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/slhaf/agenticgpt/agents-mdgit clone --depth 1 https://github.com/slhaf/AgenticGPTWrote 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/slhaf/agenticgpt/agents-md)<a href="https://agentmods.dev/instructions/slhaf/agenticgpt/agents-md"><img src="https://agentmods.dev/badge/instructions/slhaf/agenticgpt/agents-md.svg" alt="Measured on agentmods" 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 | $0.00689 | $0.00689 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
AgenticGPT 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
The root Cargo workspace contains three Rust crates: crates/agentic-gpt (Linux local-agent CLI), crates/agentic-gpt-hub (HTTP/WebSocket hub), and crates/agentic-gpt-protocol (shared wire types). API contracts live in openapi/; operational and development notes are in docs/; release helpers are in scripts/.
console/ is a separate Kotlin Multiplatform/Compose project. Shared UI and domain code belongs in console/shared/src/commonMain; platform integrations belong in androidMain, jvmMain, jsMain, or wasmJsMain. Host applications live in androidApp, desktopApp, and webApp. Keep generated output (target/, console/build/, dist/) out of commits.
Build, Test, and Development Commands
cargo check --workspace: type-check all Rust crates quickly.cargo test --workspace: run the full Rust test suite.cargo fmt --all -- --check: enforce CI formatting.cargo run -p agentic-gpt-hub -- init: initialize a development hub.cargo run -p agentic-gpt -- run: launch the local agent.cd console && ./gradlew :desktopApp:run: run the desktop console.cd console && ./gradlew :shared:jvmTest: run shared JVM tests. Android, JS, and Wasm tasks are listed inconsole/README.md../scripts/dist-linux.sh: create multi-architecture Linux release artifacts usingcross.
Coding Style & Naming Conventions
Use rustfmt defaults and idiomatic Rust naming: snake_case functions/modules, PascalCase types, and SCREAMING_SNAKE_CASE constants. Preserve camelCase JSON contracts through explicit Serde attributes. Kotlin uses four-space indentation, PascalCase types/composables, camelCase members, and lowercase package names under work.slhaf.agentic.console. Prefer shared code over duplicated platform implementations.
Testing Guidelines
Place Rust unit tests beside implementation code in #[cfg(test)] modules; use #[tokio::test] for async behavior. Kotlin tests belong in the matching source set, such as commonTest or jvmTest, and test classes should end in Test. Add regression tests for bug fixes. No numeric coverage threshold is configured; prioritize policy, protocol, persistence, and transport edge cases.
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 · 35 lines · 689 tokens per session scan A cd20dcb08f98
AgenticGPT AGENTS.md is an instructions file published in the GitHub repository slhaf/AgenticGPT (5 stars, last pushed 8d ago), licensed MIT. It adds 689 tokens to every session, about $0.0034 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 instructions, from other repositories
Pake AGENTS.md
AGENTS.md instructions for tw93/Pake, covering agents.md - pake project knowledge base, project identity, repository structure, development commands and code conventions.
chat-on-steroids AGENTS.md
Instructions for totec448-spec/chat-on-steroids, covering chat on steroids — the agent map, 1. the app in sixty seconds, 2. where the bugs actually are, name the identity, then find where it is lost and 3. what is authoritative.
Pake copilot-instructions.md
Copilot instructions for tw93/Pake, a project described as: 🤱🏻 Turn any webpage into a desktop app with one command.
Pake CLAUDE.md
Claude Code instructions for tw93/Pake, a project described as: 🤱🏻 Turn any webpage into a desktop app with one command.
chat-on-steroids CLAUDE.md
Instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
webcodex AGENTS.md
Instructions for yyjeqhc/webcodex, covering agents.md — webcodex repository guide, v1 active development, 1. verify and preserve, 2. build the simplest useful product and 3. follow intent and make focused changes.