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 skills/nanocoai/nanoclaw/debugnpx skills add nanocoai/nanoclaw --skill debuggit clone --depth 1 https://github.com/nanocoai/nanoclawWhat 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 | $0.00041 | $0.03485 |
| Opus 5 | $0.00020 | $0.01742 |
| Sonnet 5 | $0.00008 | $0.00697 |
| Haiku 4.5 | $0.00004 | $0.00348 |
Grade D, and why
debug scanned grade D with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
docker info &>/dev/null && echo "OK" || echo "NOT RUNNING - start Docker Desktop (macOS) or sudo systemctl start docker (Linux)" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf data/v2-sessions/<group>/<session>/ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS http://127.0.0.1:10254/ >/dev/null 2>&1 && echo "OK" || echo "CHECK - gateway not responding on 127.0.0.1:10254" How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NanoClaw Container Debugging
This guide covers debugging the containerized agent execution system.
Architecture Overview
The host is a single Node process that orchestrates per-session agent containers. The two session DBs are the sole IO surface between host and container — there is no IPC, no file watcher, and no stdin piping.
Host (Node) Container (Bun, Linux VM)
──────────────────────────────────────────────────────────────────────
src/container-runner.ts container/agent-runner/src/
│ │
│ spawns one container per session │ polls inbound.db for work,
│ with the session folder mounted │ calls the agent provider,
│ at /workspace │ writes replies to outbound.db
│ │
├── data/v2-sessions/<group>/<session>/ ──> /workspace
│ ├── inbound.db (host writes, container reads RO)
│ ├── outbound.db (container writes, host reads)
│ └── .heartbeat (container touches → /workspace/.heartbeat)
├── groups/<folder> ─────────────────────> /workspace/agent (cwd)
├── <group>/.claude-shared ──────────────> /home/node/.claude
└── agent-runner src + skills ───────────> /app/src, /app/skills
Message flow: host writes a row to inbound.db (messages_in) and wakes the container; the container's poll loop picks it up, runs the agent, and writes the reply to outbound.db (messages_out); the host's delivery poll reads messages_out and sends it through the channel adapter. See docs/db.md and docs/db-session.md for the full two-DB model.
Container identity: the container runs as user node with HOME=/home/node. Per-group Claude state (settings, session history) lives in <group>/.claude-shared on the host, mounted to /home/node/.claude.
Log Locations
| Log | Location | Content |
|---|---|---|
| Host errors | logs/nanoclaw.error.log |
Delivery failures, crash-loop backoff, warnings — check this first |
| Host app log | logs/nanoclaw.log |
Full routing chain: inbound routing, container spawn/exit, delivery |
| Setup logs | logs/setup.log, logs/setup-steps/*.log |
Per-step install output (bootstrap, container, onecli, mounts, service) |
| Session inbound | data/v2-sessions/<group>/<session>/inbound.db (messages_in) |
Did the message reach the container? |
| Session outbound | data/v2-sessions/<group>/<session>/outbound.db (messages_out) |
Did the agent produce a reply? |
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 · 298 lines · 41 tokens per session scan D 4be0e0d989b3
debug is a skill published in the GitHub repository nanocoai/nanoclaw (30,678 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 3,485 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
self-reflection
Daily loop that reviews the bot's own recent outbound behavior and any pending lessons in self/learnings.md, stress-tests candidate rules against 10-20 hypothetical scenarios, and on explicit owner approval routes each to the right home among three sinks — prompts/project.md (durable behavioral rules), a memory file…
render-style
House style for the renderhtml tool — dark dashboard / architecture-diagram look with stat tiles, bar rows, numbered timeline steps, two-panel grids, status pills, connector arrows, callout bands, and verdict blocks. Read this skill before calling renderhtml so the output is visually consistent. Provides CSS tokens…
reminder-format
House format for the text passed to reminderset. Read before calling reminderset, and again before editing a reminder (cancel + re-create). Three rules — open with the literal marker , state the goal in one line, then list numbered steps the future-self should run when the reminder fires. Keeps fired envelopes…
openclaw-control
控制和管理 OpenClaw AI 助手。用于发送消息给 OpenClaw、检查状态、管理配置和安装技能。当用户想要与 OpenClaw 交互或管理 OpenClaw 时使用此技能。.
Pynchy Development
Use when running pynchy locally — running the app, tests, linting, formatting, prek hooks, or rebuilding the agent container. Also use when determining whether you're on the live Pynchy host or a local machine, and for debugging agent behavior-- session transcript branching, inspecting message history and agent traces…
Pynchy Plugin Authoring
Use when creating, scaffolding, or updating a pynchy plugin, including channels, MCP servers, skills, agent cores, workspace specs, and container runtime plugins. Also use when users ask how to register plugins via config.toml, add entry points, or validate plugin hook wiring.