Install rtk token-compression proxy into agent containers. Routes Bash tool calls through rtk for 60–90% token savings on dev commands (git, cargo, pytest, docker, kubectl, etc.).
Install rtk — a CLI proxy delivering 60–90% token savings on common dev commands (git, cargo, pytest, docker, kubectl, etc.) — and wire it transparently into agent containers via the Claude Code PreToolUse hook.
rtk binary at ~/.local/bin/rtk on the host~/.local/bin/rtk mounted read-only at /usr/local/bin/rtk inside the target agent group's containersPreToolUse hook in the agent group's settings.json so every Bash call is automatically filtered through rtk — no CLAUDE.md instructions neededThis skill has no in-tree integration test by design. Its only functional reach-ins are runtime operator actions — the host-only ncl groups config add-mount (Step 3) and the settings.json PreToolUse hook write (Step 4) — neither of which leaves a line in the source tree whose deletion a test could catch. There are no package dependencies or Dockerfile edits to guard either. Conformance is idempotent apply + REMOVE.md; the mount and hook are verified at runtime (see Verify).
curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh
If the script put the binary elsewhere, move it:
find ~/.local ~/.cargo/bin ~/bin -name rtk 2>/dev/null
mv "$(which rtk 2>/dev/null)" ~/.local/bin/rtk
Verify:
~/.local/bin/rtk --version
chmod +x ~/.local/bin/rtk # if needed
ncl groups list
Note the group ID (e.g. ag-1776342942165-ptgddd). Repeat Steps 3–5 for each group.
Mount the host rtk binary read-only into the container with the host-only add-mount verb. It is idempotent — re-running skips the entry if it is already present:
ncl groups config add-mount --id <group-id> \
--host ~/.local/bin/rtk \
--container /usr/local/bin/rtk \
--ro
This verb is operator-only and runs host-side (via /setup, /customize, or /manage-mounts); it is rejected from inside a container.
The host root (~/.local/bin) must also be in the external mount allowlist at ~/.config/nanoclaw/mount-allowlist.json for the mount to take effect at spawn. Add it there if it isn't already.
Verify:
ncl groups config get --id <group-id>
# Look for the /usr/local/bin/rtk mount
Each agent group has a settings.json at:
data/v2-sessions/<group-id>/.claude-shared/settings.json
This file is mounted at /home/node/.claude/settings.json inside the container and is read by Claude Code for hooks, env, and model config.
Add the PreToolUse entry with jq. This drops any existing rtk Bash hook first, then appends a fresh one, so it is safe to re-run without creating duplicates:
SETTINGS="data/v2-sessions/<group-id>/.claude-shared/settings.json"
jq '.hooks.PreToolUse = ((.hooks.PreToolUse // [])
| map(select((.hooks // []) | any(.command == "rtk hook claude") | not)))
+ [{"matcher":"Bash","hooks":[{"type":"command","command":"rtk hook claude"}]}]' \
"$SETTINGS" > /tmp/rtk-settings.json && mv /tmp/rtk-settings.json "$SETTINGS"
ncl groups restart --id <group-id>
Confirm the binary is executable inside the container so a missing or non-executable mount surfaces immediately rather than as a silent hook failure:
docker exec "$(docker ps --filter "name=<group-id>" --format '{{.Names}}' | head -1)" rtk --version
Then ask the agent to run git status or any other supported command. rtk intercepts it silently. Check savings with:
~/.local/bin/rtk gain
rtk: command not found inside the containerMount wasn't applied or container wasn't restarted:
ncl groups config get --id <group-id>
# Look for the /usr/local/bin/rtk mount
ncl groups restart --id <group-id>
Verify the hook is in settings.json:
jq '.hooks.PreToolUse' data/v2-sessions/<group-id>/.claude-shared/settings.json
If missing, re-run Step 4.
chmod +x ~/.local/bin/rtk
Copy a source-pinned command for your client. You run it yourself.
Destination: .claude/skills/add-rtk · pinned to the source commit
# Run from your project root
git clone https://github.com/nanocoai/nanoclaw.git .skillboard-tmp
git -C .skillboard-tmp checkout 7be8d7f6b9863e7c78c513717c21a6fcf04c3d28
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/.claude/skills/add-rtk" ".claude/skills/"
rm -rf .skillboard-tmpReview the source before running. This copies files into your project; it is not a one-click install and does not verify runtime safety.
sudo apt update && sudo apt install -y gitnpm install -g @anthropic-ai/claude-code# Run from your project root
git clone https://github.com/nanocoai/nanoclaw.git .skillboard-tmp
git -C .skillboard-tmp checkout 7be8d7f6b9863e7c78c513717c21a6fcf04c3d28
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/.claude/skills/add-rtk" ".claude/skills/"
rm -rf .skillboard-tmpDestination: .claude/skills/add-rtk
Scanner static-checks@0.1.0 · commit 7be8d7f6b986. Static checks cannot prove runtime safety – review the source and the exact diff before installing. How checks work.
Piping a downloaded script directly into a shell runs unreviewed remote code.
Evidence: curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/r…· fingerprint 2de68f8979f3f8b8
Instructs shell/process/package operations that run commands on the host.
Evidence: chmod +x· fingerprint d242f67f7a76ea57
Fetches remote content at runtime, which can change after review.
Evidence: curl· fingerprint 427e4b79b1f0fc90