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 skills add borski/travel-hacking-toolkit --skill southwestgit clone --depth 1 https://github.com/borski/travel-hacking-toolkitWrote 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/skills/borski/travel-hacking-toolkit/southwest)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/southwest"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/southwest/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/skills/borski/travel-hacking-toolkit/southwest"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/southwest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 17 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 21 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 22 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 25 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 29 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 126 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 199 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 203 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 298 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 302 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 306 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 69 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- low Tool Misuse · line 21 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- low Tool Misuse · line 22 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- low Tool Misuse · line 126 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- low Tool Misuse · line 298 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- low Tool Misuse · line 302 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- low Tool Misuse · line 306 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00040 | $0.03853 |
| Opus 5 | $0.00020 | $0.01927 |
| Sonnet 5 | $0.00008 | $0.00771 |
| Haiku 4.5 | $0.00004 | $0.00385 |
Grade A, and why
southwest 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 11d 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.
Southwest Airlines Search
Search southwest.com via Patchright (undetected Playwright fork). Southwest is the only major US airline not in any GDS, API, or flight search tool. This skill is the only way to get SW-specific data: fare classes, points pricing, and Companion Pass qualification.
Requires Patchright (undetected Playwright fork). Standard Playwright and agent-browser are detected and blocked by SW. Patchright patches the browser fingerprint to bypass detection.
Must run headed (headless=False). SW detects headless browsers even with Patchright. On macOS, a Chrome window briefly appears and closes. For background operation with no popup, use Docker:
# Search new flights (default, no login needed)
docker run --rm ghcr.io/borski/sw-fares --origin SJC --dest DEN --depart 2026-05-15
docker run --rm ghcr.io/borski/sw-fares --origin SJC --dest DEN --depart 2026-05-15 --return 2026-05-18 --points --json
# Check existing reservation for price drops (requires SW login)
docker run --rm -e SW_USERNAME -e SW_PASSWORD \
ghcr.io/borski/sw-fares change --conf ABC123 --first Jane --last Doe --json
# List all upcoming trips
docker run --rm -e SW_USERNAME -e SW_PASSWORD \
ghcr.io/borski/sw-fares change --list --json
# Build locally
docker build -t sw-fares skills/southwest/
The Docker image uses xvfb to create a virtual display inside the container. Patchright runs "headed" against xvfb, bypassing SW's headless detection without opening any windows on your machine.
# Install
pip install patchright && patchright install chromium
# Search cash fares
python3 scripts/search_fares.py --origin SJC --dest DEN --depart 2026-05-15
# Search cash + points
python3 scripts/search_fares.py --origin SJC --dest DEN --depart 2026-05-15 --return 2026-05-18 --points
# JSON output
python3 scripts/search_fares.py --origin SJC --dest DEN --depart 2026-05-15 --points --json
Key implementation details learned the hard way:
- Navigate to southwest.com homepage FIRST, then to the results URL. Direct URL without homepage warmup gets blocked.
- Use
fareType=POINTSURL parameter for points pricing. Don't try to click the Points toggle on the page. - Use a fresh persistent browser context (temp dir) each run to avoid fingerprint accumulation.
- Extract text from
[role='main']NOT<main>. The<main>element contains the booking form.[role='main']contains the flight results. - Flight blocks can be parsed by splitting on
# \d+patterns and ending atView seats. - Always dismiss the cookie banner first. It blocks interactions.
What ships with it
5 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.
- 11d ago First seen · 342 lines · 40 tokens per session scan A 28f0c559560a
southwest is a skill published in the GitHub repository borski/travel-hacking-toolkit (659 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 3,853 once invoked, about $0.0002 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
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.
browser_visible
Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…
dev-browser
Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, log into sites, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot"…
an
Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.