Skip to content
Back to skills

Verify Config

ASecurity

Config doctor for clawback — loads the merged config (DEFAULTS < global < ./CLAWBACK.md < CLI overrides) exactly as the proxy's loadConfig does, prints a secret-free summary of the resolved values plus the merge-order sources, and exits non-zero if the canonical CLAWBACK.md did NOT take effect (host not 0.0.0.0, tls off, or adminToken missing) so a bad parse fails loudly instead of silently falling back to loopback defaults. Read-only; never prints the adminToken value, only its length. Use t...

  • 5 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added August 31, 2026
ai-agentsbashnode

Works with

  • cli

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned August 31, 2026

npx -y skills add zapgun-ai/clawback --skill verify-config --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Verify Config?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Verify Config
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/zapgun-ai-verify-config/badge)](https://www.skillsdirectory.com/skills/zapgun-ai-verify-config)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: verify-config
description: Config doctor for clawback — loads the merged config (DEFAULTS < global < ./CLAWBACK.md < CLI overrides) exactly as the proxy's loadConfig does, prints a secret-free summary of the resolved values plus the merge-order sources, and exits non-zero if the canonical CLAWBACK.md did NOT take effect (host not 0.0.0.0, tls off, or adminToken missing) so a bad parse fails loudly instead of silently falling back to loopback defaults. Read-only; never prints the adminToken value, only its length. Use to confirm a CLAWBACK.md edit actually parsed and merged before starting the proxy, or to debug which config layer won.
---

# clawback config doctor

Run `.skills/verify-config/scripts/verify_config_parse.mjs` from the project
root. It loads the merged config the same way the proxy would and prints what
actually resolved — no secrets — then fails loudly if the canonical
`CLAWBACK.md` did not take effect.

```bash
node .skills/verify-config/scripts/verify_config_parse.mjs              # resolve from ./ (cwd)
node .skills/verify-config/scripts/verify_config_parse.mjs /path/to/project
```

The optional positional argument is the directory to resolve config from
(defaults to the current working directory).

## What it prints

- **sources (merge order)** — each contributing tier and file path, lowest
  precedence first, exactly the layering in CLAUDE.md's *Config Merging
  Strategy* (`DEFAULTS < global < local < CLI`).
- **resolved** — host, port, tls, cert/key paths, selfSign, passthrough,
  keepAliveEnabled, injectExtendedCacheTtl, adminPathPrefix, and whether an
  adminToken is present (length only — the value is never shown).
- **warnings** — any non-fatal notes `loadConfig` surfaced.

## Exit status

Exits **non-zero** with a `FAIL:` list when any of these are off — the
signature of a `CLAWBACK.md` that did not parse or merge:

- `host` is not `0.0.0.0` (the canonical LAN bind did not stick),
- `tls` is not `true`,
- `adminToken` is missing (a non-loopback bind would have thrown anyway).

Otherwise it prints `OK: canonical CLAWBACK.md parsed and merged`. Pairs with
the [write-config](../write-config/SKILL.md) skill, which generates that file.

Files in this skill

  • SKILL.md2.2 KB
  • scripts/verify_config_parse.mjs2.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.