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 cyanheads/mcp-reporter --skill field-testgit clone --depth 1 https://github.com/cyanheads/mcp-reporterWrote 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/cyanheads/mcp-reporter/field-test)<a href="https://agentmods.dev/skills/cyanheads/mcp-reporter/field-test"><img src="https://agentmods.dev/badge/skills/cyanheads/mcp-reporter/field-test/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/cyanheads/mcp-reporter/field-test"><img src="https://agentmods.dev/badge/skills/cyanheads/mcp-reporter/field-test.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 | $0.00025 | $0.00392 |
| Opus 5 | $0.00013 | $0.00196 |
| Sonnet 5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
field-test 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 yesterday.
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.
What it actually says
Field test
Read CLAUDE.md, source and the full diff. Build the target list from every changed behavior, including complete pre-existing changes. Test the local build, not a globally installed or remote published version.
Run bun run devcheck, bun run rebuild, and bun run test:package. Tests use known synthetic fixtures; do not execute the user's local server config or start unrelated services.
Verify applicable boundaries:
- All four capability classes, full optional descriptor metadata, server identity/instructions and negotiated protocol version.
- Legacy default without discovery, auto fallback, pinned modern success/failure, and both stdio/Streamable HTTP.
- Later pages, empty pages with cursors, empty-string cursors, repeated cursors, limits and later-page errors. Counts must disclose incompleteness.
- Unadvertised, successful empty, malformed and failed lists. One server/list failure must not discard successful neighbors.
- Config shape validation, disabled entries, transport conflicts and static headers.
- Credential sentinels in env/args/headers/URLs and nested errors; none may reach diagnostics, callbacks or reports through configuration/error handling.
- Rendering flags independently and together, supplied examples, zero connection duration, delimiter escaping and code-fence balance.
- Startup failure, timeout, report-write failure and transport cleanup; no stranded processes or timers.
- Compiled Node CLI help/version/options and programmatic import, with actual package contents inspected.
For new bugs, observe a failing regression before fixing. For existing untested behavior, pin a passing characterization before editing. Use additional live targets only when the user explicitly requests them. Report commands and concrete outcomes, not inferred success.
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.
- yesterday First seen · 29 lines · 25 tokens per session scan A de5cab72a5cb
field-test is a skill published in the GitHub repository cyanheads/mcp-reporter (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 392 once invoked, about $0.0001 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 2026-09-09.
Other skills, from other repositories
harness-design-fuzzing
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…
gmail-query-syntax
Reference for Gmail's search query syntax — operators like is:sent, newerthan:, from:, has:attachment, label:, and how they compose. Read this when constructing a Gmail search query string for the googleworkspace.gmailsearchmessages Code Mode call, especially when filtering by sent vs received, recency, sender, or…
email-formatting
Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.
json-schema-emails
Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.
summary-style-guide
Tone and length conventions for email summaries — voice, verb tense, what to include vs omit, and target sentence count. Read this when writing the prose Summary line for each email so the voice is consistent across the report.
atf-testing
Build ServiceNow Automated Test Framework tests and suites — impersonation, form steps, assertions, server-side script steps, test parameters, and execution via snowcreateatftest / snowexecuteatftest.