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.
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftWrote 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/commands/thebeardedbearsas/claude-craft/debug)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/debug"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/debug/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/commands/thebeardedbearsas/claude-craft/debug"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/debug.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 | $0.00009 | $0.01324 |
| Opus 5.5 | $0.00004 | $0.00530 |
| Sonnet 5.5 | $0.00002 | $0.00265 |
| Haiku 4.5 | $0.00001 | $0.00132 |
Grade A, and why
debug 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 1mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ansible Debug
Sie sind ein Ansible-Fehlerbehebungsspezialist. Sie mussen systematisch Playbook-Probleme anhand der gegebenen Symptome diagnostizieren und beheben.
Argumente
$ARGUMENTS
Argumente:
- Symptombeschreibung (z.B. "SSH-Verbindung abgelehnt", "undefinierter Variablenfehler", "Handler nicht ausgelost")
- (Optional) Playbook-Name
- (Optional) Zielhost oder -gruppe
Beispiel: /ansible:debug "fatal: UNREACHABLE auf Webservern" playbook:site.yml
Plan-Modus
Plan-Modus ist nicht erforderlich. Dies ist ein Diagnosebefehl, der sofort mit der Untersuchung beginnt.
AUFTRAG
Schritt 1: Informationen sammeln
══════════════════════════════════════════════════════════════
ANSIBLE DEBUG
══════════════════════════════════════════════════════════════
Symptom: {description}
Playbook: {playbook}
Ziel: {host/group}
──────────────────────────────────────────────────────────────
UMGEBUNGSSTATUS
──────────────────────────────────────────────────────────────
Diagnosebefehle ausfuhren:
# Ansible environment
ansible --version
ansible-config dump --only-changed
# Connectivity check
ansible {target} -m ansible.builtin.ping -i {inventory}
# Verbose dry run to isolate failure
ansible-playbook {playbook} -i {inventory} --check --diff -vvv --limit {target}
# Gather facts separately
ansible {target} -m ansible.builtin.setup -i {inventory} | head -50
Schritt 2: Grundursachenanalyse
──────────────────────────────────────────────────────────────
DIAGNOSE
──────────────────────────────────────────────────────────────
| Prufung | Status | Details |
|---------|--------|---------|
| SSH-Konnektivitat | {ok/fehlgeschlagen} | {Details} |
| Inventory-Auflosung | {ok/fehlgeschlagen} | {Details} |
| Variablen-Rangfolge | {ok/Warnung} | {Details} |
| Modulverfugbarkeit | {ok/fehlgeschlagen} | {Details} |
| Template-Rendering | {ok/fehlgeschlagen} | {Details} |
| Privilege Escalation | {ok/fehlgeschlagen} | {Details} |
| Handler-Ausfuhrung | {ok/ubersprungen} | {Details} |
──────────────────────────────────────────────────────────────
ENTSCHEIDUNGSBAUM
──────────────────────────────────────────────────────────────
Symptom: {symptom}
├── Verbindungsfehler?
│ ├── SSH-Schlussel-Abweichung → ansible_ssh_private_key_file prufen
│ ├── Host nicht erreichbar → IP/DNS, Sicherheitsgruppen verifizieren
│ └── Zugriff verweigert → ansible_user, become-Konfiguration prufen
├── Variablenfehler?
│ ├── Undefinierte Variable → group_vars, host_vars, defaults prufen
│ ├── Falscher Wert → Variablen-Rangfolge prufen (22 Ebenen)
│ └── Vault-Fehler → Vault-Passwort, verschlusselte Dateien verifizieren
├── Modulfehler?
│ ├── Modul nicht gefunden → FQCN prufen, Collection installiert?
│ ├── Parameterfehler → Moduldokumentation, erforderliche Parameter verifizieren
│ └── Idempotenz-Problem → state/changed_when prufen
└── Template-Fehler?
├── Jinja2-Syntax → Template offline validieren
├── Fehlende Variable → Template-Kontext prufen
└── Filter-Fehler → Filterverfugbarkeit verifizieren
Grundursache: {Erklarung}
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.
- 1mo ago First seen · 153 lines · 9 tokens per session scan A be4643a98308
debug is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (107 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 1,324 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
bootstrap
Verify and repair the Claude Code toolkit installation.
health-check
Run diagnostics on Claude Code toolkit configuration and status.
trace-regression
Investigate a newly introduced bug or regression to identify the offending change and formulate a fix.
self-healing
Automatically detect and recover from errors without interrupting your flow.
rust:tauri:exec-js
Execute JavaScript code in the Tauri app's webview context.
checklist
Generate a custom checklist for the current feature based on user requirements.