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/zdavison/deer/claude-mdgit clone --depth 1 https://github.com/zdavison/deerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/zdavison/deer/claude-md)<a href="https://agentmods.dev/instructions/zdavison/deer/claude-md"><img src="https://agentmods.dev/badge/instructions/zdavison/deer/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02331 | $0.02331 |
| Opus 5 | $0.01166 | $0.01166 |
| Sonnet 5 | $0.00466 | $0.00466 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
deer CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deer
Unattended coding agent — runs Claude Code in sandboxed tmux sessions against git worktrees, with a TUI dashboard.
Monorepo Structure
Bun workspace monorepo with three packages:
packages/shared/— Shared utilities used by both deerbox and the TUI (private, never published)packages/deerbox/— Core sandbox orchestration library (no TUI dependencies)- Root (
src/) — Ink/React TUI dashboard
deer/ # workspace root
package.json # "workspaces": ["packages/*"]
src/ # deer TUI source (imports from "@deer/shared")
packages/
shared/
src/ # shared utilities: constants, i18n, credentials, git/detect, git/finalize
package.json # name: "@deer/shared", private: true
tsconfig.json
deerbox/
src/ # core modules (agent, sandbox, config, etc.)
package.json
tsconfig.json
Stack
- Runtime: Bun (required — uses
Bun.$,Bun.file,Bun.spawn, etc.) - Language: TypeScript (ESM)
- UI: Ink + React (terminal TUI)
- Sandbox: Anthropic SRT (
@anthropic-ai/sandbox-runtime) — bwrap on Linux, seatbelt on macOS - Config: TOML via
@iarna/toml
Commands
bun test # run all tests
bun run dev # run CLI from source (must be inside a git repo)
bun run build # compile Linux x64 binary to dist/
Architecture
Each agent task:
- deer TUI invokes deerbox as a subprocess (via
src/deerbox.ts) — deerbox outputs JSON to stdout - deerbox (
session.ts) prepares a sandboxed session: worktree → ecosystem detection → gitconfig → auth proxy → SRT command - deer TUI launches the prepared command in a tmux session (
deer-<taskId>) viasrc/sandbox/index.ts - Finalizes by creating a GitHub PR and cleaning up
@deer/shared (shared utilities)
Private package — never published. Both deerbox and the TUI depend on it.
| File | Purpose |
|---|---|
packages/shared/src/index.ts |
Barrel export for all shared APIs |
packages/shared/src/constants.ts |
Shared constants (HOME, DEFAULT_MODEL, BYPASS_DIALOG_*, MAX_DIFF_FOR_PR_METADATA, PR_METADATA_MODEL) |
packages/shared/src/i18n.ts |
Language detection, setLang/getLang/getPRLanguage/detectLang |
packages/shared/src/credentials.ts |
resolveCredentials() — OAuth/API key resolution from env/files/keychain |
packages/shared/src/git/detect.ts |
detectRepo() — git repo detection by walking up from a directory |
packages/shared/src/git/finalize.ts |
PR creation: createPullRequest, updatePullRequest, pushBranchUpdates, hasChanges |
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.
- 3d ago First seen · 162 lines · 2,331 tokens per session scan A bf2bcb10b4d9
deer CLAUDE.md is an instructions file published in the GitHub repository zdavison/deer (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,331 tokens to every session, about $0.0117 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.