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-failure)<a href="https://agentmods.dev/rules/stackhawk/agent-skills/stackhawk-hawkscan-ci-failure"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-hawkscan-ci-failure/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-failure"><img src="https://agentmods.dev/badge/rules/stackhawk/agent-skills/stackhawk-hawkscan-ci-failure.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 | $0.00061 | $0.02309 |
| Opus 5.5 | $0.00024 | $0.00924 |
| Sonnet 5.5 | $0.00012 | $0.00462 |
| Haiku 4.5 | $0.00006 | $0.00231 |
Grade A, and why
stackhawk-hawkscan-ci-failure scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
read -r version url < <(curl -fsSL https://download.stackhawk.com/hawkdocs/hawk.manifest.json \ How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Failure Semantics Reference
How HawkScan signals scan outcomes in CI, when to block vs warn, and how to think about retries and caching.
Exit Codes
| Exit code | Meaning | Pipeline action |
|---|---|---|
0 |
Scan ran; no findings at or above failureThreshold. |
Pass. |
1 |
Scan failed before producing results (config error, app unreachable, auth failure, invalid applicationId, internal scanner error). |
Fail. Do not retry — this is almost always a config issue that needs human attention. |
42 |
Scan ran; findings met or exceeded failureThreshold. |
Real finding. Either fail (block mode) or warn (warn-only mode), per the integration choice. |
Exit code 42 is the intended success path of failure — the scan worked, and it found something worth blocking on. Treating it like a flake (retrying, swallowing) defeats the purpose of running the scan.
failureThreshold — Tuning the Block Line
failureThreshold in stackhawk.yml decides which severity levels trip exit code 42:
app:
applicationId: ${APP_ID}
failureThreshold: High # one of: High, Medium, Low, All
| Value | Exit 42 when... |
|---|---|
High |
Any High finding is present (default; recommended for new pipelines) |
Medium |
Any Medium or High finding is present |
Low |
Any Low, Medium, or High finding is present |
All |
Any finding at all is present (often noisy) |
Tuning guidance:
- Start at
Highfor a new pipeline. You want the first month to be calibration — find out which severity levels your app actually produces, work through them, then ratchet down. - Drop to
Mediumonce the High-severity backlog is empty AND the team is committed to triaging Mediums within a sprint cadence. LowandAllare appropriate only for high-maturity teams with active triage processes; otherwise the noise drowns out real signal.
The hawkscan skill owns failureThreshold writes — this skill does not change it. If the user asks to "make CI less noisy," route them to the hawkscan skill for the config edit (which also handles excludePaths and excludePlugins).
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 First seen · 197 lines · 61 tokens per session scan A 62a3f150a675
stackhawk-hawkscan-ci-failure is a cursor rule published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 9d ago), licensed MIT. It adds 61 tokens to every session and 2,309 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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.