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 voidhashcom/lensflare --skill find-errorgit clone --depth 1 https://github.com/voidhashcom/lensflareWrote 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/voidhashcom/lensflare/find-error)<a href="https://agentmods.dev/skills/voidhashcom/lensflare/find-error"><img src="https://agentmods.dev/badge/skills/voidhashcom/lensflare/find-error/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/voidhashcom/lensflare/find-error"><img src="https://agentmods.dev/badge/skills/voidhashcom/lensflare/find-error.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 | $0.00052 | $0.00353 |
| Opus 5.5 | $0.00021 | $0.00141 |
| Sonnet 5.5 | $0.00010 | $0.00071 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
find-error 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 2mo 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.
What it actually says
Find an error in Lensflare
You have access to the Lensflare MCP server (lensflare).
- Call
lensflare:listDatasetsif the user has not specified one. If exactly one dataset exists, use it. Otherwise, ask the user which to query. - Call
lensflare:queryTelemetrywithquery: 'level in ["error", "fatal"] or status = "error"'. Uselimit: 50unless the user asked for more. - Group the returned records by
name(for spans) ormessage(for logs) to find the dominant failure mode. - For the most frequent error, if it has a
traceId, calllensflare:getTraceand readsummary.erroredSpansto identify the failing span. - Report: the error class, frequency, the failing service, and the first failing span. Include the
traceIdso the user can open the trace in the desktop app.
Query language reminder. Use ~= for regex, contains for substring, and quote string values. Boolean operators are and / or / not. Top-level fields include level, status, serviceName, traceId, durationUs. Attributes use attributes.<key> (or attr.<key>). The full grammar is in the queryTelemetry tool description.
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.
- 2mo ago First seen · 17 lines · 52 tokens per session scan A a6a73b5cb66f
find-error is a skill published in the GitHub repository voidhashcom/lensflare (100 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 353 once invoked, about $0.0002 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.
find-error compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| find-errorvoidhashcom/lensflare | Skill | 100 | 4mo ago | MIT | A | 52 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |