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 pedroiff0/awesome-skills --skill adhoc-verificationgit clone --depth 1 https://github.com/pedroiff0/awesome-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/skills/pedroiff0/awesome-skills/adhoc-verification)<a href="https://agentmods.dev/skills/pedroiff0/awesome-skills/adhoc-verification"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/adhoc-verification/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/pedroiff0/awesome-skills/adhoc-verification"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/adhoc-verification.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 | $0.00086 | $0.00956 |
| Opus 5 | $0.00043 | $0.00478 |
| Sonnet 5 | $0.00017 | $0.00191 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
adhoc-verification 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 8d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad-hoc local verification harness
Use this when you need to prove a specific change works, the full suite is
slow/irrelevant, or a post-edit system reminder demands "fresh passing
verification evidence." This is NOT a substitute for npm test when the suite
is fast — prefer the canonical suite. But a focused harness is the right tool
for one targeted behavior, or to satisfy a reminder cheaply.
When to reach for this
- A
systemreminder asks for ad-hoc verification of changed paths. - You changed one middleware/route and want a 10-second check instead of the full 30s suite.
- You need to demonstrate a negative property (e.g. "instance B rejects a cookie minted by instance A") that the suite doesn't isolate.
Steps
- Write the script INSIDE the package directory (e.g.
app/), never in/tmp. A script in/tmpcannot resolve the project'snode_modules/(require('supertest')→MODULE_NOT_FOUND). Name it./hermes-verify-*.jsso it's obviously throwaway and matches the reminder's prefix suggestion. - No Jest globals.
describe/it/beforeAll/afterAllare undefined in a plainnoderun — they crash withReferenceError. Instead wrap everything in an async IIFE and call the project's own DB setup/teardown helpers manually (e.g.setupDb(),teardownDb(),clearDb()from the test helpers), insidetry/finally. - Require the app factory, set env first. Set
process.env.*(NODE_ENV, JWT_SECRET, feature flags) BEFORErequire('./src/app'), because the app reads flags at construction time. If you re-instantiate with different env, restore the prior env after, or build each instance in its own closure. - Drive with supertest:
await request(app).get('/path').set('Cookie', ...). Assert onres.statusandres.text/body. PrintPASS:/FAIL:lines andprocess.exit(nonZeroOnFailure). - Run, then delete:
node ./hermes-verify-x.jsthenrm ./hermes-verify-x.js.
Critical pitfall: single-instance masking of isolation bugs
A SINGLE app instance with a feature flag on will apply that middleware to ALL
matching paths — so "isolation" between two security contexts cannot be shown
with one instance. To verify that instance A ignores/rejects a token from
instance B (different secret/cookie), you MUST build TWO separate createApp()
instances, each with its own env, and:
- mint a "foreign" cookie by signing a JWT with a different secret than the
instance under test (
jwt.sign(payload, 'other-secret-32+', ...)); - assert the instance UNDER TEST ignores/overwrites it (e.g. demo autologin returns 200 despite a foreign cookie) AND that the instance WITHOUT autologin rejects it (redirects / 401).
What ships with it
2 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.
- 8d ago First seen · 65 lines · 86 tokens per session scan A 308e10774241
adhoc-verification is a skill published in the GitHub repository pedroiff0/awesome-skills (1 stars, last pushed 5d ago), licensed MIT. It adds 86 tokens to every session and 956 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 2026-09-03.
Other skills, from other repositories
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
qa
Read-only automated QA sweep of a deployed stardust site on AEM Edge Delivery Services — validates routing, content fidelity vs the source capture, template conformance, rendered integrity (geometry, JS errors, broken images), visual regression vs baselines, metadata/SEO/JSON-LD, link integrity, accessibility (axe)…
debugging
Playwright test debugging conventions for the scaffold — reading failure messages, classifying failure modes (TimeoutError, ZodError, strict-mode violation, locator not found, network errors, schema drift), the playwright.config.ts capture defaults (trace on-first-retry, screenshot only-on-failure, video…
dogfood
This skill guides you through systematic exploratory QA testing of web applications using the browser toolset. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.
playwright-trace-analyzer
Analyzes Playwright E2E trace.zip archives (and bare trace JSONL when unpacked). Extracts the action timeline, network waterfall, console errors, and DOM-snapshot anchors, then identifies the highest-impact problems (flaky waits, slow selectors, network bottlenecks, hung actions, unhandled console errors, navigation…