Headlong is a Bash-based agent microharness for running language-model agents in persistent, self-directed loops. People use it to create agents that maintain ongoing interests and projects, interact through shell commands, and share one stream of conversations across a team and chat services.
Borrowing it
Nothing to install: this file belongs to laude-institute/headlong. 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/laude-institute/headlong/main/AGENTS.mdgit clone --depth 1 https://github.com/laude-institute/headlongWrote 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/laude-institute/headlong/agents-md)<a href="https://agentmods.dev/instructions/laude-institute/headlong/agents-md"><img src="https://agentmods.dev/badge/instructions/laude-institute/headlong/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/laude-institute/headlong/agents-md"><img src="https://agentmods.dev/badge/instructions/laude-institute/headlong/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 | $0.01516 | $0.01516 |
| Opus 5.5 | $0.00606 | $0.00606 |
| Sonnet 5.5 | $0.00303 | $0.00303 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade C, and why
headlong AGENTS.md scanned grade C with 2 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 16d 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.
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 -fsSL https://headlong.ai/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://headlong.ai/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Headlong as a coding agent
This file is for coding agents (Claude Code, Cursor, and similar). It covers installing Headlong without a tty, checking that it is healthy, and the sharp edges that are not obvious from the code.
Before you change or review code in this repository, read CHARTER.md. It holds the maintainers' standing rules on architecture, security, and quality, and every change is checked against it.
Naming: Headlong is the agent framework — identities, thinkers, the
mind log, bridges, the dash. shellm is one tool inside it: the
CLI implementation of Recursive Language Models in bash (bin/shellm),
plus its run machinery (shellm-docker, shellm-explore). Use "Headlong"
for the system and "shellm" only for that tool. Framework commands are
headlong-* (headlong-init, headlong-web, ...; the old shellm-* names
remain as symlinks) and framework env vars are HEADLONG_* (legacy
SHELLM_* spellings still honored). The state home defaults to
~/.headlong, falling back to ~/.shellm when only that exists (so
pre-rename installs keep their state); explicit HEADLONG_HOME or
SHELLM_HOME overrides both. Systemd units are headlong-*; a box provisioned before
the rename is migrated once with deploy/migrate-units.sh (see
deploy/DEPLOY.md). What deliberately keeps the shellm name: the
/opt/shellm deploy path, the shellm and shellm-telegram UNIX users,
~shellm/.shellm, the per-identity .shellm/ subdirectory, the
~/.headlong-thinkers template dir that install.sh seeds, and the
*.shellm.net domains. If you take one of those on, or any other
structural change to a live box, read deploy/MIGRATIONS.md first — it
lists the couplings that fail silently.
Headlong creates a persistent identity whose mind is a loop of LLM calls
run by a dispatcher. The identity has a name (default ada), and that
name becomes a shell command. A local web dashboard shows the mind's
trajectory.
Install without a tty
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.
- 16d ago Changed · +5 lines · +49 tokens per session 964a008af469
- 1mo ago First seen · 116 lines · 1,467 tokens per session scan C cb88981be5d1
headlong AGENTS.md is an instructions file published in the GitHub repository laude-institute/headlong (1,227 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,516 tokens to every session, about $0.0061 per session on Opus 5.5. A static security scan graded it C with 2 findings (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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).