sidecar AGENTS.md

Repository guidance for Sidecar, including its use of td, a command-line task tracker that keeps work context between sessions. It also defines how to write plans, review completed work, and demonstrate features.

In plain words
What is it for?
Starting and logging tasks, handing work to another session, approving completed work, writing readable plans, and demonstrating finished features.
Why use it?
It makes ongoing tasks recoverable across sessions and sets clear expectations for recording progress and reviewing changes.

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/marcus/sidecar/agents-md
Clone the repo
git clone --depth 1 https://github.com/marcus/sidecar

Made for: Codex, OpenCode.

Per session 2,978 This file is loaded in full into every session.
When invoked 2,978 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.02978 $0.02978
Opus 5 $0.01489 $0.01489
Sonnet 5 $0.00596 $0.00596
Haiku 4.5 $0.00298 $0.00298

Measured 2d ago against content hash bda4725fd78f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

sidecar 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 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- td-agent-instructions:start -->
AGENTS.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working with td

td keeps task context durable across sessions. In a new context, run td usage --new-session -q to see current work.

Use your judgment about how much tracking a task needs. For substantive work: td start <id>, record progress with td log, hand off with td handoff <id>, then td review <id>.

Closing needs a review. Say who did it (default trusted mode; delegated/strict allow only the first):

  • independent session: td approve <id> --reason "..."
  • a sub-agent: td approve <id> --reviewed-by "<who>"
  • you: td approve <id> --self-review --reason "..."

Prefer a reviewer with its own TD_CONTEXT_ID; never name one who did not review.

Run td usage or td <command> --help.

Markdown plans

When writing plans or other Markdown documents, do not insert hard line breaks to keep a column width — let paragraphs flow as single long lines. Hard-wrapped text renders poorly when the document is viewed at any width other than the one it was written for.

Commit completed work by default

Unless the user explicitly asks not to commit, create a focused commit once the requested work is complete, verified, and reviewed. Stage only files that belong to the task, preserve unrelated dirty or staged changes, and do not push unless the user asks.

Working inside a Sidecar shell

Run sidecar agents for what you can do from here, and use it. (sidecar --agents was the legacy spelling and may fail on current builds.) The two that earn their keep every session: keep the shell's name describing your current task, and put a file or issue in front of the user rather than describing its path (sidecar open works from any context, not only a Sidecar shell). Never edit shells.json or rename tmux sessions directly.

Demoing Features

When you finish building or modifying a user-facing feature, make it easy for the user to try it in an isolated demo environment using ./scripts/demo.sh. Demo runs are 100% ephemeral: they automatically compile a fresh binary from the current working tree, use private tmux sockets and temp state trees, and clean up on exit.

Read the full file on GitHub · 280 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. 2d ago First seen · 280 lines · 2,978 tokens per session scan C bda4725fd78f

Subscribe to this mod's changes

sidecar AGENTS.md is an instructions file published in the GitHub repository marcus/sidecar (1,049 stars, last pushed 2d ago), licensed MIT. It adds 2,978 tokens to every session, about $0.0149 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.