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/b1rdmania/ghostclaw/debugnpx skills add b1rdmania/ghostclaw --skill debuggit clone --depth 1 https://github.com/b1rdmania/ghostclawWhat 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 | $0.00038 | $0.01915 |
| Opus 5 | $0.00019 | $0.00958 |
| Sonnet 5 | $0.00008 | $0.00383 |
| Haiku 4.5 | $0.00004 | $0.00192 |
Grade D, and why
debug scanned grade D with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
MCP servers are configured in `data/sessions/{folder}/.claude/settings.json`. Global servers are synced automatically from `agent-spawner.ts:buildGlobalMcpServers()`. 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/sessions/ How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GhostClaw Agent Debugging
This guide covers debugging the agent execution system.
Architecture Overview
Host (macOS/Linux)
───────────────────────────────────────────────
src/index.ts agent-runner/
│ │
│ spawns child process │ runs Claude Agent SDK
│ with env vars │ with MCP servers
│ │
├── GHOSTCLAW_GROUP_DIR ──> groups/{folder}/
├── GHOSTCLAW_IPC_DIR ───> data/ipc/{folder}/
├── GHOSTCLAW_GLOBAL_DIR > groups/global/
├── CLAUDE_CONFIG_DIR ───> data/sessions/{folder}/.claude/
└── HOME ────────────────> (inherited, real home)
Important: Agents run as direct Node.js child processes, not containers. CLAUDE_CONFIG_DIR provides per-group session isolation while HOME stays untouched so tools like gh, Gmail OAuth, etc. find their credentials naturally.
Log Locations
| Log | Location | Content |
|---|---|---|
| Main app logs | logs/ghostclaw.log |
Routing, agent spawning, scheduling |
| Main app errors | logs/ghostclaw.error.log |
Host-side errors |
| Agent run logs | groups/{folder}/logs/agent-*.log |
Per-run: input, stderr, stdout |
| Claude sessions | data/sessions/{folder}/.claude/projects/ |
Claude Code session history |
Enabling Debug Logging
Set LOG_LEVEL=debug for verbose output:
# For development
LOG_LEVEL=debug npm run dev
# For launchd service (macOS), add to plist EnvironmentVariables:
<key>LOG_LEVEL</key>
<string>debug</string>
# For systemd service (Linux), add to unit [Service] section:
# Environment=LOG_LEVEL=debug
Debug level shows:
- Full environment configuration
- Agent process arguments
- Real-time agent stderr
Common Issues
1. "Claude Code process exited with code 1"
Check the agent log file in groups/{folder}/logs/agent-*.log
Common causes:
Missing Authentication
Invalid API key · Please run /login
Fix: Ensure .env file exists with either OAuth token or API key:
cat .env # Should show one of:
# CLAUDE_CODE_OAUTH_TOKEN=sk-ant-oat01-... (subscription)
# ANTHROPIC_API_KEY=sk-ant-api03-... (pay-per-use)
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 · 227 lines · 38 tokens per session scan D 1550fa281346
debug is a skill published in the GitHub repository b1rdmania/ghostclaw (91 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 1,915 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
lobu-operator
Contribute safely to the Lobu monorepo: worktrees, package rules, red-to-green fixes, validation gates, SDK-first operations, PRs, and rollout checks.
company-agent-infrastructure
Use when designing or building internal/company AI agents that need shared context across company systems, durable organizational memory across sessions or agents, user-scoped permissions, approvals, audit, or governed actions. Also use when deciding whether ordinary MCP tools, RAG, or local agent memory are enough…
lobu-builder
Use when working inside a Lobu project generated by @lobu/cli or any repository centered on lobu.config.ts, AGENTS.md, agent prompt files, local skills, and evals. This skill helps a coding agent inspect the right files, make Lobu-native changes, keep the stack runnable, and validate semantics with chat tests and…
crm-ops
How to operate the Lobu funnel CRM — create and enrich leads, log interactions, advance funnel stages, open and update pilots, and produce the weekly digest. Use whenever the task touches the pipeline.
deliveroo-order
Turn collected lunch orders into a clean per-person order list for a human to place on Deliveroo. Use in step 2 of the lunch run, after orders are collected. The live menu is fetched automatically by the lobu-team-lunch-finalize reaction (via the Owletto Chrome extension) — this skill never places an order or touches…
lobu
Use Lobu MCP for shared, permission-aware company context, durable organizational memory, and governed actions. Trigger when the user asks what the organization knows, needs context from connected company systems, wants to preserve a durable fact or decision, or needs to discover and use Lobu SDK capabilities.