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-model)<a href="https://agentmods.dev/rules/stackhawk/agent-skills/stackhawk-hawkscan-model"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-hawkscan-model/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-model"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-hawkscan-model.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 | $0.00111 | $0.04092 |
| Opus 5.5 | $0.00044 | $0.01637 |
| Sonnet 5.5 | $0.00022 | $0.00818 |
| Haiku 4.5 | $0.00011 | $0.00409 |
Grade A, and why
stackhawk-hawkscan-model 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 — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StackHawk Platform Model
Deep reference for the object model behind every HawkScan run. Read this
when the primer in SKILL.md isn't enough, when you see an unexpected
findings[].paths[].status value, or when deciding whether to create a
new App / Env.
Table of Contents
- The Four Objects in Detail
- What Goes in
stackhawk.yml(and What Doesn't) - The Finding Lifecycle (Triage States)
- Tags and Commit Traceability
- Technology Flags
- Rescan: Derived Scans for Fast Fix Verification
- Create vs. Reuse Decision Tree
- Cross-Reference to the api Skill
The Four Objects in Detail
Organization (orgId)
The tenant. A UUID tied to your StackHawk account. Set implicitly by your
HAWK_API_KEY (each key is scoped to one org); you rarely reason about it
directly. hawk op org get shows the active org.
Most customers have a single org. Multi-org setups exist (consultancies,
MSSPs) — when present, every hawk op command accepts --org <ID> or uses
named profiles (hawk op -P <profile> app list).
Not in stackhawk.yml. Implicit via auth.
Application (applicationId)
The long-lived object representing "the thing you're scanning." Each App:
- Has a stable UUID (shown as
applicationIdin configs, APIs, everywhere) - Has a name (human-readable — used for
hawk op app listlookups) - Has a team ownership assignment
- Has technology flags that shape scan rule selection (see §5)
- Is scanned across one or more Environments
An App lives for the lifetime of the thing you're protecting. Renaming a repo, refactoring, changing languages — none of these should produce a new App. New Apps are for genuinely new services.
In stackhawk.yml: app.applicationId.
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 · +1 lines d0353703afe8
- 1mo ago First seen · 413 lines · 111 tokens per session scan A 80cff131d5fd
stackhawk-hawkscan-model is a cursor rule published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 8d ago), licensed MIT. It adds 111 tokens to every session and 4,092 once invoked, about $0.0004 per session on Opus 5.5. 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
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).