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/stackhawk/agent-skills/stackhawk-hawkscan-cligit clone --depth 1 https://github.com/stackhawk/agent-skillsWhat 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 | $0.00057 | $0.02437 |
| Opus 5 | $0.00028 | $0.01218 |
| Sonnet 5 | $0.00011 | $0.00487 |
| Haiku 4.5 | $0.00006 | $0.00244 |
Grade A, and why
stackhawk-hawkscan-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HawkScan CLI Reference
The hawk CLI is preferred for local/agentic use — lower overhead than Docker,
faster iteration on config, and better localhost networking.
Option resolution order: CLI flag → API_KEY environment variable → ~/.hawk/hawk.properties. For local/agentic use, run hawk init --browser to write credentials to ~/.hawk/hawk.properties — no env var needed. For CI/CD pipelines, prefix invocations with API_KEY=$HAWK_API_KEY hawk ....
Contents
- Top-Level Options
- Setup
- Core Scan Commands
- Scan Flags for Agentic Loops
- Validation Commands
- hawk config
- Diagnostic Commands
- Perch (Daemon Mode)
- Subcommand Options
- Exit Codes
- Config File Path Rules
Top-Level Options
These go before the command (hawk [options] <command>):
hawk scan # after `hawk init --browser` — credentials from ~/.hawk/hawk.properties
hawk --no-color scan # strip ANSI escape codes (required for log parsing)
hawk --num-stored-sessions=4 scan # number of sessions to keep (default: 4)
hawk --log-roll-size=100MB scan # log file roll size (default: 100MB)
hawk --log-files-count=10 scan # max rolled log files to upload (default: 10)
Setup
hawk init --browser # first-time: browser device-flow auth, saves to ~/.hawk/hawk.properties
API_KEY=$HAWK_API_KEY hawk scan # CI/CD: pass key directly when no local config (pipelines, Docker)
Core Scan Commands
hawk scan # scan using stackhawk.yml in current directory
hawk scan stackhawk-ci.yml # scan with a specific config file
hawk scan base.yml override.yml # merge configs (later file wins)
hawk rescan # re-run plugins that fired on the most recent scan
hawk rescan --scan-id <SCAN_ID> # re-run plugins against a specific prior scan
hawk rescan --scan-id <SCAN_ID> --json-output # rescan + structured output for parsing
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 · 274 lines · 57 tokens per session scan A 4bab2323a5f2
stackhawk-hawkscan-cli is a cursor rule published in the GitHub repository stackhawk/agent-skills (15 stars, last pushed 12d ago), licensed MIT. It adds 57 tokens to every session and 2,437 once invoked, about $0.0003 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.