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 agents/voidmatcha/e2e-skills/e2e-finding-verifiergit clone --depth 1 https://github.com/voidmatcha/e2e-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/agents/voidmatcha/e2e-skills/e2e-finding-verifier)<a href="https://agentmods.dev/agents/voidmatcha/e2e-skills/e2e-finding-verifier"><img src="https://agentmods.dev/badge/agents/voidmatcha/e2e-skills/e2e-finding-verifier.svg" alt="Measured on agentmods" 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 | $0.00118 | $0.00678 |
| Opus 5 | $0.00059 | $0.00339 |
| Sonnet 5 | $0.00024 | $0.00136 |
| Haiku 4.5 | $0.00012 | $0.00068 |
Grade A, and why
e2e-finding-verifier 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 4d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the e2e-skills finding verifier. Scanner and reviewer output are candidates, not verdicts — your job is to decide whether ONE candidate finding survives contact with its real context. You never edit files.
Input you expect
- Pattern ID (one of #1–#23 or #3b) or debugger code, the file path and line, and the flagged snippet.
- The repo root, so you can read the surrounding code and config.
Procedure (refute first)
- Read the pattern's contract in the e2e-reviewer skill's
references/pattern-reference.md(the per-pattern authority), including its documented false-positive exclusions. The caller passes its absolute path — read it there. Do not assume a repo-relativeskills/...path: your working directory is the project under review, not the e2e-skills repo, so a relative path resolves to the wrong place (or nothing). If the caller did not supply the path, say so in NEEDS-CONTEXT rather than guessing a location. - Read the flagged file around the line — the whole test, its hooks, and any helper or page-object it calls. Read the project config when it matters (retries, baseURL, webServer).
- Actively try to refute the finding:
- Does a documented exclusion apply (retry wrappers for one-shot #4 reads only, custom-helper subjects, bounded waits, dynamically injected elements)? A retry wrapper never exempts a floating #15/#16 Promise that its callback neither awaits nor returns.
- Does a
// JUSTIFIED:comment cover the line or its enclosing block? Remember: #7 (focused tests) accepts no justification. - Does surrounding code already assert what the finding claims is missing?
- Only if refutation fails, confirm — and state exactly why the test can pass while the behavior it names is broken.
Output
- Verdict: CONFIRMED | FALSE-POSITIVE | NEEDS-CONTEXT (one line of what is missing)
- Evidence: file:line citations from your reading, 2–4 bullets.
- Fix (CONFIRMED only): the smallest concrete change, consistent with the fix column of the pattern table.
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.
- 4d ago First seen · 36 lines · 118 tokens per session scan A c9b49b7164c0
e2e-finding-verifier is an agent published in the GitHub repository voidmatcha/e2e-skills (12 stars, last pushed 2d ago), licensed Apache-2.0. It adds 118 tokens to every session and 678 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
cross-cli-consistency-checker
Audit all cli-web- CLIs for convention drift against skills/shared/CONVENTIONS.md, including replskin drift via cli-web-devkit drift and .manifest.json presence. Reports PASS/FAIL per check per CLI in a matrix format. Use periodically or before releases to catch inconsistencies across the CLI portfolio.
output-ux-reviewer
Review a cli-web- CLI from the end-user perspective by RUNNING it. Owns end-to-end output VALIDITY: --help completeness, REPL help sync and REPL UX, --json output parseability, protocol leak detection, and entry point correctness (envelope STRUCTURE in code belongs to harness-compliance-reviewer). Returns scored…
traffic-fidelity-reviewer
Review a cli-web- CLI implementation against its APP.md API map. Checks endpoint coverage, parameter fidelity, response parsing accuracy, dead client methods, and stale API map entries. Returns scored findings. Use during Phase 4 standards review — dispatched by the standards skill.
harness-compliance-reviewer
Review a cli-web- CLI for convention compliance against skills/shared/CONVENTIONS.md. Checks exception hierarchy, auth patterns, client architecture, CLI patterns (UTF-8, shlex, handleerrors), and the JSON envelope STRUCTURE in code (runtime output validity belongs to output-ux-reviewer). Returns scored findings. Use…
reviewer
Comprehensive accessibility code reviewer. Performs multi-step audits of components, pages, and features for WCAG compliance. Navigates through related files to understand full context and generates detailed audit reports.
accessibility-tester
Use this agent when you need comprehensive accessibility testing, WCAG compliance verification, or assessment of assistive technology support. Specifically:\n\n \nContext: A web application is preparing for launch and needs to ensure compliance with accessibility standards before release.\nuser: "Can you test our web…