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/stackhawk/agent-skillsWrote 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/stackhawk/agent-skills/stackhawk-api-hawk-op)<a href="https://agentmods.dev/rules/stackhawk/agent-skills/stackhawk-api-hawk-op"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-api-hawk-op/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/rules/stackhawk/agent-skills/stackhawk-api-hawk-op"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-api-hawk-op.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 | $0.00061 | $0.03048 |
| Opus 5.5 | $0.00024 | $0.01219 |
| Sonnet 5.5 | $0.00012 | $0.00610 |
| Haiku 4.5 | $0.00006 | $0.00305 |
Grade B, and why
stackhawk-api-hawk-op scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
curl -fsSL "$url" -o hawk && chmod +x hawk && sudo mv hawk /usr/local/bin/hawk Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
url=$(curl -fsSL "$MANIFEST" | jq -r --arg g "$GROUP" \ How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hawk op Shortcuts — StackHawk API, one command at a time
Cheat sheet: user intent → hawk op command. hawk op --help and
hawk op <cmd> --help are the canonical flag references.
See SKILL.md for the full workflow.
Setup (once) {#setup-once}
Install the combined hawk CLI — a single self-contained binary (no Java needed).
macOS — Homebrew (recommended):
brew tap stackhawk/cli
brew trust stackhawk/cli
brew install hawk
Otherwise resolve the binary from the manifest (the source of truth for the version
and every download URL, https://download.stackhawk.com/hawkdocs/hawk.manifest.json):
# macOS / Linux — resolve the right binary from the manifest, then install
MANIFEST=https://download.stackhawk.com/hawkdocs/hawk.manifest.json
case "$(uname -s)/$(uname -m)" in
Darwin/arm64) GROUP=darwin-arm64 ;;
Darwin/x86_64) GROUP=darwin-x64 ;;
Linux/x86_64) GROUP=linux-x64 ;;
Linux/aarch64|Linux/arm64) GROUP=linux-aarch64 ;;
esac
url=$(curl -fsSL "$MANIFEST" | jq -r --arg g "$GROUP" \
'.latest.assets[] | select(.asset.group == $g and (.url | endswith("/hawk"))) | .url')
curl -fsSL "$url" -o hawk && chmod +x hawk && sudo mv hawk /usr/local/bin/hawk
URL pattern: https://download.stackhawk.com/hawk/<version>/<group>/hawk[.pkg|.exe|.msi]
(<group>: darwin-arm64, darwin-x64, linux-x64, linux-aarch64, windows-x64,
windows-arm64). macOS .pkg and Windows .msi installers are also available —
see https://docs.stackhawk.com/downloads/.
hawk init --browser # Browser device-flow auth; writes ~/.hawk/hawk.properties
hawk op status # Confirm auth
hawk init writes credentials to ~/.hawk/hawk.properties.
hawk op reads that file plus the HAWK_API_KEY env var.
Non-interactive sessions (CI, containers, headless agents): set HAWK_API_KEY directly as a secret.
Org ID and output format can be set via env vars:
export HAWK_API_KEY=<your-api-key> # from app.stackhawk.com → Settings → API Keys
export HAWK_ORG_ID=<org-uuid>
export HAWK_FORMAT=json
hawk op app list
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 Changed f11d86557b81
- 1mo ago First seen · 306 lines · 61 tokens per session scan B 26d644bafe10
stackhawk-api-hawk-op is a cursor rule published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 3,048 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).