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/update-ghostclawnpx skills add b1rdmania/ghostclaw --skill update-ghostclawgit clone --depth 1 https://github.com/b1rdmania/ghostclawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/b1rdmania/ghostclaw/update-ghostclaw)<a href="https://agentmods.dev/skills/b1rdmania/ghostclaw/update-ghostclaw"><img src="https://agentmods.dev/badge/skills/b1rdmania/ghostclaw/update-ghostclaw.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00035 | $0.01234 |
| Opus 5 | $0.00017 | $0.00617 |
| Sonnet 5 | $0.00007 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
update-ghostclaw 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update GhostClaw
Pulls the latest GhostClaw release, runs migrations, rebuilds, and restarts the service. Creates a backup tag before changing anything so the user can roll back.
Steps
1. Preflight
Memory warning: Before proceeding, tell the user:
"⚠️ Heads up: updating will reset your active session. If you want to preserve recent conversation context, back up your memory files first:
groups/main/memory/— identity, state, and loggroups/main/CLAUDE.md— personalised soulThe update won't delete these files, but a fresh session after restart won't have the previous conversation in context."
Check that the working tree is clean:
git status --porcelain
If there's any output, stop and tell the user: "You have uncommitted changes. Commit or stash them first, then run /update-ghostclaw again."
Get the current version:
node -e "console.log(require('./package.json').version)"
Save this as OLD_VERSION.
Check for updates:
git fetch origin
git log HEAD..origin/main --oneline
If no new commits, tell the user: "GhostClaw is already up to date (vOLD_VERSION)." and stop.
Otherwise, show the user the list of incoming commits and how many there are. Ask: "These updates are available. Apply them?"
2. Backup
Create a backup tag so the user can roll back:
git tag "backup/pre-update-$(git rev-parse --short HEAD)-$(date +%s)"
Tell the user the tag name. Remind them they can roll back with:
git reset --hard <tag-name> && npm run build && launchctl kickstart -k gui/$(id -u)/com.ghostclaw
3. Pull
git merge origin/main
If there are merge conflicts, stop. Tell the user which files conflict and that they need to resolve manually. Do NOT force-resolve conflicts — this code runs bare metal with full system access.
4. Install dependencies and run migrations
npm install
This also runs the postinstall script which bootstraps agent-runner.
Get the new version:
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.
- 4d ago First seen · 191 lines · 35 tokens per session scan A c4063add4a28
update-ghostclaw is a skill published in the GitHub repository b1rdmania/ghostclaw (92 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,234 once invoked, about $0.0002 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 2026-08-30.
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.