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-optimize)<a href="https://agentmods.dev/rules/stackhawk/agent-skills/stackhawk-optimize"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-optimize/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-optimize"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-optimize.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 | $0.00098 | $0.01750 |
| Opus 5.5 | $0.00039 | $0.00700 |
| Sonnet 5.5 | $0.00020 | $0.00350 |
| Haiku 4.5 | $0.00010 | $0.00175 |
Grade A, and why
stackhawk-optimize 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize Skill
Turn a codebase into an optimal HawkScan configuration. The skill detects the real tech
stack and app shape, expresses that as a trial scan policy (tech flags + plugins) plus
local stackhawk.yml corrections, runs one trial scan so the user sees real results, and
then promotes the setup or discards it with no residue.
Why a trial policy (not editing the app)
Org scan policies are stored as hosted assets and downloaded by the scanner at scan time
when app.scanPolicy.name is set (see references/trial-lifecycle.md). Creating a trial
policy and referencing it in stackhawk.yml therefore leaves the application's own policy,
plugins, and tech flags untouched until the user promotes. This is the core safety
property.
Preflight (run before anything else)
# Identify the driving skill for CLI usage telemetry (read by hawk/hawkop).
export _STACKHAWK_SKILL=optimize
- CLI versions / auth — reuse the hawkscan skill's preflight (
hawk version,hawk config --help,hawk opauth). Additionally confirm the policy write commands exist:hawk op policy create --helpmust succeed. If it errors with "unrecognized subcommand", STOP and tell the user to upgrade hawk. Also confirm metrics support:hawk op scan metrics --helpmust succeed. If it errors with "unrecognized subcommand", the metrics/refine phase is skipped (pre-scan optimization still works); tell the user to upgrade hawk to enable refinement. - App + env — resolve the target app and env. If the app is not onboarded, defer to the hawkscan skill's onboarding, then return here.
- Permissions / feature flag — the org needs
ORG_POLICY_MANAGEMENT+WRITE_POLICY/DELETE_POLICY. If apolicy createdry-run reports a permission/feature error, degrade to recommend-only: print the proposed policy JSON + yml diff and stop.
Workflow
Two modes. Setup configures scan policy + tech flags (no scan) and is what hawkscan
Phase 0c invokes on every fresh stackhawk.yml; it is also re-runnable anytime via /optimize. Refine runs a trial
scan and tunes from per-path metrics; it runs only via /optimize or when a scan is slow.
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 d395cb7fef3c
- 1mo ago First seen · 115 lines · 98 tokens per session scan A 925ada344cc4
stackhawk-optimize is a cursor rule published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 9d ago), licensed MIT. It adds 98 tokens to every session and 1,750 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).