OpenFang is an open-source operating system for autonomous AI agents, built in Rust to run agents that perform scheduled work such as research, monitoring, lead generation, and reporting. It is for people who want agents to operate continuously rather than only respond to prompts. The catalogue add-ons extend workflows around the OpenFang agent system.
Borrowing it
Nothing to install: this file belongs to RightNow-AI/openfang. 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/RightNow-AI/openfang/main/CLAUDE.mdgit clone --depth 1 https://github.com/RightNow-AI/openfangWrote 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/rightnow-ai/openfang/claude-md)<a href="https://agentmods.dev/instructions/rightnow-ai/openfang/claude-md"><img src="https://agentmods.dev/badge/instructions/rightnow-ai/openfang/claude-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/rightnow-ai/openfang/claude-md"><img src="https://agentmods.dev/badge/instructions/rightnow-ai/openfang/claude-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 | $0.01399 | $0.01399 |
| Opus 5.5 | $0.00560 | $0.00560 |
| Sonnet 5.5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade D, and why
openfang CLAUDE.md scanned grade D with 3 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 2mo 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X PUT http://127.0.0.1:4200/api/<endpoint> -d '...' Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://127.0.0.1:4200/api/agents | python3 -c "import sys,json; print(json.load(sys.stdin)[0]['id'])" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:4200/api/health # Verify it's up How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenFang — Agent Instructions
Project Overview
OpenFang is an open-source Agent Operating System written in Rust (14 crates).
- Config:
~/.openfang/config.toml - Default API:
http://127.0.0.1:4200 - CLI binary:
target/release/openfang.exe(ortarget/debug/openfang.exe)
Build & Verify Workflow
After every feature implementation, run ALL THREE checks:
cargo build --workspace --lib # Must compile (use --lib if exe is locked)
cargo test --workspace # All tests must pass (currently 1744+)
cargo clippy --workspace --all-targets -- -D warnings # Zero warnings
MANDATORY: Live Integration Testing
After implementing any new endpoint, feature, or wiring change, you MUST run live integration tests. Unit tests alone are not enough — they can pass while the feature is actually dead code. Live tests catch:
- Missing route registrations in server.rs
- Config fields not being deserialized from TOML
- Type mismatches between kernel and API layers
- Endpoints that compile but return wrong/empty data
How to Run Live Integration Tests
Step 1: Stop any running daemon
tasklist | grep -i openfang
taskkill //PID <pid> //F
# Wait 2-3 seconds for port to release
sleep 3
Step 2: Build fresh release binary
cargo build --release -p openfang-cli
Step 3: Start daemon with required API keys
GROQ_API_KEY=<key> target/release/openfang.exe start &
sleep 6 # Wait for full boot
curl -s http://127.0.0.1:4200/api/health # Verify it's up
The daemon command is start (not daemon).
Step 4: Test every new endpoint
# GET endpoints — verify they return real data, not empty/null
curl -s http://127.0.0.1:4200/api/<new-endpoint>
# POST/PUT endpoints — send real payloads
curl -s -X POST http://127.0.0.1:4200/api/<endpoint> \
-H "Content-Type: application/json" \
-d '{"field": "value"}'
# Verify write endpoints persist — read back after writing
curl -s -X PUT http://127.0.0.1:4200/api/<endpoint> -d '...'
curl -s http://127.0.0.1:4200/api/<endpoint> # Should reflect the update
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.
- 2mo ago First seen · 124 lines · 1,399 tokens per session scan D 2783c2ca5584
openfang CLAUDE.md is an instructions file published in the GitHub repository RightNow-AI/openfang (18,243 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,399 tokens to every session, about $0.0056 per session on Opus 5.5. A static security scan graded it D with 3 findings (sends data to an external url, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
openfang CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| openfang CLAUDE.mdRightNow-AI/openfang | Instructions file | 18k | 4mo ago | Apache-2.0 | D | 1,399 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |