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/ohadassulin/headless-coder-sdk/claude-mdgit clone --depth 1 https://github.com/OhadAssulin/headless-coder-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/ohadassulin/headless-coder-sdk/claude-md)<a href="https://agentmods.dev/instructions/ohadassulin/headless-coder-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/ohadassulin/headless-coder-sdk/claude-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 | $0.01313 | $0.01313 |
| Opus 5 | $0.00656 | $0.00656 |
| Sonnet 5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
headless-coder-sdk CLAUDE.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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
This is a monorepo for the headless-coder-sdk - a unified TypeScript SDK that provides a consistent interface for multiple headless AI coders (Codex, Claude, Gemini). It uses pnpm workspaces and is published as separate npm packages under the @headless-coder-sdk/* scope.
The SDK standardizes threads, streaming, structured outputs, permissions, and sandboxing across different AI coder backends, allowing seamless switching with a single line of code.
Build & Development Commands
Install dependencies:
pnpm install
Build all packages:
pnpm build
# Internally runs: node ./scripts/run-workspaces.mjs build
Lint:
pnpm lint
Test all packages:
pnpm test
# Internally runs: node ./scripts/run-workspaces.mjs test
Run smoke tests:
pnpm smoke
# Set HEADLESS_CODER_KEEP_SMOKE_TMP=1 to keep temp project for inspection
Work with specific packages:
# Build a single package
pnpm --filter @headless-coder-sdk/core build
Run examples:
pnpm --filter @headless-coder-sdk/examples-tests test
Architecture
Core Design Pattern
The SDK uses an adapter pattern with a central registry to provide unified access to different AI coder backends:
@headless-coder-sdk/core- Defines shared types (HeadlessCoder,ThreadHandle,CoderStreamEvent) and the adapter registry (factory.ts)- Adapter packages - Each adapter (codex, claude, gemini) implements the
HeadlessCoderinterface and exports:CODER_NAME- unique provider identifier constantcreateAdapter()- factory function withcoderNameproperty for auto-registrationcreateHeadless*()- convenience helper that registers and returns coder in one call
Key Interfaces (packages/core/src/types.ts)
HeadlessCoder- Main interface withstartThread(),resumeThread(),getThreadId(),close()ThreadHandle- Returned by startThread/resumeThread, hasrun()andrunStreamed()methodsCoderStreamEvent- Unified event types:init,message,tool_use,tool_result,progress,permission,file_change,plan_update,usage,error,cancelled,doneRunResult- ContainsthreadId,text,json,usage,raw
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.
- 5d ago First seen · 138 lines · 1,313 tokens per session scan A d65dc3534eca
headless-coder-sdk CLAUDE.md is an instructions file published in the GitHub repository OhadAssulin/headless-coder-sdk (38 stars, last pushed 2mo ago), licensed MIT. It adds 1,313 tokens to every session, about $0.0066 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
cli-continues typescript.instructions.md
Instructions for yigitkonur/cli-continues, covering typescript review guidelines, type safety, discriminated unions, async patterns and import rules.
typescript AGENTS.md
AGENTS.md instructions for typeship-ax/typescript, covering typeship — agent context, ground rules, authentication, using the sdk and documentation.
eai-gofer typescript.instructions.md
Instructions for eai-support/eai-gofer, covering typescript development instructions, code quality standards, file structure and testing.
aptos-ts-sdk CLAUDE.md
Claude Code instructions for aptos-labs/aptos-ts-sdk, covering claude.md, project overview, runtime compatibility, common commands and commit guidelines.
aptos-ts-sdk AGENTS.md
AGENTS.md instructions for aptos-labs/aptos-ts-sdk, covering agents.md, project overview, runtime compatibility, requirements and repo layout.
sdk CLAUDE.md
Claude Code instructions for zama-ai/sdk, a project described as: TypeScript SDK for confidential FHE smart contracts on Zama Protocol.