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/git-treeline/cli/claude-mdgit clone --depth 1 https://github.com/git-treeline/cliWhat 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 | $0.00630 | $0.00630 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
cli 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 yesterday.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-treeline CLI — agent guide
Go CLI for worktree environment management. Allocates ports, databases, and services across parallel git worktrees; exposes an MCP server for AI agent integration.
Stack
- Go 1.26+
- Cobra for CLI structure (
cmd/) - bubbletea/v2 for TUI components
- mcp-go for the MCP server (
cmd/serve.go)
Development
make ci # lint + test (installs golangci-lint and govulncheck if absent)
go test ./... # tests only
go build . # build the binary
Testing conventions
Prefer pure extraction over dependency injection — see CONTRIBUTING.md for the
full hierarchy. New commands need table-driven tests in cmd/<name>_test.go.
Run go test ./cmd/... after any cmd/ change; run go test ./... before
opening a PR.
README update policy
README.md is the canonical user-facing reference. Keep it accurate; it is
not auto-generated.
Update the README when a PR:
- Adds a new command (add a row to the CLI reference table and, if the command warrants it, a numbered section in Quick start)
- Adds a flag to an existing command (add it to the flags column of that command's row in the CLI reference table)
- Changes a flag's name or behavior in a user-visible way
- Adds or changes a
.treeline.ymlfield (update the project config fields table) - Adds or changes a user config key (update the user config section)
- Adds or changes an interpolation token (update the tokens table)
- Changes the behavior of an existing command in a way that contradicts the current docs
Do not update the README for:
- Bug fixes that restore documented behavior
- Internal refactors with no user-visible surface change
- Dependency bumps
- CI / workflow changes
- Test-only changes
How to update:
- CLI reference table (bottom of README): one row per command, format
| \gtl ` | `--flag1` `--flag2` | Description |. Keep flags in roughly the order they appear in--help`. Use backtick-wrapped flag names. - Quick start numbered sections: only add a new section for commands a new user would encounter early. Networking, database, and advanced lifecycle commands already have sections; don't duplicate them. Extend an existing section when adding a flag to a well-known command.
- Config tables: mirror the field names and types exactly as they appear in the Go structs — don't invent defaults that aren't enforced in code.
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.
- yesterday First seen · 70 lines · 630 tokens per session scan A f35eeac21a37
cli CLAUDE.md is an instructions file published in the GitHub repository git-treeline/cli (5 stars, last pushed 4d ago), licensed MIT. It adds 630 tokens to every session, about $0.0032 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.