Borrowing it
Nothing to install: this file belongs to elsoul/erpc-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/elsoul/erpc-sdk/main/AGENTS.mdgit clone --depth 1 https://github.com/elsoul/erpc-sdkWrote 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/instructions/elsoul/erpc-sdk/agents-md)<a href="https://agentmods.dev/instructions/elsoul/erpc-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/elsoul/erpc-sdk/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/elsoul/erpc-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/elsoul/erpc-sdk/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00499 | $0.00499 |
| Opus 5 | $0.00249 | $0.00249 |
| Sonnet 5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
erpc-sdk 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 yesterday.
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 — 18 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex project agents
This project uses the canonical registry at .codex/agent-registry.json. Load only the selected persona profile in .codex/agents; never load the full roster.
Work routing
Planning selects L1 and L2 contributors and attaches non-author gates; never dispatch L3. Implementation requires an L1-approved Task Brief naming exact owned files and acceptance criteria, then an independent gate; an author cannot self-review. Path and category routing, fallback behavior, and cross-domain Cyan gates are defined in the registry. Future assets/** and registry/** are proposed directories.
Use the current tree and branch. The active session allows at most 3 concurrent child threads, excluding the root task (4 total tasks). Pass the selected profile's explicit model and reasoning effort when spawning a fresh bounded process; a task name alone does not load a persona.
Product guardrails
Five languages consume common data. Swap quotes/routes/build use configured RPC and local logic; no hosted Jupiter/0x dependencies. Weekly release is future work; current scripts remain human-approved. Bridging is separate research requiring exact chains, native versus wrapped addresses, proof/attestation, and relayer dependencies. No role grants push, tag, publish, live-funds, or secret authority; current or future explicit user authorization remains authoritative. An L1 approval in the Task Brief is required before L3 work; metadata is structural preflight, not proof of authorization. License, dependency, SBOM, security, and release-readiness work involves eu-oss-compliance and reads .codex/docs/eu-oss-compliance.md; review packets state applicability status, primary source and as-of date, evidence, gaps, owner, due date, and next review. EU OSS packets are planning evidence only: no self-issued legal compliance or CE certification and no standing authority for regulatory filings, public vulnerability disclosure, or live effects; honor explicit user authorization.
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.
- yesterday First seen · 18 lines · 499 tokens per session scan A 34b72e38dd01
erpc-sdk AGENTS.md is an instructions file published in the GitHub repository elsoul/erpc-sdk (2 stars, last pushed yesterday), licensed MIT. It adds 499 tokens to every session, about $0.0025 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 2026-09-16.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).