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-data-seedgit 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 | $0.00000 | $0.02436 |
| Opus 5 | $0.00000 | $0.01218 |
| Sonnet 5 | $0.00000 | $0.00487 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade A, and why
stackhawk-data-seed 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StackHawk Data Seed Skill
This skill produces checked-in, reproducible seed-data artifacts for a target repo so authenticated HawkScan finds non-empty results. The hawk perch seed command provides the deterministic steps — a static repo pre-flight (storage + upstream detection), a manifest validator, and an artifact finalizer. This skill supplies the reasoning between them: it reads the pre-flight's digest and designs the minimum seed manifest. It works the same across every agent that can run a subprocess and read its output.
It does NOT run the artifacts, start the environment, or write stackhawk.yml — those belong to the human, the user's tooling, and the hawkscan skill respectively.
When to Run
Invoke explicitly when:
- User says "set up data for HawkScan" / "seed this repo" / "my scan has no data to hit."
- Configuring HawkScan against a repo for the first time and the app needs authenticated routes to scan.
- A previous
data-seed/exists but the data shape changed (new entity types, new upstream service).
Do NOT run autonomously after code changes — this is a setup tool, not a per-commit safety net.
Phase 0: Preflight
0.1 — Confirm working directory
The user must invoke from inside the target repo (the repo HawkScan will scan):
test -d .git || echo "NOT-A-REPO"
pwd
If not a git repo, ask the user to cd to the target repo and re-invoke.
0.2 — Confirm hawk supports the seed flow (capability gate)
This skill drives the caller-driven hawk perch seed subcommands (validate and finalize). Probe for them directly:
# Identify the driving skill for CLI usage telemetry (read by hawk/hawkop).
export _STACKHAWK_SKILL=stackhawk-data-seed
if hawk perch seed validate --help >/dev/null 2>&1 && hawk perch seed finalize --help >/dev/null 2>&1; then
echo "SEED-FLOW-OK"
else
echo "SEED-FLOW-UNSUPPORTED"
fi
hawk version 2>/dev/null || hawk --version 2>/dev/null # for the message only; never gates
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 · 183 lines · 0 tokens per session scan A 13edf5516762
stackhawk-data-seed is a cursor rule published in the GitHub repository stackhawk/agent-skills (15 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,436 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
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.