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 rules/rkawaishi/workato-dev-kit/org-knowledge-overlaygit 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 | $0.00003 | $0.01151 |
| Opus 5 | $0.00002 | $0.00575 |
| Sonnet 5 | $0.00001 | $0.00230 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
org-knowledge-overlay 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Org Knowledge Overlay
A convention for accumulating organization-specific knowledge separately from the kit's knowledge base (docs/).
This guarantees that updating the kit does not lose or overwrite the organization's learning.
Layout
<workspace-root>/
├── docs/ ← symlink to kit/docs/ (read-only)
│ ├── connectors/<name>.md
│ ├── logic/<topic>.md
│ ├── platform/<topic>.md
│ ├── patterns/<...>
│ └── learned-patterns.md
└── org/ ← organization knowledge. The kit never touches this.
└── docs/ ← mirrors the docs/ tree
├── connectors/<name>.md
├── logic/<topic>.md
├── platform/<topic>.md
├── patterns/<...>
└── learned-patterns.md
org/ is managed in the workspace repository (outside the kit submodule).
You may create directories under org/docs/ on demand; you do not need to pre-create empty ones.
Responsibilities
| Type of knowledge | Where it lives | Skill that writes it |
|---|---|---|
| Workato official spec and API info for every connector | docs/ (kit) |
/sync-connectors, /auto-learn |
| Field info and operational know-how for what the org actually uses | org/docs/ |
/learn-recipe, /learn-pattern |
| Corrections or addenda to kit docs | org/docs/<same-relative-path> |
Edited manually by the user |
| Org-specific connectors, logic, patterns | org/docs/<...> |
Edited manually by the user |
Do not edit the kit's docs/ directly — that would commit into the kit submodule.
If you find an error, write a correction at org/docs/<same-relative-path>.
If you later want to upstream it into the kit, open a separate PR (out of scope here).
Read convention
When a skill or recipe-creation process references @docs/<path>, it must also check the matching @org/docs/<path>:
- Read
@docs/<path>. - If
@org/docs/<path>exists, read it as well. - When the two conflict, the org version wins (org overrides kit defaults).
- Non-overlapping information from each is additive.
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 · 108 lines · 3 tokens per session scan A eb17827a4cb8
org-knowledge-overlay is a cursor rule published in the GitHub repository rkawaishi/workato-dev-kit (5 stars, last pushed 3d ago), licensed MIT. It adds 3 tokens to every session and 1,151 once invoked, about $0.0000 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.