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/rkawaishi/workato-dev-kit/learn-patternnpx skills add rkawaishi/workato-dev-kit --skill learn-patterngit clone --depth 1 https://github.com/rkawaishi/workato-dev-kitWhat 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 | $0.00038 | $0.01298 |
| Opus 5 | $0.00019 | $0.00649 |
| Sonnet 5 | $0.00008 | $0.00260 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
learn-pattern 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn-pattern
A Workato expert records construction patterns into org/docs/patterns/recipe-patterns/.
The goal is to document know-how the expert already has. A reference recipe can be supplied as optional source material.
The write target is a single location in the org knowledge layer (the kit submodule's docs/ is left alone). See @.claude/rules/org-knowledge-overlay.md.
Usage
/learn-pattern— start recording a pattern (interactive)/learn-pattern "Pagination loop"— specify the pattern name/learn-pattern "Approval workflow" "additional caveats"— append to an existing pattern/learn-pattern <file-path>— supply a recipe as reference material (the pattern itself is decided interactively)
Procedure
1. Confirm the expert's intent
First survey existing patterns (read kit canonical and org sides; org wins on conflicts):
docs/patterns/recipe-patterns/_index.md— kit canonical, generic patterns.org/docs/patterns/recipe-patterns/_index.md— org-recorded patterns (if present).projects/docs/patterns/_index.md— legacy org-domain patterns (if present; read-only for backwards compatibility).
Ask the user what they want to record:
What are we recording?
A. A new pattern (e.g. pagination loop, batch processing, etc.)
B. An addition to an existing pattern (caveats, variations, etc.)
Existing patterns:
- org/docs/patterns/recipe-patterns/: <list pattern names>
- (legacy) projects/docs/patterns/: <list pattern names if any>
Skip this question and proceed when the argument already makes the name / intent clear.
2. Interview the pattern
Ask the expert for the key points. You don't need to ask everything — build the structure from what they say:
- When is it used — what kind of requirement makes you reach for this composition?
- Composition highlights — which steps go where?
- Why this composition — why pick this over alternatives?
- Gotchas — pitfalls you only learn the hard way.
If a reference recipe is supplied, read the .recipe.json and summarize its structure for the expert. Use it to make the pattern concrete by cross-referencing the expert's description.
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 · 163 lines · 38 tokens per session scan A f7b9371de001
learn-pattern is a skill published in the GitHub repository rkawaishi/workato-dev-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 1,298 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 2026-08-31.
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…