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 skills add abstractonion/cadence --skill break-work-into-verifiable-stepsgit clone --depth 1 https://github.com/abstractonion/cadenceWrote 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/abstractonion/cadence/break-work-into-verifiable-steps)<a href="https://agentmods.dev/skills/abstractonion/cadence/break-work-into-verifiable-steps"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/break-work-into-verifiable-steps/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.
<a href="https://agentmods.dev/skills/abstractonion/cadence/break-work-into-verifiable-steps"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/break-work-into-verifiable-steps.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.00388 |
| Opus 5 | $0.00019 | $0.00194 |
| Sonnet 5 | $0.00008 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
break-work-into-verifiable-steps 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.
What it actually says
Break work into verifiable steps
A multi-file or multi-concern change is a sequence of small steps, not one heroic edit. Each step should be independently runnable, independently verifiable, and — when shipping incrementally — independently revertable.
When this applies
The change touches more than one file's primary logic, spans multiple commits, or has more than one acceptance criterion. For tiny single-file edits, just do it.
Each step has
- Files. Exact paths created or modified.
- What changes. The actual code or the precise edit — not "add appropriate handling" or "wire it up".
- How to verify. The command to run (test, build, manual check) and what passing looks like.
- A commit boundary. When shipping incrementally, each step lands as its own focused commit (see
clean-commits).
Don't
- Don't write a step as "TBD" or "similar to step N" — every step must stand on its own; the next reader may not be reading top-to-bottom.
- Don't skip the verify line. "Should work" is not verification (see
verify-with-runtime). - Don't start step N+1 until step N's check passes. A failing step gets fixed before moving on, not deferred to the end.
Why
A sequence of small verified steps is recoverable when something goes wrong: you can point at the last green step and restart from there. A single 800-line diff is not. Steps also make handoff trivial — anyone (including a future session) can pick up at the next unchecked item without re-deriving the plan.
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.
- 10d ago First seen · 30 lines · 38 tokens per session scan A d6d97b25803c
break-work-into-verifiable-steps is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 388 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.
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…