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-hawkscan-scan-planninggit 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 | $0.00088 | $0.03515 |
| Opus 5 | $0.00044 | $0.01758 |
| Sonnet 5 | $0.00018 | $0.00703 |
| Haiku 4.5 | $0.00009 | $0.00351 |
Grade A, and why
stackhawk-hawkscan-scan-planning 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Planning Reference (Discovery)
Discovery is how the hawkscan skill decides what to scan and how before it writes or
edits a single stackhawk.yml. Run it in three situations:
- First scan of a repo. No
stackhawk.ymlexists yet (SKILL.md Step 1a / Step 2a) — discovery produces the surface inventory that Step 2a's config generation consumes. - The quality gate looped back with a structural gap. A post-scan coverage check found routes the scan never reached, or a surface it didn't know existed. Re-run discovery against that specific gap rather than starting over.
- The user asks to re-plan the scan. New API surface added, a monorepo grew a service, an old assumption no longer holds.
Discovery is stateless: there is no plan file. stackhawk.yml is the only durable artifact,
and anything the user tells you that isn't a config field belongs as a comment in
stackhawk.yml or in the repo's CLAUDE.md/AGENTS.md — see "Ask, don't guess" below.
Work code-first, interactively: explore before asking, ask the user before guessing, and never stall waiting for information you could get by reading three more files or asking one direct question.
Contents
- Discover the app's API surfaces
- Recommend code changes for gaps
- Ask, don't guess
- Configure per surface
- Cross-checking
Discover the app's API surfaces
Pass 1 — read what the repo already says
Most repos document themselves. Read these, in priority order, before exploring code — treat what they say as authoritative and don't rediscover by grepping what a doc already states:
| Source | Typically documents |
|---|---|
AGENTS.md |
run/build/test commands, layout, conventions |
CLAUDE.md |
same, written for agents — often the richest source |
GEMINI.md, .github/copilot-instructions.md |
agent run/build guidance |
.cursor/rules/* |
project conventions and setup steps |
README* |
quickstart, run command, default host/port |
CONTRIBUTING* |
local dev setup, how to run services and tests |
docs/ setup / quickstart / architecture pages |
deeper API and service-boundary detail |
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 · 218 lines · 88 tokens per session scan A 549127d9a7e7
stackhawk-hawkscan-scan-planning is a cursor rule published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 12d ago), licensed MIT. It adds 88 tokens to every session and 3,515 once invoked, about $0.0004 per session on Opus 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
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.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.