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/nodnarbnitram/claude-code-extensions/security-scangit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWhat 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 | $0.00015 | $0.00520 |
| Opus 5 | $0.00008 | $0.00260 |
| Sonnet 5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
security-scan 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 2d 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.
What it actually says
Security Scan Command
Run language-specific security scanners on the specified path or entire project.
Task
-
Determine scan target:
- If
$1is provided, use it as the target path - If no argument, scan the entire project (current directory)
- If
-
Detect languages in the target path:
- Use Glob to find file types:
**/*.py,**/*.go,**/*.{js,jsx,ts,tsx} - Determine which security tools are needed
- Use Glob to find file types:
-
Run security scans (using
uvx/npxfor on-demand tool execution):- Python files → Use
bandit(https://github.com/PyCQA/bandit)- Run:
uvx bandit -r $TARGET -f screen(or-f jsonfor JSON output)
- Run:
- Go files → Use
gosec(https://github.com/securego/gosec)- Check:
gosec -version - Install if missing:
go install github.com/securego/gosec/v2/cmd/gosec@latest - Run:
gosec -fmt=text ./...(or-fmt=json)
- Check:
- JS/TS files → Use
ultracite(https://www.ultracite.ai/usage)- Run:
npx ultracite check(checks for security and quality issues) - Alternative:
npx ultracite fix(auto-fixes issues where possible)
- Run:
- Python files → Use
-
If Go tools are missing:
- Ask user if they want to install
gosec
- Ask user if they want to install
-
Report findings:
- Parse output and summarize security issues by severity
- Show high/medium/low severity counts
- List critical findings with file locations
- Provide recommendations for fixing issues
Target Path
${1:-.}
Notes
- Use
uvxfor Python tools (no installation required) - Use
npxfor JS/TS tools (no installation required) - For Go tools, check availability and offer installation
- Handle cases where no files of a given type exist
- Provide clear, actionable security recommendations
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.
- 2d ago First seen · 52 lines · 15 tokens per session scan A bb5245865b92
security-scan is a command published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 520 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.