Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rengwu/wayfinder-mapsnpx agentmods add skills/rengwu/wayfinder-maps/verifyWrote 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/rengwu/wayfinder-maps/verify)<a href="https://agentmods.dev/skills/rengwu/wayfinder-maps/verify"><img src="https://agentmods.dev/badge/skills/rengwu/wayfinder-maps/verify/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/rengwu/wayfinder-maps/verify"><img src="https://agentmods.dev/badge/skills/rengwu/wayfinder-maps/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Rogue Agent · line 56 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 60 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00025 | $0.00771 |
| Opus 5 | $0.00013 | $0.00385 |
| Sonnet 5 | $0.00005 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
verify 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 9d 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.
failure only shows in the log while curl happily talks to the OLD server — check How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying wayfinder-maps
Build & fixture
go build -o /tmp/wayfinder-maps ./cmd/wayfinder-maps
There is no sample map in the repo. Create an effort dir with map.md +
tickets/NN-slug.md. Ticket format: YAML frontmatter (type:, blocked_by: [01],
claimed_by:, undermined_by: [NN]) then # Title, ## Question; a ## Answer
section with prose = resolved, ## Ruled out = out_of_scope. Map format: # Name,
## Destination, and fog under ## Not yet specified as
- **Title.** clears-with: NN. Sanity-check the fixture with
wayfinder-maps status <effort-dir>.
Launch
PORT=78xx /tmp/wayfinder-maps serve <effort-dir> # pick a fresh port EVERY time
Gotcha: the user often has an instance (binary wm) already listening; a bind
failure only shows in the log while curl happily talks to the OLD server — check
the serve log says "serving", don't trust the port being answerable.
Dev mode: WAYFINDER_DEV=cmd/wayfinder-maps/web (path to web/ from cwd) serves
the frontend from disk with Cache-Control: no-store instead of the go:embed copy.
Drive (GUI surface)
Playwright's cached headless shell works without a full playwright install:
cd <scratch> && npm i playwright-core
# executablePath: ~/Library/Caches/ms-playwright/chromium_headless_shell-*/chrome-headless-shell-mac-arm64/chrome-headless-shell
- Wait ~4s after goto: the constellation fades in over 2.2s (a plain
--screenshot --virtual-time-budgetcapture shows HUD but NO stars — artifact, not a bug). - App state is inside ES modules (not on window). To click a specific star, find it by pixel colour on the canvas (frontier glow is gold) — layout is deterministic (fixed PRNG seed), so positions repeat across runs.
- Live-reload probe: append
## Answer\ntextto a ticket while the map is open; the 1.5s poller updates the HUD counts in ~2-3s. - Recents on the splash come from the user's real config — don't dismiss entries.
Flows worth driving: map render (all statuses + fog + edges), click star → panel
markdown, data-goto cross-ticket link, Escape closes, wheel zoom (labels thin
out), back button → splash/maplist.
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.
- 9d ago First seen · 70 lines · 25 tokens per session scan A f9d612a4fbf5
verify is a skill published in the GitHub repository rengwu/wayfinder-maps (121 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 771 once invoked, about $0.0001 per session on Opus 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 skills, from other repositories
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.