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/elbwalker/walkeros/walkeros-create-sourcenpx skills add elbwalker/walkerOS --skill walkeros-create-sourcegit clone --depth 1 https://github.com/elbwalker/walkerOSWhat 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 | $0.00065 | $0.07823 |
| Opus 5 | $0.00032 | $0.03911 |
| Sonnet 5 | $0.00013 | $0.01565 |
| Haiku 4.5 | $0.00006 | $0.00782 |
Grade A, and why
walkeros-create-source 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 — 904 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a New Source
Prerequisites
Before starting, read these skills:
- understanding-flow - How sources fit in architecture
- understanding-sources - Source interface
- understanding-transformers - Transformer chaining from sources
- understanding-events - Event structure sources emit
- understanding-mapping - Transform raw input to events
- testing-strategy - How to test with env pattern and dev examples
- using-step-examples -
Authoritative
Flow.StepExamplepattern,createTrigger, Three Type Zones - using-logger - For an HTTP source, see
"Choosing a level on public endpoints": rejected client input is debug or warn
plus a
rejectedcounter and a 4xx, never an error-level log - writing-documentation - Documentation standards (for Phase 9)
Source Types
A source's identity is split into two fields:
| Field | Meaning | Examples |
|---|---|---|
source.type |
The kind of source (its role / mechanism) | browser, dataLayer, cookiefirst, fetch |
source.platform |
The runtime that hosts the source (web, server, app, ...) |
web, server |
| Platform | Input | Example types |
|---|---|---|
web |
DOM events, dataLayer | browser, dataLayer |
server |
HTTP requests, webhooks | gcp, express, lambda, fetch |
What ships with it
11 files 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.
- examples/index.ts 251 B runs code
- examples/inputs.ts 1.0 KB runs code
- examples/mapping.ts 1.1 KB runs code
- examples/outputs.ts 833 B runs code
- examples/requests.ts 669 B runs code
- templates/server/dev.ts 206 B runs code
- templates/server/index.test.ts 4.2 KB runs code
- templates/server/index.ts 3.5 KB runs code
- templates/server/schemas.ts 543 B runs code
- templates/server/types.ts 465 B runs code
- TESTING.md 1.7 KB
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 · 904 lines · 65 tokens per session scan A dec1cadec6d0
walkeros-create-source is a skill published in the GitHub repository elbwalker/walkerOS (343 stars, last pushed 7d ago), licensed MIT. It adds 65 tokens to every session and 7,823 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 2026-08-30.
Other skills, from other repositories
task-management
Task management CLI for tracking and managing feature subtasks with status, dependencies, and validation.
content-enrich
内容加工：给任意采集产物（转录稿 / 文章 / 笔记）自动补「摘要 + 要点 + 标签 + 价值判断」， 写进 frontmatter 并在正文顶部插入摘要块。是「加工层」通用能力，惠及仓库所有采集 skill。.
ab-test-generator
Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my landing page copy", "headline alternatives", "CTA variations", "which version is better", "optimize conversions"…
conversion-tracker
Set up affiliate conversion tracking with UTM parameters and link tagging. Triggers on: "set up tracking", "create UTM links", "track my affiliate links", "tracking pixels", "click attribution", "organize my links", "UTM parameters", "tag my links", "campaign tracking", "link tracking setup", "prepare for launch"…
internal-linking-optimizer
Analyze site's internal link structure and optimize for hub-and-spoke SEO architecture. Triggers on: "optimize internal links", "internal linking", "link structure", "hub and spoke links", "orphan pages", "link equity", "internal link audit", "fix my internal links", "link architecture", "site structure optimization"…
performance-report
Generate affiliate performance reports with KPIs and recommendations. Triggers on: "show my affiliate report", "how are my programs doing", "performance review", "earnings report", "monthly affiliate report", "weekly report", "analyze my affiliate earnings", "which program is best", "EPC report", "conversion rate…