What is bedside AGENTS.md?

A set of repository instructions for coding agents working on the tig/bedside project. It explains the project structure, writing rules, command-line architecture, and how agents should ask the operator for approval.

Guiding edits and other agent work in the Bedside repository, including documentation style, image handling, project paths, and approval steps.

It gives agents project-specific rules and keeps sensitive or high-judgment actions behind explicit human decisions. It also points them to the correct files and workflows.

bedside AGENTS.md — Instructions file by tig

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/tig/bedside/agents-md

Clone the repo

git clone --depth 1 https://github.com/tig/bedside

Made for: Codex, OpenCode.

Per session 601 This file is loaded in full into every session.

When invoked 601 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.

Model	Per session	Once invoked
Fable 5	$0.00601	$0.00601
Opus 5	$0.00300	$0.00300
Sonnet 5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 2d ago against content hash 62c3d0368c77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bedside 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project guidance for AI coding agents working in tig/bedside.

What this repo is

Portable Bedside standard: contract/, surface/, eval/, plus a minimal Python CLI (src/bedside/). Not silico. Not mcec. Not domain product UX.

Human index: README.md. Writing style: follow Tig voice mechanics (no em-dashes, no horizontal rules, short paragraphs, Oxford commas, sentence-ended list items) when editing prose.

Brand images: docs/images/README.md. Canonical docs/images/hero.jpg (README) and docs/images/social-preview.jpg (GitHub 1280×640). Export social with python scripts/export_social_preview.py.

Help the operator (Bedside)

We follow Bedside: manners for agents operating tools for smart, high-judgment non-experts.

Pin: see bedside.toml (do not soft-fork tenets).
Normative contract path: contract
Human gates: call bedside ask / bedside step (or the host structured choice UI).

Summary (full contract is normative):

Assume low ops literacy, high judgment.
No walls of shell or choice.
Prefer doing over instructing.
No silent work.
Human acts are explicit and dumb-simple.
Own first-time setup from zero.
Own scary surfaces in plain language.
Confirm what they can see, in their words.
Never leave them at a cliff.
Teach only what tomorrow requires.
Compound what you learn.

Domain notes (this repo only)

First-run: pip install -e ".[dev]" then bedside doctor and bedside eval.
Scary surfaces: none physical; prefer doing install and tests yourself.
Leave-behind: pytest -q and bedside eval (one proof path for manners).

CLI architecture

bedside.cli: argparse adapter only.
bedside.commands.*: UI-agnostic command cores (future tui-cs/cli should call these).
bedside.eval_engine: rule-based R1-R11 scoring.
Operator gates: ask (structured choice) and step (one human act + confirm).
Exit codes: 0 ok, 10 human-needed / non-recommended ask / declined step, 20 manners fail, 30 setup error.

Read the full file on GitHub · 57 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.

2d ago First seen · 57 lines · 601 tokens per session scan A 62c3d0368c77

Subscribe to this mod's changes

bedside AGENTS.md is an instructions file published in the GitHub repository tig/bedside (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 601 tokens to every session, about $0.0030 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.

Planning Productivity Writing and docs agent-orchestration agent-skills agentic-ai agentic-workflow ai bedside

bedside AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

What this repo is

Help the operator (Bedside)

Domain notes (this repo only)

CLI architecture

What this file has done since we first saw it

Other instructions, from other repositories

tutti AGENTS.md

babysitter AGENTS.md

rn-dev-agent AGENTS.md

team AGENTS.md

babysitter CLAUDE.md

symphony-trello AGENTS.md