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-hawkscan-scan-policy)<a href="https://agentmods.dev/rules/stackhawk/agent-skills/stackhawk-hawkscan-scan-policy"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-hawkscan-scan-policy/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-hawkscan-scan-policy"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-hawkscan-scan-policy.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 | $0.00000 | $0.01479 |
| Opus 5.5 | $0.00000 | $0.00592 |
| Sonnet 5.5 | $0.00000 | $0.00296 |
| Haiku 4.5 | $0.00000 | $0.00148 |
Grade A, and why
stackhawk-hawkscan-scan-policy 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 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.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Policy Reference
How the scan policy is chosen, attached, and tuned across the first scan and any follow-up
full scans. Read this before Phase 0c and before starting a second full scan. Field syntax is
canonical in hawk config show app.scanPolicy --text; the optimize skill owns policy creation.
Contents
- First scan: one broad policy, run to completion
- Tech flags before the first scan
- Follow-up full scans: prune, do not crank
- Attaching a named org policy
- Hand-built policy traps
First scan: one broad policy, run to completion
- One broad policy for the detected stack. The first scan uses the preset that matches the
app shape (
DEFAULT,DEFAULT_API, or the GraphQL preset — confirm names withhawk op policy list) plus the detected tech flags, built by optimize Setup (Phase 0c). Not every plugin at HIGH strength; not a hand-picked subset. - Run it to completion. Do not stop it early and do not chain several long scans. The first completed broad scan reaches most of the findings any config can reach; further hours add a finding or two, and a follow-up at lowest threshold / HIGH strength adds time, not findings.
- Broadest scan last. When several full scans run in one env, the last completed scan is
the result on the platform. Ending on a narrow scan
(
includePathson a few routes, a reduced plugin set) replaces the broad result. Narrow diagnostic scans are fine mid-session; finish with the broad one.
Tech flags before the first scan
A newly created app has every tech flag enabled, so the scan runs rules for databases,
languages, and frameworks the app does not have and takes longer with no coverage gain. Before
the first scan, set the flags to the detected stack: optimize Setup does this in Phase 0c, and
SKILL.md Phase 0c gives the fallback when optimize is skipped or degrades to recommend-only.
Detection heuristics and flag names are in tech-flags.md; the hawk op app tech-flags commands
are in platform-model.md. If detection finds no evidence, leave the flags alone.
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 First seen · 92 lines · 0 tokens per session scan A 5ae8cd808080
stackhawk-hawkscan-scan-policy is a cursor rule published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,479 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 2026-09-17.
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).