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.
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 skills add laude-institute/headlong --skill chatgit 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/skills/laude-institute/headlong/chat)<a href="https://agentmods.dev/skills/laude-institute/headlong/chat"><img src="https://agentmods.dev/badge/skills/laude-institute/headlong/chat.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00010 | $0.00824 |
| Opus 5 | $0.00005 | $0.00412 |
| Sonnet 5 | $0.00002 | $0.00165 |
| Haiku 4.5 | $0.00001 | $0.00082 |
Grade A, and why
chat 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 2d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chat — Talking to humans
I can talk to humans and other AIs. I send and receive messages by way of my trajectory. Each message is a step in my trajectory.
There is a CLI tool called chat that is used for me and others to send messages. Others can use chat send <message> to append chat messages to my trajectory. To send a message to others, I can write steps directly to my trajectory or I can use chat reply <to_name> <message>.
Trajectory step types
A step in my trajectory with "type":"message" is a message to or from me. I know who it is from and to by looking at the step's to and from fields.
A message in my trajectory to me, i.e. my name, is someone talking to me.
A message in my trajectory from me, i.e. my name, is something I already said.
Replying to humans
To send a reply, I can use chat reply <to_name>:
chat reply <to_name> <message>
This creates a message step with from set to my name and to set to the recipient.
IMPORTANT: if I use chat send it sends a message to myself, so I must NEVER use chat send to reply to somebody else. I always use chat reply.
Reviewing conversation history
chat history [N] # show last N messages (default 20)
chat history --with <name> [--since 7d] # my whole conversation with one person
chat history --with <name> -n 50 --json # same, as JSON with timestamps
chat pending # requests the responder deferred to me that I have not delivered yet
--with groups a person across every name a bridge has used for them (a
Slack user's DM and every channel thread, a phone chat name), so it is the
way to check what someone and I said before, even days ago. It reads a
small index next to my trajectory, so it is fast; chat person-key <name>
shows the stable key behind a routing name.
When to reply
I should reply when I see a message that seems directed at me or asks me a question. I keep my replies natural and conversational. I can also start a conversation if I have a reason to talk to the person, such as asking for help or sharing something relevant to them.
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.
- 2d ago Changed · +25 lines 8248abde4179
- 8d ago First seen · 40 lines · 10 tokens per session scan A c886c9088db7
chat is a skill published in the GitHub repository laude-institute/headlong (1,126 stars, last pushed 2d ago), licensed Apache-2.0. It adds 10 tokens to every session and 824 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…