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-understanding-transformersnpx skills add elbwalker/walkerOS --skill walkeros-understanding-transformersgit clone --depth 1 https://github.com/elbwalker/walkerOSWrote 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-understanding-transformers)<a href="https://agentmods.dev/skills/elbwalker/walkeros/walkeros-understanding-transformers"><img src="https://agentmods.dev/badge/skills/elbwalker/walkeros/walkeros-understanding-transformers.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.03698 |
| Opus 5 | $0.00019 | $0.01849 |
| Sonnet 5 | $0.00008 | $0.00740 |
| Haiku 4.5 | $0.00004 | $0.00370 |
Grade A, and why
walkeros-understanding-transformers 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 5d 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 — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Understanding walkerOS Transformers
Overview
Transformers are middleware for validating, enriching, and redacting events in the walkerOS pipeline. They run in chains at configurable points between sources, collector, and destinations.
Core principle: Transformers transform events. They don't capture (sources) or deliver (destinations)—they modify events in-flight.
Use Cases
| Use Case | Purpose | Example |
|---|---|---|
| Validate | Ensure events match schema contracts | JSON Schema validation |
| Enrich | Add server-side data to events | User segments, geo data |
| Redact | Remove sensitive data before destinations | Strip PII, anonymize IPs |
Available Packages
| Package | Env | Purpose |
|---|---|---|
@walkeros/transformer-validate |
both | Enforce JSON Schema contracts on events at runtime |
@walkeros/transformer-ga4 |
server | Decode GA4 Measurement Protocol hits into events |
@walkeros/server-transformer-bot |
server | Annotate an automation score and client category |
@walkeros/server-transformer-fingerprint |
server | Derive a stable visitor fingerprint |
Contract validation
@walkeros/transformer-validate is the runtime arm of a
contract. Event shapes
live in the top-level contract block; the transformer references one via
$contract.<name> in its contract setting and validates the canonical event.
mode: "strict" drops invalid events (chain-stop); mode: "pass" (default)
annotates event.source.valid and continues so a downstream step can route on
the verdict. format: true additionally checks the canonical WalkerOS.Event
structure. Filtering is the same mechanism: an inline schema that rejects the
unwanted events plus mode: "strict", there is no separate ignore field. See
Website: Validate transformer.
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.
- 5d ago First seen · 489 lines · 39 tokens per session scan A 443928f595cd
walkeros-understanding-transformers is a skill published in the GitHub repository elbwalker/walkerOS (343 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 3,698 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 2026-08-30.
Other skills, from other repositories
task-management
Task management CLI for tracking and managing feature subtasks with status, dependencies, and validation.
meter-off
Disable CocoMeter token tracking. Finalizes the current session record and appends to history. Does not delete history — just stops active tracking.
meter-on
Enable CocoMeter token and credit tracking for this session. Creates tracking state in .cocoplus/meter/ and activates per-tool token capture via post-tool-use hook.
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
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。.
issue-progress-tracking
GitHub issue workflow ceremony using gh CLI — labels issues as in-progress, creates feature branches (issue/N-description), commits with issue references, posts progress comments, and links PRs with Closes #N. Keeps issues in sync with development work. Use when starting work on an issue, tracking progress, or…