sidecar AGENTS.md

A short set of coding-agent instructions for the Sidecar repository. It favors simplifying rewrites, requires explicit permission for backward compatibility, and notes that some user-facing text is embedded in an image.

In plain words
What is it for?
Making code changes in Sidecar, deciding when a rewrite is appropriate, avoiding unrequested compatibility work, and refreshing the social-preview image after changing the install command, tagline, or color palette.
Why use it?
It prevents contributors from preserving old interfaces or forgetting to refresh generated branding after changing visible product details. It also points to the skill that handles those asset updates.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/anteprojector/sidecar/agents-md
Clone the repo
git clone --depth 1 https://github.com/anteprojector/sidecar

Made for: Codex, OpenCode.

Per session 77 This file is loaded in full into every session.
When invoked 77 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00077 $0.00077
Opus 5 $0.00039 $0.00039
Sonnet 5 $0.00015 $0.00015
Haiku 4.5 $0.00008 $0.00008

Measured 2d ago against content hash 75bffb43bce1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sidecar 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 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.

AGENTS.md · 10 lines

What it actually says

Agent Instructions

Be aggressive with rewrites when they make the system simpler or more coherent.

Do not add backwards compatibility unless explicitly instructed.

Some user-facing copy is baked into images (site/assets/og.png). After changing the install command, tagline, or palette, re-render the generated assets — see .claude/skills/refresh-brand-assets/SKILL.md.

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. 2d ago First seen · 10 lines · 77 tokens per session scan A 75bffb43bce1

Subscribe to this mod's changes

sidecar AGENTS.md is an instructions file published in the GitHub repository anteprojector/sidecar (5 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session, about $0.0004 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 2026-08-31.

Related

Other instructions, from other repositories

git-worktree-runner copilot-instructions.md

Instructions for coderabbitai/git-worktree-runner, covering copilot instructions, architecture & flow, key concepts, adapter contract and manual testing (essential subset).

coderabbitai/git-worktree-runner · 1,250 tokens

git-worktree-runner completions.instructions.md

Instructions for coderabbitai/git-worktree-runner, covering completions instructions, when to update completions, file responsibilities, implementation pattern and testing completions.

coderabbitai/git-worktree-runner · 1,366 tokens

git-worktree-runner testing.instructions.md

Instructions for coderabbitai/git-worktree-runner, covering testing instructions, basic create/remove, branch sanitization, remote branch (if exists) and local existing branch.

coderabbitai/git-worktree-runner · 766 tokens

git-worktree-runner ai.instructions.md

Instructions for coderabbitai/git-worktree-runner, covering ai adapter instructions, when to use a file vs registry, adding a standard ai tool (registry), adding a custom ai tool (file override) and toolname adapter.

coderabbitai/git-worktree-runner · 491 tokens

git-worktree-runner editor.instructions.md

Instructions for coderabbitai/git-worktree-runner, covering editor adapter instructions, when to use a file vs registry, adding a standard editor (registry), adding a custom editor (file override) and editorname adapter.

coderabbitai/git-worktree-runner · 533 tokens

icloud-docker AGENTS.md

Instructions for mandarons/icloud-docker, covering icloud docker, quick reference, commands, architecture overview and key conventions.

mandarons/icloud-docker · 1,047 tokens