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 instructions/lefinepro/ocawe/agents-mdgit clone --depth 1 https://github.com/lefinepro/ocaweWhat 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 | $0.00382 | $0.00382 |
| Opus 5 | $0.00191 | $0.00191 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
ocawe AGENTS.md 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.
What it actually says
Ocawe Framework Development Agent Guide
Goal
Develop and evolve Ocawe framework internals safely and consistently.
Scope
- Runtime engine and declarative workflow API
- NodeKind execution model
- Registry surface (
Ocawe::RegistryApi.node_kind,Ocawe::RegistryApi.resource) - HTTP runtime endpoints and compatibility behavior
- Type-safe schema/DSL integration
Core Rules
- Keep runtime behavior deterministic.
- Prefer additive API changes; avoid hidden implicit behavior.
- Preserve error envelope consistency for HTTP APIs.
- Keep NodeKind execution explicit and testable.
- Add/update specs with every behavior change.
- Don't use any
Architecture Focus
- Declarative runtime:
src/framework/workflows/declarative - DSL/schema:
src/framework/workflows/dsl - Registry API:
src/framework/registry/api.cr - HTTP app/endpoints:
src/framework/http
Change Checklist
- Update code and types.
- Update runtime wiring/boot paths.
- Update docs in
packages/docs/guides. - Add or adjust specs under
spec/. - Validate no stale API names remain.
Commit Instructions
- Analyze the project changes and make a commit with conventional commits format.
- Make a commit explaining why the changes were made and what's new.
- Commit only changed files, not all files, and do not add new files unless they were added manually.
API Direction
- Use
Workflow#step(type, id, ...)as the unified node entry for built-in and external nodes. - For NodeKind steps use
Workflow#step(Ocawe::NodeKind.new(...), id: ...). - Register node kinds only via
Ocawe::RegistryApi.node_kind. - Register resource handlers only via
Ocawe::RegistryApi.resource.
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 · 44 lines · 382 tokens per session scan A e26b951acc1d
ocawe AGENTS.md is an instructions file published in the GitHub repository lefinepro/ocawe (11 stars, last pushed 2d ago), licensed 0BSD. It adds 382 tokens to every session, about $0.0019 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 instructions, from other repositories
voltagent AGENTS.md
Instructions for VoltAgent/voltagent, covering voltagent, what is voltagent?, validating changes, important notes for ai agents and gotchas.
mastra AGENTS.md
AGENTS.md instructions for mastra-ai/mastra: Unless asked, don't inspect reference or modify examples. Use the most-specific AGENTS.md; for package work, read packages/ /AGENTS.md first.
mastra CLAUDE.md
Claude Code instructions for mastra-ai/mastra, a project described as: Mastra is the modern TypeScript framework for AI-powered applications and agents.
mem9 AGENTS.md
Instructions for unvulcanised-watercress762/mem9, covering what this repo is, high-level modules, commands, go server build / verify and single go test.
voltagent CLAUDE.md
Instructions for VoltAgent/voltagent, a project described as: AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework.
SelfMemory CLAUDE.md
Instructions for SelfMemory/SelfMemory, covering claude.md — selfmemory-core, commands, code style, structure and ci.