⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
add-compact
Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
Status: actively maintained, best-effort, as a personal project of @trsdn. It is for a developer comfortable forking a repository, running Docker or Apple Container, and authenticating the GitHub Copilot CLI — not a packaged app a non-developer installs by name.
Language: this project's interface, documentation, and source are English only; no localized builds are published.
What Changed from NanoClaw
NanoPieLot is a full port of NanoClaw from Anthropic/Claude to the GitHub Copilot SDK:
- Any Copilot model.
/model listto see what's available,/model <id>to switch. GPT-4.1, Claude, Gemini — whatever your GitHub plan gives you. - Same architecture. Everything else works exactly like NanoClaw: containers, channels, skills, groups, scheduling.
- Authentication via
copilot logindevice flow.
Quick Start
gh repo fork trsdn/nanopielot --clone
cd nanopielot
copilot
Then run /setup.
Commands prefixed with
/(like/setup,/add-whatsapp) are CLI agent skills. Type them inside thecopilotprompt, not in your regular terminal.
Requirements
- macOS, Linux, or Windows (via WSL2)
- Node.js 20+
- GitHub Copilot CLI
- Apple Container (macOS) or Docker (macOS/Linux)
Migration from NanoClaw
If you are migrating an existing NanoClaw setup or maintaining a fork, read the NanoPieLot-specific migration notes in docs/MIGRATION.md.
Troubleshooting
For common NanoPieLot-specific deployment and runtime problems, see docs/TROUBLESHOOTING.md.
Architecture
Channels → SQLite → Polling loop → Container (GitHub Copilot SDK) → Response
Single Node.js process. Channels self-register at startup. Agents run in isolated Linux containers. Per-group message queue with concurrency control.
Data and privacy
NanoPieLot runs on infrastructure you provide and control; this project itself collects nothing.
| Question | Answer |
|---|---|
| What is collected | Nothing by this project: no telemetry, no analytics, no crash reporting. |
| Where data goes | The channels you enable (WhatsApp, Telegram, Slack, Discord, Gmail) and the GitHub Copilot API, which your agent containers call to respond. No other outbound destination. |
| Who receives your content | GitHub (via the Copilot SDK/API) and whichever chat platforms you connect. Their own terms and privacy policies govern what they do with it. |
| What is stored locally | Conversation and group state in SQLite at store/messages.db, per-group memory under groups/, and the Copilot device-login session under data/copilot-auth/. All on the machine you run it on. |
| Retention | Kept until you delete the data directory or the group; nothing is sent anywhere for retention beyond the platforms above. |
Accessibility
NanoPieLot has no graphical interface of its own; every surface is either a chat platform's own client (WhatsApp, Telegram, Slack, Discord, Gmail — their accessibility, not this project's) or plain-text console/log output during setup and debugging, which uses no colour-only signalling.
Security and support
Report a vulnerability privately through GitHub's private vulnerability
reporting. Ask
for help by opening an issue with the /debug skill's output; see
docs/TROUBLESHOOTING.md first.
Contributing Workflow
For issue-driven work, create a dedicated branch and merge via pull request. Avoid developing feature or issue work directly on main.
Special Thanks
NanoPieLot wouldn't exist without NanoClaw. The original project's philosophy, architecture, and skill system are the foundation of everything here. We just swapped the engine. 🥧
Forked from upstream commit a3fb3be (2026-03-28).
License
MIT — see LICENSE
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
.github/skills/add-compact/SKILL.md6.7 KBupstream ↗
--- name: add-compact description: Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only. --- # Add /compact Command Adds a `/compact` session command that compacts conversation history to fight context rot in long-running sessions. Uses Copilot CLI's built-in `/compact` slash command — no synthetic system prompts. **Session contract:** `/compact` keeps the same logical session alive. The SDK returns a new session ID after compaction (via the `init` system message), which the agent-runner forwards to the orchestrator as `newSessionId`. No destructive reset occurs — the agent retains summarized context. ## Phase 1: Pre-flight Check if `src/session-commands.ts` exists: ```bash test -f src/session-commands.ts && echo "Already applied" || echo "Not applied" ``` If already applied, skip to Phase 3 (Verify). ## Phase 2: Apply Code Changes Merge the skill branch: ```bash git fetch upstream skill/compact git merge upstream/skill/compact ``` > **Note:** `upstream` is the remote pointing to `trsdn/nanopielot`. If using a different remote name, substitute accordingly. This adds: - `src/session-commands.ts` (extract and authorize session commands) - `src/session-commands.test.ts` (unit tests for command parsing and auth) - Session command interception in `src/index.ts` (both `processGroupMessages` and `startMessageLoop`) - Slash command handling in `container/agent-runner/src/index.ts` ### Validate ```bash npm test npm run build ``` ### Rebuild container ```bash ./container/build.sh ``` ### Restart service ```bash launchctl kickstart -k gui/$(id -u)/com.nanopielot # macOS # Linux: systemctl --user restart nanopielot ``` ## Phase 3: Verify ### Integration Test 1. Start NanoPieLot in dev mode: `npm run dev` 2. From the **main group** (self-chat), send exactly: `/compact` 3. Verify: - The agent acknowledges compaction (e.g., "Conversation compacted.") - The session continues — send a follow-up message and verify the agent responds coherently - A conversation archive is written to `groups/{folder}/conversations/` (by the PreCompact hook) - Container logs show `Compact boundary observed` (confirms SDK actually compacted) - If `compact_boundary` was NOT observed, the response says "compact_boundary was not observed" 4. From a **non-main group** as a non-admin user, send: `@<assistant> /compact` 5. Verify: - The bot responds with "Session commands require admin access." - No compaction occurs, no container is spawned for the command 6. From a **non-main group** as the admin (device owner / `is_from_me`), send: `@<assistant> /compact` 7. Verify: - Compaction proceeds normally (same behavior as main group) 8. While an **active container** is running for the main group, send `/compact` 9. Verify: - The active container is signaled to close (authorized senders only — untrusted senders cannot kill in-flight work) - Compaction proceeds via a new container once the active one exits - The command is not dropped (no cursor race) 10. Send a normal message, then `/compact`, then another normal message in quick succession (same polling batch): 11. Verify: - Pre-compact messages are sent to the agent first (check container logs for two `runAgent` calls) - Compaction proceeds after pre-compact messages are processed - Messages **after** `/compact` in the batch are preserved (cursor advances to `/compact`'s timestamp only) and processed on the next poll cycle 12. From a **non-main group** as a non-admin user, send `@<assistant> /compact`: 13. Verify: - Denial message is sent ("Session commands require admin access.") - The `/compact` is consumed (cursor advanced) — it does NOT replay on future polls - Other messages in the same batch are also consumed (cursor is a high-water mark — this is an accepted tradeoff for the narrow edge case of denied `/compact` + other messages in the same polling interval) - No container is killed or interrupted 14. From a **non-main group** (with `requiresTrigger` enabled) as a non-admin user, send bare `/compact` (no trigger prefix): 15. Verify: - No denial message is sent (trigger policy prevents untrusted bot responses) - The `/compact` is consumed silently - Note: in groups where `requiresTrigger` is `false`, a denial message IS sent because the sender is considered reachable 16. After compaction, verify **no auto-compaction** behavior — only manual `/compact` triggers it ### Validation on Fresh Clone ```bash git clone <your-fork> /tmp/nanopielot-test cd /tmp/nanopielot-test claude # then run /add-compact npm run build npm test ./container/build.sh # Manual: send /compact from main group, verify compaction + continuation # Manual: send @<assistant> /compact from non-main as non-admin, verify denial # Manual: send @<assistant> /compact from non-main as admin, verify allowed # Manual: verify no auto-compaction behavior ``` ## Security Constraints - **Main-group or trusted/admin sender only.** The main group is the user's private self-chat and is trusted (see `docs/SECURITY.md`). Non-main groups are untrusted — a careless or malicious user could wipe the agent's short-term memory. However, the device owner (`is_from_me`) is always trusted and can compact from any group. - **No auto-compaction.** This skill implements manual compaction only. Automatic threshold-based compaction is a separate concern and should be a separate skill. - **No config file.** NanoPieLot's philosophy is customization through code changes, not configuration sprawl. - **Transcript archived before compaction.** The existing `PreCompact` hook in the agent-runner archives the full transcript to `conversations/` before the SDK compacts it. - **Session continues after compaction.** This is not a destructive reset. The conversation continues with summarized context. ## What This Does NOT Do - No automatic compaction threshold (add separately if desired) - No `/clear` command (separate skill, separate semantics — `/clear` is a destructive reset) - No cross-group compaction (each group's session is isolated) - No changes to the container image, Dockerfile, or build script ## Troubleshooting - **"Session commands require admin access"**: Only the device owner (`is_from_me`) or main-group senders can use `/compact`. Other users are denied. - **No compact_boundary in logs**: The SDK may not emit this event in all versions. Check the agent-runner logs for the warning message. Compaction may still have succeeded. - **Pre-compact failure**: If messages before `/compact` fail to process, the error message says "Failed to process messages before /compact." The cursor advances past sent output to prevent duplicates; `/compact` remains pending for the next attempt.README.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/trsdn-nanopielot-github-skills-add-compact.md