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 dcosson/h2 --skill e2e-wiring-reviewgit clone --depth 1 https://github.com/dcosson/h2Wrote 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/dcosson/h2/e2e-wiring-review)<a href="https://agentmods.dev/skills/dcosson/h2/e2e-wiring-review"><img src="https://agentmods.dev/badge/skills/dcosson/h2/e2e-wiring-review/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/dcosson/h2/e2e-wiring-review"><img src="https://agentmods.dev/badge/skills/dcosson/h2/e2e-wiring-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.02370 |
| Opus 5.5 | $0.00026 | $0.00948 |
| Sonnet 5.5 | $0.00013 | $0.00474 |
| Haiku 4.5 | $0.00006 | $0.00237 |
Grade A, and why
e2e-wiring-review 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 1mo 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-to-End Wiring Review
Systematically audit a component or application from the perspective of its end users. Start at every user-facing entry point — however users interact with the system (loading a web page, calling an API, running a CLI command, connecting via a protocol, tapping a button) — and trace each interaction through every layer of the system to verify it actually works end-to-end.
The goal is to find dead code, stubs, hardcoded behavior, and unwired paths where individual pieces may exist in isolation but are never reachable from the outside.
This is NOT a code quality review. It is a wiring audit: does the system actually work end-to-end for every flow the specs/plans describe?
Inputs
$0: Component or feature name (e.g.,search,checkout,auth,cli)$1...(optional): Plan docs, specs, or design docs to compare against- Output:
docs/reviews/{component}-e2e-wiring-audit.md
Critical Rules
- Start from the user's perspective. Identify how end users interact with the system and trace inward from there. Do NOT start from internal code and assume it's reachable.
- Every claim must cite code. "X is wired" must reference the specific file and line where the connection happens. "X is stubbed" must show the stub.
- Compare against specs/plans. Every feature or endpoint specified in design docs, specs, or requirements must be checked. If a spec says it exists, verify it actually works end-to-end.
- Check runtime, not just compile time. Code may compile and pass unit tests but never be instantiated at runtime (e.g., a service that's never registered, a route that's never mounted, a constructor that's never called during startup). Look for this pattern specifically — it is the most common wiring miss.
Phase 1: Enumerate User-Facing Entry Points
Identify every way a user (human or machine) interacts with the system. The entry points depend on the type of application:
Web Applications
- Pages/routes (URLs users visit)
- Forms and interactive elements
- WebSocket connections
- OAuth/SSO callback URLs
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.
- 1mo ago First seen · 232 lines · 65 tokens per session scan A 265f10338cd9
e2e-wiring-review is a skill published in the GitHub repository dcosson/h2 (163 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 2,370 once invoked, about $0.0003 per session on Opus 5.5. 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
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
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.
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
webapp-qa
Perform scoped exploratory QA of a web application, reproduce defects, collect screenshots and console evidence, and deliver a prioritized report.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…