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.
npx agentmods add instructions/proggarapsody/bitbottle/agents-mdgit clone --depth 1 https://github.com/proggarapsody/bitbottleWhat 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 | $0.01997 | $0.01997 |
| Opus 5 | $0.00999 | $0.00999 |
| Sonnet 5 | $0.00399 | $0.00399 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
bitbottle 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
See CONTRIBUTING.md for full workflow, code style, and testing conventions.
Reference implementations
reference/gh/ contains a shallow clone of github.com/cli/cli. When in doubt about CLI design patterns (flag naming, config structs, auth flows), check how gh does it there first.
Design principles
Read before designing any new command, interface, package, transport, MCP tool, or error site. Pre-merge-check §6 ("Design-judge") gates merges against both.
docs/TASTE.md— UX (gh philosophy, standard flags, TTY-aware output, error format), agentic skill experience, MCP tool shape.docs/ARCHITECTURE.md— SOLID, layered structure, composite + optional interfaces, deep modules, design decisions, gh references.
Automation
The autonomous iteration loop is documented in docs/workflows/iteration-cycle/.
Agent-specific wrappers (e.g. .claude/commands/auto-iter.md) inherit one-way from
these canonical docs — they add delivery details (model names, tool invocation syntax)
without duplicating procedural content.
Workflow
End-to-end procedures live in docs/workflows/ and are tool-neutral — humans, Codex, Cursor, Aider, and Claude all follow them.
docs/agent-primer.md— required architectural reading for any subagent implementing a new scope.docs/workflows/iteration-cycle/— the iteration loop:README.md(canonical procedure),quickref.md(halt routing, outcome enum, cadence),scripts.md(script catalog),autonomous.md(autonomous-mode deltas),parallel-mode.md(multi-scope iteration).docs/workflows/pre-merge-check.md— the merge gate (sections 0–9). Must pass before any branch lands onmain.
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 · 103 lines · 1,997 tokens per session scan A a49e66d807ff
bitbottle AGENTS.md is an instructions file published in the GitHub repository proggarapsody/bitbottle (3 stars, last pushed 14d ago), licensed MIT. It adds 1,997 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 2026-08-31.
Other instructions, from other repositories
dev3000 AGENTS.md
Instructions for vercel-labs/dev3000, covering agents.md, runtime, local ui, production workflows, browser tools and development rules.
agent-inspect AGENTS.md
Instructions for rajudandigam/agent-inspect, covering agentinspect ai maintainer instructions, product boundary, source of truth, public-copy rule and start every task.
jenkins-cli CLAUDE.md
Instructions for avivsinai/jenkins-cli, covering claude.md, build & test commands, run a single test, skip e2e tests during unit testing and e2e with colima on macos (if docker is unreachable).
patchloom AGENTS.md
Instructions for patchloom/patchloom, covering agents.md, project overview, dev commands, git hygiene and release prs (release-please).
ducklab AGENTS.md
Instructions for jrullan/ducklab, covering working in this repository as an agent and path 1: conventional (edit the tree directly).
goal-flight AGENTS.md
Instructions for simonrowland/goal-flight, covering agent notes, goal flight routing, project commands (this repo), git workflow (this repo) and git-visible trigger hygiene.