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 agentmods add skills/nikeyes/stepwise-dev/small-safe-stepsnpx skills add nikeyes/stepwise-dev --skill small-safe-stepsgit clone --depth 1 https://github.com/nikeyes/stepwise-devWhat 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 | $0.00071 | $0.03237 |
| Opus 5 | $0.00036 | $0.01618 |
| Sonnet 5 | $0.00014 | $0.00647 |
| Haiku 4.5 | $0.00007 | $0.00324 |
Grade A, and why
small-safe-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 2d 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STARTER_CHARACTER = 🪜⚡
Small Safe Steps
Mission
Help you divide ANY work into the smallest, safest, most valuable steps possible — ideally 1-3 hours each.
Core belief: Risk grows faster than the size of the change.
How to Use This Skill
Automatic activation - just ask:
- "How do I migrate from SendGrid to AWS SES?"
- "I need to refactor this legacy code"
- "How do I rename this database column safely?"
- "What's the safest way to implement X?"
Manual invocation:
/small-safe-steps+ describe your work- Example:
/small-safe-steps Migrate authentication from Auth0 to Keycloak
In workflow with other skills:
- Use story-splitting → Break large story into smaller ones
- Use complexity-review → Simplify technical approach
- Use small-safe-steps (THIS SKILL) → Plan 1-3h implementation steps
When to Use This Skill
Use when:
- Work feels too big or risky (refactoring, migrations, performance fixes)
- Database schema changes, API changes, service replacements
- User asks "how do I implement" after deciding what to build
- Work will take more than 1 day
Do NOT use when:
- User is still deciding WHAT to build (use story-splitting or hamburger-method first)
- Work is already small (< 3 hours)
- User asks for architectural review (use complexity-review instead)
Applies to ALL Types of Work
Product Work
- Feature implementation
- User stories (after initial splitting)
- UX improvements
Technical Work
- Refactorings
- Performance improvements
- Tech debt reduction
- Architecture changes
- Database migrations
Research & Investigation
- Debugging complex issues
- Spike/POC work
- Technology evaluation
- Root cause analysis
Operations & Deployment
- Infrastructure changes
- Service migrations
- Deployment process improvements
Core Process
Step 1: Understand the Goal
Clarify the goal by asking:
- "What's the end state we want?"
- "Why are we doing this now?"
- "What's the smallest outcome that would be valuable?"
- "How will we know it's done?"
- "What's the risk if this goes wrong?"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 376 lines · 0 tokens per session scan A a8ef8c7aa1a5
small-safe-steps is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 14d ago), licensed Apache-2.0. It adds 71 tokens to every session and 3,237 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…