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 rules/bugbasesecurity/pentest-copilot/tool-registration-checklistgit clone --depth 1 https://github.com/bugbasesecurity/pentest-copilotWrote 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/rules/bugbasesecurity/pentest-copilot/tool-registration-checklist)<a href="https://agentmods.dev/rules/bugbasesecurity/pentest-copilot/tool-registration-checklist"><img src="https://agentmods.dev/badge/rules/bugbasesecurity/pentest-copilot/tool-registration-checklist.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00374 |
| Opus 5 | $0.00000 | $0.00187 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
tool-registration-checklist 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 4d 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
Tool Registration Checklist
When adding or removing an agent tool, update ALL of these locations:
Backend (source of truth)
- Handler:
backend/src/tools/handlers/<tool-name>.ts— create/delete theToolDefinition - Registry:
backend/src/tools/registry.ts— import +toolRegistry.register() - Availability (if tool requires config):
backend/src/utils/toolAvailability.ts— add to unconfigured list when env var is missing
Frontend (must stay in sync with registry)
- Sidebar panel:
frontend/src/components/session/AgentToolsPanel.jsxTOOL_GROUPS— add the tool name to the appropriate group (or create a new group)TOOL_LABELS— add a human-readable label
- Chat transcript:
frontend/src/components/pages/session/sessionId/ToolCallBlock.jsxTOOL_LABELS— add the display labelformatArgsPreview()— add a one-liner showing the most useful arggetCodePreview()— optionally add syntax-highlighted preview (for script/command tools)
Notes
- The backend API (
GET /agent/session/:id/agent-tools-config) dynamically returns all registered tools fromtoolRegistry.getAll(), so the backend side is automatic after step 2. - The frontend filters tools through
TOOL_GROUPS— any tool not listed there won't appear in the sidebar even if the API returns it. - If the tool needs consent gating, set
requiresConsent: trueor implementshouldRequireConsentin the handler.
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.
- 4d ago First seen · 29 lines · 0 tokens per session scan A a332249860ba
tool-registration-checklist is a cursor rule published in the GitHub repository bugbasesecurity/pentest-copilot (1,340 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 374 tokens. 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 cursor rules, from other repositories
no-jumping-ahead
ALWAYS follow these rules when working on this codebase.
changelog-posts
How we do changelog posts and format them.
cursorrules
aggregatereports to keep SUMMARY.md and metadata.json synchronized.
ipynb-files
This file contains rules and prompts for handling Jupyter Notebook (.ipynb) files in Cursor IDE, which currently doesn't have native support for .ipynb files.
safari-automation
Patterns and best practices for automating Safari browser interactions for web UI automation and testing.
dependencies
Dependency management guidelines.