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-optimize-metricsgit 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 | $0.00074 | $0.01154 |
| Opus 5 | $0.00037 | $0.00577 |
| Sonnet 5 | $0.00015 | $0.00231 |
| Haiku 4.5 | $0.00007 | $0.00115 |
Grade A, and why
stackhawk-optimize-metrics 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Metrics → Refine Loop
After the trial scan, analyze its metrics and refine the config using real scan data.
This skill does NOT compute metrics — it consumes hawk op scan metrics.
Get the metrics
hawk op scan metrics <SCAN_ID> --format json
<SCAN_ID> is the trial scan's id (use the id returned by the trial scan; latest also works).
Output (MetricsJson):
{
"scan_id": "...",
"request_health": { "timeout": 0, "connection_failure": 0, "timeout_streak_max": 0 },
"scan_flags": ["timeout-prone"],
"paths": [
{
"method": "GET", "path": "/x", "total_requests": 100,
"status_counts": {"200": 90, "429": 10},
"class_2xx": 90, "class_3xx": 0, "class_4xx": 10, "class_5xx": 0,
"error_rate": 0.10,
"time": {"p50_bucket": 256, "p90_bucket": 4096, "max_bucket": 8192, "est_total_ms": 30000},
"flags": ["slow-path", "rate-limited"]
}
],
"operations": []
}
Useful read-only views (human framing): --sort {heaviest|slowest|erroring|most-requested},
--top N, --method <VERB>, --operations.
Flag → lever mapping
| Flag | Meaning | Lever | Tier | Goal |
|---|---|---|---|---|
rate-limited |
429s from target | lower hawk.scan.concurrentRequests |
auto | better+faster |
timeout-prone |
target overwhelmed/flaky (scan-level) | lower hawk.scan.concurrentRequests |
auto | reliability |
heavy-path |
path dominates est. scan time | app.excludePaths (or narrow includePaths) |
confirm | faster |
slow-path |
high p90 latency | app.excludePaths if low security value |
confirm | faster |
auth-wall |
>=50% 401/403 — route not actually tested | guide app.authentication.* (never fabricate creds) |
confirm / needs-input | better coverage |
server-erroring / error-prone |
app erroring under scan | surface for investigation; optionally app.excludePaths |
advisory / confirm | better findings |
Tiers
- auto = concurrency reductions ONLY (non-destructive, reversible, no coverage loss). Apply, then re-scan.
- confirm = anything that drops coverage (
app.excludePaths) or needs human input (app.authentication.*). Show the exact yml diff; apply only on explicit approval.
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 · 97 lines · 74 tokens per session scan A 75d7e1f7e9ee
stackhawk-optimize-metrics is a cursor rule published in the GitHub repository stackhawk/agent-skills (15 stars, last pushed 12d ago), licensed MIT. It adds 74 tokens to every session and 1,154 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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.