Borrowing it
Nothing to install: this file belongs to squadcodercom/squadcoder. 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/squadcodercom/squadcoder/main/AGENTS.mdgit clone --depth 1 https://github.com/squadcodercom/squadcoderWrote 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/squadcodercom/squadcoder/agents-md)<a href="https://agentmods.dev/instructions/squadcodercom/squadcoder/agents-md"><img src="https://agentmods.dev/badge/instructions/squadcodercom/squadcoder/agents-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 5.1 | $0.02006 | $0.02006 |
| Opus 5 | $0.01003 | $0.01003 |
| Sonnet 5 | $0.00401 | $0.00401 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
squadcoder AGENTS.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 3d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SquadCoder
This repo is SquadCoder — an open-source, RTL/Hebrew-first AI coding assistant, a rebranded
fork of MiMoCode (XiaomiMiMo/MiMo-Code, itself a fork of sst/opencode).
- Goal: keep pulling bug fixes/updates from MiMo/opencode (
upstream/opencoderemotes) while keeping our brand and developing our way. Isolate our diff — seedocs/FORK_STRATEGY.md. - What's ours (don't expect upstream to maintain):
.squadcoder/(config, skills, plugins),packages/squadcoder-plugin-*, and rebrand edits taggedSQUADCODER:. These aremerge=ours. - Working method: reuse before build (core → plugin/config → safe third-party → build); only i18n/RTL/branding touch core, kept small and marked.
- ⛔ BEFORE BUILDING ANY FEATURE, READ
docs/REUSE_AUDIT.md— the canonical per-feature verdict (already-in-core? safe extension to adopt? or build?). It exists so we never double-work.docs/PROJECT_STATUS.mdis the living status board (requirements, done, pending, user's notes). - Durable context lives outside the repo: the memory store at
~/.claude/projects/C--Users-raviv-OneDrive-Desktop-SquadCoder/memory/(MEMORY.mdindex) and the plan at~/.claude/plans/i-decided-to-create-compiled-corbato.md. Read them first.
Build & release (auto-rebuild rule)
- When a set of fixes is COMPLETE and requires a rebuild for the user to install, REBUILD THE PRODUCTION INSTALLER automatically (without waiting to be asked) to the canonical path:
C:\Users\raviv\OneDrive\Desktop\MuminAI\mumin\release\SquadCoder-desktop-win-x64-installer.exe - Recipe (run from
packages/desktop, prod channel). Ifseed/or.squadcoder/plugin-src/*changed, first runbun script/make-seed.tsfrom repo root:- Clear
out/+dist/first (OneDrive locks files). $env:OPENCODE_CHANNEL='prod'; bun run build$env:OPENCODE_CHANNEL='prod'; bun run package:winCopy-Item -Force packages/desktop/dist/SquadCoder-desktop-win-x64-installer.exe release/(also copy the.blockmap).
- Clear
- Renderer-only edits (packages/app components / i18n) ship via
bun run buildalone — SKIPprebuild. A.squadcoder/plugin-src/*or engine (packages/opencode) change is engine-side → runbun run prebuild(re-bundles the plugin + rebuilds the engine node bundle) BEFOREpackage:win. bun run build(electron-vite/babel+solid) is a SEPARATE pass frombun typecheck— a file can pass typecheck yet fail babel parse (e.g. a duplicate import). Always run the real build before declaring a fix shipped.- SQUADCODER: desktop release version is single-sourced from
packages/desktop/package.json(what Settings displays viaapp.getVersion()). Never hand-type a release tag — derive it. To cut a release: (1)bun script/set-version.ts <v>(writes the same version to desktop + app, anti-drift), (2) build the installer per the recipe above, (3)bun script/release-desktop.ts(derives thev<v>tag from package.json and creates/refreshes the GitHub release;--dry-runpreviews). This is separate from the opencode CLI/npm flow (script/version.ts/script/release.ts, sourced frompackages/opencode/package.json).
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.
- 3d ago First seen · 148 lines · 2,006 tokens per session scan A 0045f2ecee57
squadcoder AGENTS.md is an instructions file published in the GitHub repository squadcodercom/squadcoder (11 stars, last pushed 2mo ago), licensed MIT. It adds 2,006 tokens to every session, about $0.0100 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 2026-09-03.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.