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 commands/hex/claude-guard/statusgit clone --depth 1 https://github.com/hex/claude-guardWhat 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 | $0.00013 | $0.00539 |
| Opus 5 | $0.00006 | $0.00269 |
| Sonnet 5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
status 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 yesterday.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guard Status
Display the active protections provided by the claude-guard plugin. If an optional category argument is provided, show detailed patterns for that category only.
Instructions
Read the pattern packs to extract the current protection rules:
$CLAUDE_PLUGIN_ROOT/hooks/scripts/guard/packs/core.py$CLAUDE_PLUGIN_ROOT/hooks/scripts/guard/packs/cloud.py$CLAUDE_PLUGIN_ROOT/hooks/scripts/guard/packs/infra.py$CLAUDE_PLUGIN_ROOT/hooks/scripts/guard/packs/cicd.py$CLAUDE_PLUGIN_ROOT/hooks/scripts/guard/packs/dns.py$CLAUDE_PLUGIN_ROOT/hooks/scripts/guard/packs/credentials.py
Present a summary organized by tier:
Format
claude-guard status
==================
Tier 1: Hard Deny (catastrophic, must run manually)
- filesystem: N patterns
- disk: N patterns
- database: N patterns
- kubernetes: N patterns
- aws: N patterns
- gcp: N patterns
- github-cli: N patterns
- dns: N patterns
Tier 2: Deny + Redirect (safer alternative suggested)
- git: N patterns
- filesystem: N patterns
- docker: N patterns
- database: N patterns
- kubernetes: N patterns
- permissions: N patterns
- aws: N patterns
- gcp: N patterns
- azure: N patterns
- terraform: N patterns
- pulumi: N patterns
- cdk: N patterns
- github-cli: N patterns
- dns: N patterns
Tier 3: Warn (credential scanner)
- credential patterns: N patterns
- destructive SQL: N patterns
Allowlisted safe patterns: N patterns
Pipeline features:
- Command normalization: path stripping, whitespace collapse, env prefix removal
- Context classification: string literal / comment / execution bridge detection
- Explain mode: set CLAUDE_GUARD_EXPLAIN=1 for pipeline trace on stderr
If a category argument is provided (e.g., /claude-guard:status git), show the detailed patterns for that category including the blocked command regex and the safe alternative.
Count patterns by parsing the Python source files directly — do not hardcode counts.
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.
- yesterday First seen · 71 lines · 13 tokens per session scan A 0819e9bf10d1
status is a command published in the GitHub repository hex/claude-guard (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 539 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
VibeGuard: Check
Run all guard scripts with one click and output project health report.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
safe-build
Build the application for development or production.
update
Use when: search results seem noisy, after bulk imports, or for periodic memory/registry maintenance.
test
Run Postman collection tests, analyze results, diagnose failures, and suggest fixes.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…