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-ci)<a href="https://agentmods.dev/rules/stackhawk/agent-skills/stackhawk-hawkscan-ci"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-hawkscan-ci/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-ci"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-hawkscan-ci.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 | $0.00000 | $0.04518 |
| Opus 5.5 | $0.00000 | $0.01807 |
| Sonnet 5.5 | $0.00000 | $0.00904 |
| Haiku 4.5 | $0.00000 | $0.00452 |
Grade A, and why
stackhawk-hawkscan-ci scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HawkScan CI Skill
This skill graduates a working local HawkScan setup into a CI/CD
pipeline. It is a wrapper around the local-scan path the hawkscan
skill owns — it never generates stackhawk.yml, never picks auth
recipes, never parses findings. Its scope is the pipeline file alone.
Hand-off rule: if stackhawk.yml doesn't exist or doesn't validate,
the agent must invoke the hawkscan skill first. This skill does not
onboard apps from scratch.
Step 0: Hand-off Check
Before doing anything CI-specific, confirm the local scan path is in place. Run:
test -f stackhawk.yml || echo "MISSING_CONFIG"
timeout 30 hawk validate config stackhawk.yml 2>&1 | head -20
If stackhawk.yml is missing, validation fails, or applicationId is
still a placeholder (${APP_ID} with no real value, or literal
your-app-id):
"I need a working local scan first. Run the hawkscan skill (or invoke it explicitly) to generate and validate
stackhawk.yml, then come back here."
Stop. Do not proceed. That message is the entire output: do not preview
the pipeline (no action names, images, secrets, triggers, or workflow
snippets) — the provider and shape are decided only once stackhawk.yml validates.
Step 1: Detect the CI Provider
Glob the repo for known CI config locations:
ls .github/workflows/*.yml .github/workflows/*.yaml 2>/dev/null
ls .gitlab-ci.yml 2>/dev/null
ls Jenkinsfile* 2>/dev/null
ls .circleci/config.yml 2>/dev/null
ls azure-pipelines*.yml 2>/dev/null
ls bitbucket-pipelines.yml 2>/dev/null
ls .buildkite/pipeline.yml 2>/dev/null
ls .travis.yml 2>/dev/null
ls -d bamboo-specs 2>/dev/null
ls concourse/*.yml 2>/dev/null
ls -d harness 2>/dev/null
ls appspec.yml buildspec.yml 2>/dev/null
| Match | Provider |
|---|---|
.github/workflows/*.yml, *.yaml |
GitHub Actions |
.gitlab-ci.yml |
GitLab CI/CD |
Jenkinsfile, Jenkinsfile.* |
Jenkins |
.circleci/config.yml |
CircleCI |
azure-pipelines*.yml |
Azure Pipelines |
bitbucket-pipelines.yml |
Bitbucket Pipelines |
.buildkite/pipeline.yml |
Buildkite |
.travis.yml |
Travis CI |
bamboo-specs/ |
Bamboo |
appspec.yml, buildspec.yml |
AWS CodeBuild / CodeDeploy |
concourse/*.yml (heuristic — confirm with user) |
Concourse |
harness/ |
Harness |
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.
- 23d ago Changed · +2 lines 17acf1ad8b23
- 1mo ago First seen · 340 lines · 0 tokens per session scan A 0af23349c7f6
stackhawk-hawkscan-ci is a cursor rule published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,518 tokens. 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
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
agents-shipgate
Run Agents Shipgate as the deterministic merge gate for AI-generated agent capability changes.
cursor-asdd
ASDD contribution rules for this repository.
agents
Agent engineering standards — Agents (TR-SEC-003).
infra-devops
Infrastructure, Cloud, Terraform, Docker & CI/CD Agent.
infrastructure
Terraform infrastructure-as-code standards for multi-cloud (AWS, GCP, Azure, OCI) provisioning.