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 skills/stackhawk/agent-skills/optimizenpx skills add stackhawk/agent-skills --skill optimizegit 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 | $0.00213 | $0.01877 |
| Opus 5 | $0.00106 | $0.00938 |
| Sonnet 5 | $0.00043 | $0.00375 |
| Haiku 4.5 | $0.00021 | $0.00188 |
Grade A, and why
optimize 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- stackhawk-optimize — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize Skill
Turn a codebase into an optimal HawkScan configuration. The skill detects the real tech
stack and app shape, expresses that as a trial scan policy (tech flags + plugins) plus
local stackhawk.yml corrections, runs one trial scan so the user sees real results, and
then promotes the setup or discards it with no residue.
Why a trial policy (not editing the app)
Org scan policies are stored as hosted assets and downloaded by the scanner at scan time
when app.scanPolicy.name is set (see references/trial-lifecycle.md). Creating a trial
policy and referencing it in stackhawk.yml therefore leaves the application's own policy,
plugins, and tech flags untouched until the user promotes. This is the core safety
property.
Preflight (run before anything else)
# Identify the driving skill for CLI usage telemetry (read by hawk/hawkop).
export _STACKHAWK_SKILL=optimize
- CLI versions / auth — reuse the hawkscan skill's preflight (
hawk version,hawk config --help,hawk opauth). Additionally confirm the policy write commands exist:hawk op policy create --helpmust succeed. If it errors with "unrecognized subcommand", STOP and tell the user to upgrade hawk. Also confirm metrics support:hawk op scan metrics --helpmust succeed. If it errors with "unrecognized subcommand", the metrics/refine phase is skipped (pre-scan optimization still works); tell the user to upgrade hawk to enable refinement. - App + env — resolve the target app and env. If the app is not onboarded, defer to the hawkscan skill's onboarding, then return here.
- Permissions / feature flag — the org needs
ORG_POLICY_MANAGEMENT+WRITE_POLICY/DELETE_POLICY. If apolicy createdry-run reports a permission/feature error, degrade to recommend-only: print the proposed policy JSON + yml diff and stop.
Workflow
Two modes. Setup configures scan policy + tech flags (no scan) and is what hawkscan
onboarding invokes; it is also re-runnable anytime via /optimize. Refine runs a trial
scan and tunes from per-path metrics; it runs only via /optimize or when a scan is slow.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 126 lines · 213 tokens per session scan A 4132710de1e8
optimize is a skill published in the GitHub repository stackhawk/agent-skills (15 stars, last pushed 12d ago), licensed MIT. It adds 213 tokens to every session and 1,877 once invoked, about $0.0011 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…