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 skills add Hmbown/Wizards-of-the-Ghosts --skill knockgit clone --depth 1 https://github.com/Hmbown/Wizards-of-the-GhostsWrote 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/hmbown/wizards-of-the-ghosts/knock)<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/knock"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/knock/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/knock"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/knock.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00093 | $0.01114 |
| Opus 5 | $0.00046 | $0.00557 |
| Sonnet 5 | $0.00019 | $0.00223 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
knock 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 9d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knock
Bypass access friction through legitimate unlock paths: key rotation, permission requests, and recovery workflows.
What This Skill Does
Knock is specifically about restoring legitimate access through authorized channels. It is NOT about: - Performance optimization (slow queries, throughput issues) → different spell
- Removing safety controls (approval gates, compliance checks) → different spell
- Simple bug fixes (typos, wrong ports) → different spell
- Breaking constraints (resource limits, CPU throttling) → different spell
- Security analysis (encryption schemes, certificate inspection) → different spell In this grimoire, Knock is treated as a literal spell with a prototype delivery profile. Canonical reference input: Knock (spell).
When To Use
- Activate this spell when the user's request contains an access barrier with a legitimate recovery path. Look for these patterns:
- Expired/rotated credentials: "credentials expired", "token revoked", "certificate expired", "password rotated", "key expired"
- Locked resources: "lockfile", "state is locked", "DynamoDB lock", "stale lock"
- Permission gaps: "locked out", "permissions removed", "RBAC", "403", "unauthorized", "access denied"
- Blocked processes: "stuck behind", "can't authenticate", "connection rejected", "sealed" (Vault)
- Recovery language: "rotate", "renew", "unseal", "reinstate", "force-unlock", "exception request", "proper channel"
- The core signal: something is blocking access, and there exists an authorized way to restore it.
Prerequisites
- No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.
Procedure
- Restate the target, the success condition, and any no-touch boundaries before taking action.
- Identify the lock: What exact resource is inaccessible? What kind of barrier is it (credential, permission, lockfile, certificate, sealed state)? Who owns or controls the unlock mechanism?
- Determine the legitimate path: Map the barrier to its authorized recovery mechanism:
- Expired credential → key rotation or certificate renewal
- Revoked permission → access request or RBAC adjustment
- Stale lockfile → safe removal after process verification
- Sealed service (e.g., Vault) → proper unseal procedure (Shamir keys, etc.)
- Locked state (e.g., Terraform) → force-unlock with owner confirmation
- Execute through the narrowest channel: Perform only the minimum action needed to restore access. Log each step. Do not escalate privileges beyond what the recovery path requires.
- Stop for explicit confirmation before taking a live action that changes access, triggers an alert, or touches a real system boundary.
- Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
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.
- 9d ago First seen · 89 lines · 93 tokens per session scan A 0fb9c4fb3166
knock is a skill published in the GitHub repository Hmbown/Wizards-of-the-Ghosts (107 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 93 tokens to every session and 1,114 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
agent-creator
Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use…
code-research
Use when produce structured understanding of unfamiliar codebases — architecture, data flows, dependencies, and conventions. Use when joining a new project, tracing feature implementations, or mapping system architecture.
crewai-agents
Use when crewAI multi-agent orchestration — agents, tasks, crews, tools, memory, delegation. Use when working with crewai agents.
code-agent
Use when implementing features from specs — reads requirements, writes code with tests, iterates until verification passes.
deploy-agent
Use when ship code through controlled pipeline with verification gates and rollback plans.
planning-agent
Use when decompose complex tasks into executable steps with dependencies, risk assessment, and verification criteria.