Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/elbwalker/walkerOSnpx agentmods add skills/elbwalker/walkeros/walkeros-using-step-examplesWrote 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/elbwalker/walkeros/walkeros-using-step-examples)<a href="https://agentmods.dev/skills/elbwalker/walkeros/walkeros-using-step-examples"><img src="https://agentmods.dev/badge/skills/elbwalker/walkeros/walkeros-using-step-examples/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/elbwalker/walkeros/walkeros-using-step-examples"><img src="https://agentmods.dev/badge/skills/elbwalker/walkeros/walkeros-using-step-examples.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 72 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00037 | $0.07006 |
| Opus 5.5 | $0.00015 | $0.02802 |
| Sonnet 5.5 | $0.00007 | $0.01401 |
| Haiku 4.5 | $0.00004 | $0.00701 |
Grade A, and why
walkeros-using-step-examples 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 15d 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 — 741 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Step Examples
Overview
Step examples are structured { in, out } pairs (with optional mapping for
destinations) that define the expected input/output behavior of each step in a
flow. They serve as:
- Test fixtures for automated
it.eachtesting - Simulation input for
walkeros push --simulate(pass an example'sinas--event; the CLI does not compare the result againstout) - MCP context for AI-assisted development
- Documentation showing real-world usage
Every source, transformer, and destination can ship step examples alongside its code.
The Three Type Zones
Each step in a flow sits at a boundary between arbitrary external formats and the walkerOS event model:
Source Transformer Destination
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ in: arbitrary │ │ in: walkerOS │ │ in: walkerOS │
│ (HTTP req, DOM) │ │ Event │ │ Event │
│ │ │ │ │ │ │ │ │
│ ▼ │ │ ▼ │ │ ▼ │
│ out: walkerOS │ │ out: walkerOS │ │ out: arbitrary │
│ Event │ │ Event | false │ │ (gtag, API) │
└─────────────────┘ └─────────────────┘ └─────────────────┘
arbitrary ──────────── walkerOS.Event ──────────── arbitrary
- Source converts platform-specific input into a walkerOS event
- Transformer receives and returns walkerOS events (or
falseto filter) - Destination converts a walkerOS event into vendor-specific output
The in/out/trigger Format
Every step example is an object with in (input), out (array of observable
effects), and optional trigger (how to invoke):
type StepEffect = readonly [callable: string, ...args: unknown[]];
type StepOut = readonly StepEffect[];
interface StepExample {
in: unknown; // Platform-specific input
out: StepOut; // Array of effect tuples - see shape rules below
trigger?: { type?: string; options?: unknown }; // How to invoke
mapping?: unknown; // Destination mapping rule
command?: 'config' | 'consent' | 'user' | 'run'; // Route to walker command
}
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.
- 15d ago Changed · +27 lines d7aa976a4a82
- 17d ago Changed · +49 lines 8ea206c653fa
- 23d ago Changed · +76 lines abcaf0244714
- 24d ago Changed · +20 lines c50ffc38f564
- 1mo ago First seen · 569 lines · 37 tokens per session scan A d0f445291887
walkeros-using-step-examples is a skill published in the GitHub repository elbwalker/walkerOS (348 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 7,006 once invoked, about $0.0001 per session on Opus 5.5. 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
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
fixing-flaky-tests
Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but passes on rerun or locally, when hogli ci:insights or the debugging-ci-failures skill classifies a failure as a flaky test, when given a GitHub Actions URL for a…
qa-frontend
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence, or to make a feature reel (see reel mode…
writing-tests
Gates whether a new test should exist and forces it to be efficient, protecting CI from low-value test bloat. Use before any change to what a pytest, Jest, or Playwright test asserts or sets up, down to one fixture or one assertion added to an existing block. Front-loads the value bar (every test must catch a…
creating-online-evaluations
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these…
auditing-warehouse-source-coverage
Audit already-implemented Data warehouse import sources for endpoints, schemas, and tables the vendor's API offers but we never wired up. Use when asked whether a source is missing endpoints, to find new endpoints a vendor has added since a source was built, to refresh COVERAGEGAPS.md, to prioritize which source to…