased implementation structure using vertical slices. Each phase cuts through all layers end-to-end rather than building horizontal slabs.

Step 1: Load the spec

If the handoff includes an explicit Work Contract or spec artifact path, read it as the primary input. Otherwise, if the matching spec_approved latest pointer entry for the current ticket/branch resolves to a readable artifact, read that artifact as the primary input; if not, use the workflow-configured artifact path template when present, then check for artifacts in order: plans/*work-contract*.md, plans/*-spec.md, plans/*-spec-*.md, plans/*-prd*.md, a tracker document/issue linked in conversation, or spec content in the current session. For each plans/ glob, use the file if exactly one match exists; if multiple matches exist, ask the user which file to use before falling back to the next source. Keep the narrower spec globs ahead of the PRD fallback so generated structure files like break-spec-structure.md are not treated as specs. If nothing is found, ask the user where it is.

Step 2: Check scope classification

If the input includes scope_classification, use it before phasing:

  • multi_slice: proceed with vertical slice decomposition.
  • project: first identify the missing milestones, contract boundaries, or ownership decisions. If those are not approved, route back to spec refinement instead of inventing slices. Do not scaffold by default.
  • atomic or single_pr: push back before decomposing; ask why this needs a split and proceed only with explicit user approval.
  • unknown: route back to spec refinement; do not create child slices from an unknown classification.

Low-confidence or approval-required classifications are a hard gate before slice planning: present the classifier and proposed route, keep progress prose approval-free, wait for explicit approval in the final response, record approved/declined, and do not decompose until approved. Recommend refinement questions when clearer boundaries could avoid unnecessary decomposition.

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 62 tokens per session scan A e94531a6b720

Subscribe to this mod's changes

break-spec is a skill published in the GitHub repository sandsower/beislid (10 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 1,989 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens