Borrowing it
Nothing to install: this file belongs to nickna/Conduit. 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/nickna/Conduit/master/AGENTS.mdgit clone --depth 1 https://github.com/nickna/ConduitWrote 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/nickna/conduit/agents-md)<a href="https://agentmods.dev/instructions/nickna/conduit/agents-md"><img src="https://agentmods.dev/badge/instructions/nickna/conduit/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/nickna/conduit/agents-md"><img src="https://agentmods.dev/badge/instructions/nickna/conduit/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 | $0.05437 | $0.05437 |
| Opus 5.5 | $0.02175 | $0.02175 |
| Sonnet 5.5 | $0.01087 | $0.01087 |
| Haiku 4.5 | $0.00544 | $0.00544 |
Grade A, and why
Conduit AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:5002/api/virtual-keys \ How it starts
The opening of the file, as written. The whole thing — 900 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Guide
Last Updated: 2025-11-25
Comprehensive guide for building and deploying AI agents using ConduitLLM's agentic workflows and function calling capabilities.
Table of Contents
- Overview
- Agent Architecture
- Configuration
- Building Agents
- Deployment & Operations
- Examples & Templates
- Advanced Features
- Troubleshooting
- Related Documentation
Overview
What are Agents in ConduitLLM?
In ConduitLLM, agents are AI systems that can autonomously execute functions and tools to accomplish complex tasks. Unlike simple chat completions, agents can:
- Make decisions about when to call functions
- Execute multiple functions in a single workflow
- Handle dependencies between function calls
- Iterate on results until a task is complete
- Provide real-time feedback during execution
Agentic Mode vs Manual Function Calling
ConduitLLM supports two approaches to function calling:
Manual Function Calling
- Your application receives
tool_callsfrom the LLM - You decide which functions to execute and how
- You control the flow and iteration logic
- Full control but more complex implementation
Agentic Mode (Recommended for Agents)
- Conduit automatically executes requested functions
- Handles dependency detection and parallel/sequential execution
- Manages iteration limits and cost tracking
- Provides real-time streaming events for progress
- Simplifies agent development significantly
Use Cases
Agents are ideal for:
- Data analysis workflows (query databases, process results, generate reports)
- API integration (call external services, transform data, take actions)
- Content creation pipelines (research, draft, edit, publish)
- Customer service automation (lookup records, take actions, respond)
- Development assistants (read code, run tests, suggest fixes)
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 · 900 lines · 5,437 tokens per session scan A e0c2c9d312b4
Conduit AGENTS.md is an instructions file published in the GitHub repository nickna/Conduit (13 stars, last pushed 4d ago), licensed MIT. It adds 5,437 tokens to every session, about $0.0217 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Conduit AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Conduit AGENTS.mdnickna/Conduit | Instructions file | 13 | 4d ago | MIT | A | 5,437 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |