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/andresharpe/dotbot/agents-mdgit clone --depth 1 https://github.com/andresharpe/dotbotWhat 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 | $0.03174 | $0.03174 |
| Opus 5 | $0.01587 | $0.01587 |
| Sonnet 5 | $0.00635 | $0.00635 |
| Haiku 4.5 | $0.00317 | $0.00317 |
Grade A, and why
dotbot 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (Claude Code, Codex, etc.) working in this repository. CLAUDE.md is a symlink to this file.
Project Overview
dotbot is a structured AI-assisted development framework built entirely in PowerShell 7+. It wraps AI coding workflows in managed, auditable processes with two-phase execution (analysis → implementation), per-task git worktree isolation, and a web dashboard for monitoring.
Commands
Always use pwsh (PowerShell 7), never powershell (5.1). PS 5.1 cannot handle UTF-8 files without BOM.
pwsh bootstrap.ps1 # One-time: drop PATH shim into ~/.local/bin (Unix) or %LOCALAPPDATA%\Microsoft\WindowsApps (Windows)
$env:DOTBOT_HOME = $PWD # Point at this checkout (persist via shell rc / setx)
pwsh tests/Run-Tests.ps1 # Run layers 1-3
pwsh tests/Run-Tests.ps1 -Layer 4 # E2E (needs ANTHROPIC_API_KEY)
dotbot status # Confirm DOTBOT_HOME + framework git state + active project workflow/provider
dotbot init # Initialise .bot/ in current project (workspace + .gitignore only)
dotbot init -Workflow start-from-jira -Stack dotnet,dotnet-ef
dotbot go # Launch runtime + UI for the current initialized project
dotbot serve # Launch only the low-level runtime
Architecture
bin/ — CLI entry points: dotbot, dotbot.ps1, shim/ (DOTBOT_HOME-routing PATH shim)
src/ — All source code
├── runtime/ — Process orchestration, worktrees, providers (Modules/, Scripts/, Plugins/)
├── mcp/ — PowerShell MCP server, 28 auto-discovered tools
├── ui/ — PowerShell HTTP server + vanilla JS dashboard
├── cli/ — CLI entry points (init-project, doctor, registry-*, workflow-*, tasks-*)
├── hooks/ — verify/, dev/, scripts/
├── go.ps1, init.ps1 — Project-side launcher / IDE setup (copied to .bot/)
├── server-dotnet/ — ASP.NET Core question-delivery service (sibling product)
├── studio-ui/ — React + Vite visual workflow editor (sibling product)
├── shared/ — CSS design tokens
└── packaging/ — Homebrew + Scoop recipes
content/ — Framework content copied into target .bot/
├── agents/, skills/, prompts/, recipes/, settings/, workspace-template/
├── workflows/ — start-from-prompt, start-from-jira, start-from-pr, start-from-repo
└── stacks/ — dotnet, dotnet-blazor, dotnet-ef (composable via `extends`)
tests/ — Test pyramid (layers 1-4)
docs/ — Roadmap, whitepapers, design notes, specs/
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 · 170 lines · 3,174 tokens per session scan A 71e6f6df1074
dotbot AGENTS.md is an instructions file published in the GitHub repository andresharpe/dotbot (54 stars, last pushed 5d ago), licensed MIT. It adds 3,174 tokens to every session, about $0.0159 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 2026-08-30.
Other instructions, from other repositories
hedgehog CLAUDE.md
Instructions for skyf0xx/hedgehog, covering hedgehog (this repo), layout, releasing, the star prompt and working in this repo.
hedgehog GEMINI.md
Instructions for skyf0xx/hedgehog, a project described as: HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven, BMAD-METHOD plan, so Claude Code, Cursor & Gemini CLI stay locked to it. A CLI-enforced state machine for agentic…
hope AGENTS.md
Instructions for dkstm95/hope, covering ai work instructions, writing and completion.
vibe-coding-rules CLAUDE.md
Instructions for yerdaulet-damir/vibe-coding-rules, covering claude.md — vibecodex, project purpose, architecture (mandatory), repositories/protocols.py and services/wallet/user.py.
nodespace-core CLAUDE.md
Claude Code instructions for NodeSpaceAI/nodespace-core, covering nodespace development agent guide, project overview, mandatory startup sequence — new task, mandatory startup sequence — continuing from wip and critical process violations.
Agentic-Ground-Rules AGENTS.md
AGENTS.md instructions for criger/Agentic-Ground-Rules, covering agent entrypoint, startup sequence, instruction hierarchy and public repository rules.