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 volodchenkov/claude-sdlc-agents --skill step-execution-disciplinegit clone --depth 1 https://github.com/volodchenkov/claude-sdlc-agentsWrote 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/volodchenkov/claude-sdlc-agents/step-execution-discipline)<a href="https://agentmods.dev/skills/volodchenkov/claude-sdlc-agents/step-execution-discipline"><img src="https://agentmods.dev/badge/skills/volodchenkov/claude-sdlc-agents/step-execution-discipline/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/volodchenkov/claude-sdlc-agents/step-execution-discipline"><img src="https://agentmods.dev/badge/skills/volodchenkov/claude-sdlc-agents/step-execution-discipline.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 | $0.00109 | $0.01730 |
| Opus 5 | $0.00055 | $0.00865 |
| Sonnet 5 | $0.00022 | $0.00346 |
| Haiku 4.5 | $0.00011 | $0.00173 |
Grade A, and why
step-execution-discipline 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 9d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step-Execution Discipline
Multi-step PLANs are how the team avoids 14-step single-run burnouts: tokens burn, sessions hang on step 4, no visible progress, no resume point. This skill encodes the contract.
Two parts:
- Sizing — how to decompose a SPEC into the right number of steps with the right edges.
- Execution — one invocation per step + self-handoff + checkbox state in PLAN sub-issue description.
The infra side (queue-on-running so self-handoff doesn't race the webhook) lives in plane-conductor ≥ the PR that landed queue-on-running. If your conductor is older, self-handoff drops on the floor — escalate before relying on this skill.
Part 1 — Sizing
You author the PLAN. The SA produces SPEC with acceptance criteria; only you know what's hard. Don't ask SA to pre-size — they don't know the codebase shape you're about to touch.
5-budget AND-filter (every step must pass ALL five)
| Budget | Limit | Why |
|---|---|---|
| Time | ≤15–20 min wall-clock work | Beyond this, hang risk + context bloat + retry chains land in the wrong place |
| Files | ≤10 touched | More = mixing concerns; next-step diff becomes unreadable |
| Diff | ≤300–500 net LoC | More = reviewer (human or agent) can't track between-step delta |
| Acceptance | exactly ONE binary statement | «After this step, endpoint X returns 201 with {id}». NOT «feature works», NOT «tests pass» — that's not a step, that's a goal |
| Verifiability | compiles + existing tests still green | Next step starts on a working tree, not on a half-broken one |
A draft step violating any budget → split further. Recursion until clean. The filter is AND, not OR.
Vertical slices by default
Each step is a thin vertical pass through all layers (model + migration + view + minimal smoke), not a horizontal layer (all models, then all APIs, then all UI).
❌ Horizontal (wrong):
1. All models
2. All migrations
3. All endpoints
4. All serializers
5. All UI
After step 1 nothing works. Until step 5 nothing works. No demoable point.
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.
- 9d ago First seen · 145 lines · 109 tokens per session scan A 29085713fbfd
step-execution-discipline is a skill published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,730 once invoked, about $0.0005 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…