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/clubpay/ronykit/agents-mdgit clone --depth 1 https://github.com/clubpay/ronykitWhat 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 | $0.02107 | $0.02107 |
| Opus 5 | $0.01053 | $0.01053 |
| Sonnet 5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
ronykit 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 3d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Practical instructions for coding agents and contributors working in this repository.
Last verified: 2026-08-12 — every
maketarget, path, and link in this file was checked against the tree at that commit.
- Stack: Go 1.25+ multi-module workspace (
go.work). No other language runtime is needed to build or test. - Scope: entire repository rooted at this directory.
- Default approach: prefer minimal, targeted changes over broad refactors.
- Local env: copy
.env.exampleto.env(gitignored) for the optionalOLLAMA_*/OPENAI_*/ integration-test variables.
AI assistants
- MCP:
ronyup mcp(see.cursor/mcp.json) — knowledge resources and scaffold tools. - Skill:
.agents/skills/ronykit-framework/(Agent Skills layout; Cursor discovers it automatically) — invoke/ronykit-frameworkfor orchestration; conventions live in MCP, not in the skill body. MCP index:references/mcp-map.mdunder that directory. - Path rules:
.cursor/rules/*.mdccarryglobs:frontmatter and load automatically when you editkit/,rony/,intent/,std/,x/,ronyup/, or.agents/skills/. They hold the per-area detail that used to sit in this file — put new area-specific guidance there, not here. - Exclusions:
.cursorignorekeeps secrets and vendored bulk out of reach. Add new secret paths there, not only to.gitignore.
For scaffolded application workspaces (outside this monorepo), MCP knowledge and tools are the source of truth for service layout and handler conventions.
Context map
Context is layered: this file, plus whichever path rule matches your edit, is all that loads automatically. Everything else is opened deliberately — do not read it all up front.
| When you are… | Open |
|---|---|
editing kit/, rony/, intent/, std/, x/, ronyup/, .agents/skills/ |
nothing — the matching path rule loads itself |
| scaffolding a workspace, service, or feature | the ronykit-framework skill, then ronyup mcp resources |
| needing the request flow, key abstractions, or deeper architecture | docs/architecture.md, docs/knowledge-architecture.md, docs/advanced-kit.md |
| changing agent behavior | intent/README.md, intent/DESIGN.md |
| looking for the API contract or schema | Contracts & schemas below |
| asked about dependency licenses | docs/compliance.md — never open COMPLIANCE.md, a 529 KB generated FOSSA export |
| working near the embedded API-doc UI | never open x/apidoc/internal/swagger-ui/ or x/apidoc/internal/redoc-ui/ (vendored minified bundles) |
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.
- 3d ago First seen · 154 lines · 2,107 tokens per session scan A 699e6603462e
ronykit AGENTS.md is an instructions file published in the GitHub repository clubpay/ronykit (38 stars, last pushed 5d ago), licensed BSD-3-Clause. It adds 2,107 tokens to every session, about $0.0105 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
prest copilot-instructions.md
Instructions for prest/prest, covering copilot instructions for prest go backend, project scope, core engineering principles, solid principles for go and s — single responsibility.
gorest AGENTS.md
Instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
symfony-flex-backend CLAUDE.md
Instructions for tarlepp/symfony-flex-backend, covering what is this?, table of contents ᐞ, ai documentation map ᐞ, version sources of truth ᐞ and project architecture ᐞ.
python-samples-fastapi-restful CLAUDE.md
Instructions for nanotaboada/python-samples-fastapi-restful, covering claude.md, claude code, tech stack, structure and coding guidelines.
symfony-flex-backend copilot-instructions.md
Instructions for tarlepp/symfony-flex-backend, covering what is this?, table of contents ᐞ, purpose ᐞ, architecture rules ᐞ and php and symfony rules ᐞ.
unraid-management-agent copilot-instructions.md
Instructions for ruaan-deysel/unraid-management-agent, covering copilot instructions, copilot workflow, path-specific instructions, reusable prompts and quick commands.