stackhawk-hawkscan-scan-planning

A discovery guide for planning which parts of an application HawkScan should test before creating or editing its stackhawk.yml configuration. HawkScan is an application security scanner, and an API is a set of routes that software exposes for other software to call.

In plain words
What is it for?
Use it before a first scan, after adding routes or services, or when a scan misses part of a monorepo—a repository containing multiple related projects or services.
Why use it?
It reduces the risk of missing API routes or services because the scan plan is based on the code and project documentation instead of guesses.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/stackhawk/agent-skills/stackhawk-hawkscan-scan-planning
Clone the repo
git clone --depth 1 https://github.com/stackhawk/agent-skills

Made for: Cursor.

Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 549127d9a7e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

cursor/.cursor/rules/stackhawk-hawkscan-scan-planning.mdc · 218 lines

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.yml exists 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

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

Read the full file on GitHub · 218 lines

Changes

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.

  1. 2d ago First seen · 218 lines · 88 tokens per session scan A 549127d9a7e7

Subscribe to this mod's changes

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.