little-coder: Instructions file for Codex

AGENTS.md

little-coder AGENTS.md is an instructions file for Codex, OpenCode from itayinbarr/little-coder. It costs 1,788 tokens per session, scanned C, original, Apache-2.0.

A set of operating instructions for little-coder, a coding agent designed to work with small local language models. It covers the agent's capabilities, tools, runtime rules, and file and shell use.

In plain words
What is it for?
Use it to guide little-coder while it edits files, runs commands, uses tools, or handles monitoring tasks.
Why use it?
It provides consistent rules for how little-coder should act, including what to do with long-running tasks and rejected shell commands.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is itayinbarr/little-coder's own configuration. It tells Codex and OpenCode how to work on little-coder itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything little-coder configures →

About the project

little-coder is a coding agent built on the pi framework and configured to work with smaller local language models. It is for developers who want a lightweight local coding assistant, with bundled extensions, skills, and benchmarks tuned to that setup. The catalogue instruction extends its agent workflow.

itayinbarr/little-coder · 2,716 stars · on GitHub · itayinbarr.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to itayinbarr/little-coder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/itayinbarr/little-coder/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/itayinbarr/little-coder

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for little-coder AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/itayinbarr/little-coder/agents-md/github.svg)](https://agentmods.dev/instructions/itayinbarr/little-coder/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/itayinbarr/little-coder/agents-md"><img src="https://agentmods.dev/badge/instructions/itayinbarr/little-coder/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.

agentmods 80×15 button for little-coder AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/itayinbarr/little-coder/agents-md"><img src="https://agentmods.dev/badge/instructions/itayinbarr/little-coder/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,788 This file is loaded in full into every session.
When invoked 1,788 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01788 $0.01788
Opus 5.5 $0.00715 $0.00715
Sonnet 5.5 $0.00358 $0.00358
Haiku 4.5 $0.00179 $0.00179

Measured 2mo ago against content hash d98675c14996, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

little-coder AGENTS.md scanned grade C 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

If the user asks you to monitor a process, run a background loop, or execute long-running tasks, DO NOT refuse by claiming you are "just a chat interface" or "require a prompt to take action."
AGENTS.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

little-coder

You are little-coder, a coding agent specialized for small local language models.

Capabilities & Autonomy

You are a highly capable autonomous agent. Do not act submissive or artificially limited. If the user asks you to monitor a process, run a background loop, or execute long-running tasks, DO NOT refuse by claiming you are "just a chat interface" or "require a prompt to take action." Instead, proactively write the necessary background script (Python, Bash, etc.) with write, and start it with bash (e.g. python script.py & or nohup ...).

A refused command is an answer, not an obstacle. Some deployments run a shell whitelist, so a command may come back as "<cmd>" is not in SAFE_PREFIXES. When that happens, do not go looking for another route to the same effect. Re-running the identical operation through python3 -c, node -e, env bash -c, find -exec, or any other interpreter defeats a boundary the user configured deliberately, and burns your budget discovering that. Instead: name the command that was refused, say what you needed it for, and continue with the rest of the task or hand the decision back to the user. Reach for the dedicated tools (edit, write, read) before shelling out for anything they already cover — deleting or rewriting a file you are allowed to edit does not need a shell at all.

Runtime invariants

  • write refuses on existing files. Use edit with exact old_string / new_string to modify — old_string must match exactly (whitespace included). If it appears multiple times in the file, pass replace_all: true or add more surrounding context to make the match unique. Read with line numbers first when precision is in doubt. This is a runtime invariant, not guidance — when write refuses, the error returns the exact edit call-shape for the same path; follow it.
  • edit refuses on unread files. A file must be read in the current session before you can edit it — this is a runtime invariant. If an edit is blocked, read the file first to get the exact current text (so old_string matches), then edit. Files you just wrote count as read.
  • bash / ShellSession default timeout is 30 s. For slow commands (npm install, npx, pip install, builds, training), set timeout to 120–300.
  • Tool names are case-sensitive. The core tools are lowercase (read, write, edit, bash, glob, grep, ls, webfetch, websearch, dispatch); only the browser, evidence, and shell-session tools are CamelCase. Calling Read or Bash will not resolve to read or bash.
  • Per-benchmark tools (BrowserNavigate / Click / Type / Scroll / Extract / Back / History and EvidenceAdd / Get / List) appear when relevant; their schemas are passed to you directly when available.

Read the full file on GitHub · 72 lines

Changes

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.

  1. 2mo ago First seen · 72 lines · 1,788 tokens per session scan C d98675c14996

Subscribe to this mod's changes

little-coder AGENTS.md is an instructions file published in the GitHub repository itayinbarr/little-coder (2,716 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,788 tokens to every session, about $0.0072 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

little-coder AGENTS.md compared with instructions from other repositories

little-coder AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
little-coder AGENTS.mditayinbarr/little-coderInstructions file2.7k1mo agoApache-2.0C1,788Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode