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-mapping)<a href="https://agentmods.dev/rules/stackhawk/agent-skills/stackhawk-optimize-mapping"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-optimize-mapping/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-mapping"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-optimize-mapping.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 | $0.00059 | $0.00582 |
| Opus 5.5 | $0.00024 | $0.00233 |
| Sonnet 5.5 | $0.00012 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
stackhawk-optimize-mapping 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase → Config Mapping
Tech flags
Reuse the hawkscan skill's tech-flag detection heuristics (linked from the Companion
skills section of SKILL.md) — evidence files such as package.json, pom.xml, go.mod,
requirements.txt, docker-compose.yml, Gemfile, *.csproj/*.sln.
Map detected techs to canonical flag keys. The canonical flag list is authoritative — fetch
it with hawk op app tech-flags get --app <APP> --format json and only use keys that exist.
When enabling a child flag (e.g. Language.Java.Spring), also enable its parents.
Plugins
Start from a base preset that matches the app shape:
- Plain REST/HTML app →
DEFAULT - OpenAPI-described API →
DEFAULT_API - GraphQL API → the GraphQL preset (confirm exact name via
hawk op policy list)
Fetch the base with hawk op policy get --name <PRESET>. Then:
- DROP plugin families irrelevant to the detected stack (reduces noise + time).
- KEEP/ADD families the stack needs.
Validate every plugin id against the base policy's plugin list — never invent ids.
Edit the fetched JSON as little as possible: keep every field on every plugin entry (dropping
pluginTypesilently removes the passive rules) and never writeSTRENGTH_LOW/THRESHOLD_LOW(protobuf zero values are dropped on serialization, leaving the plugin with no strength/threshold). Keep the preset's values; never delete or blank them.
stackhawk.yml correctness
- App type: SPA → enable SPA/spider settings; REST → leave spider conservative.
- OpenAPI spec present → set
app.openApiConfto point at it. - GraphQL → wire
app.graphqlConfand keep the broad GraphQL preset as the first-scan policy. Do not narrow the plugin set before one broad scan has completed (app.autoPolicy: truenarrows the plugin set; leave it unset for the first broad scan). Prune after. - Base paths → set sensible scope.
- Auth → FLAG for the user; never fabricate credentials.
Profile lean
Default balanced. A speed lean drops more borderline plugin families and tightens scope; a coverage lean keeps families when in doubt. Only deviate from balanced if the user explicitly asks.
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 · +6 lines ca5e383660a0
- 1mo ago First seen · 39 lines · 59 tokens per session scan A 44cc50efeb0d
stackhawk-optimize-mapping is a cursor rule published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 8d ago), licensed MIT. It adds 59 tokens to every session and 582 once invoked, about $0.0002 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).