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/pioootrek/worktree-switcher/agents-mdgit clone --depth 1 https://github.com/pioootrek/worktree-switcherWhat 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 | $0.00409 | $0.00409 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
worktree-switcher AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Worktree Switcher repository guide
Status: active Audience: humans and coding agents working on this repository Source of truth: repository-wide contribution and project-memory rules
Project intent
Build an open-source, local-first control plane that discovers Git worktrees and runs several development projects concurrently. Each project owns one managed server and can switch independently to another worktree while keeping a stable configured port.
Read docs/project-brief.md before making product or architecture decisions.
Keep the control plane independent from every repository it supervises.
Backlog
This project keeps its backlog and durable agent memory as canonical JSON under
docs/backlog/. Read docs/backlog/AGENTS.md before adding, updating, or
closing an item or note.
After every edit under docs/backlog/ or to a top-level project document under
docs/, run:
HUB_DIR="${LLM_OPS_HUB_DIR:-/home/pioootrek/development/llm-ops-hub}"
"$HUB_DIR/.venv/bin/python" "$HUB_DIR/bin/hub.py" fmt --backlog-dir docs/backlog
"$HUB_DIR/.venv/bin/python" "$HUB_DIR/bin/hub.py" validate --backlog-dir docs/backlog
Never edit docs/backlog/index.json manually. Backlog changes live on main
and become visible through the read-only LLM Ops Hub after they are committed
and synchronized.
Check the notes section of docs/backlog/index.json before non-trivial work.
Persist durable findings under docs/backlog/notes/ before context compaction.
Completed work moves from an open item to a done/ entry in one commit.
This project currently has no GitHub feedback integration. If one is configured
later, treat open issues labeled backlog-feedback as human instructions and
apply them according to docs/backlog/AGENTS.md.
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 · 43 lines · 409 tokens per session scan A fc3b350a0359
worktree-switcher AGENTS.md is an instructions file published in the GitHub repository pioootrek/worktree-switcher (0 stars, last pushed 2d ago), licensed MIT. It adds 409 tokens to every session, about $0.0020 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
Siftly CLAUDE.md
Instructions for viperrcrypto/Siftly, covering siftly, quick setup, ai authentication — no api key needed, key commands and project structure.
braid AGENTS.md
Instructions for openbraid/braid, covering agents.md, what braid is, repository layout, the two modes — read this before touching storage and migration code that looks like a botched rename.
braid CLAUDE.md
Instructions for openbraid/braid, a project described as: Mission control for your agent swarm — know which agent is working, which is stuck, and which is done. Works with 14 coding agents, runs entirely on your machine.
gingerpaw AGENTS.md
AGENTS.md instructions for Vikrant-Khedkar/gingerpaw, covering agents.md, commands, architecture, conventions that matter and project files.
gingerpaw CLAUDE.md
Claude Code instructions for Vikrant-Khedkar/gingerpaw, covering claude.md, commands, architecture, conventions that matter and project files.
data-table-filters CLAUDE.md
Instructions for openstatusHQ/data-table-filters, covering claude.md, project overview, monorepo structure (pnpm + turborepo), key commands and database.