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 OctoPerf/octoperf-claude-plugins --skill octoperf-export-bench-report-pdfgit clone --depth 1 https://github.com/OctoPerf/octoperf-claude-pluginsWrote 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/octoperf/octoperf-claude-plugins/octoperf-export-bench-report-pdf)<a href="https://agentmods.dev/skills/octoperf/octoperf-claude-plugins/octoperf-export-bench-report-pdf"><img src="https://agentmods.dev/badge/skills/octoperf/octoperf-claude-plugins/octoperf-export-bench-report-pdf/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/octoperf/octoperf-claude-plugins/octoperf-export-bench-report-pdf"><img src="https://agentmods.dev/badge/skills/octoperf/octoperf-claude-plugins/octoperf-export-bench-report-pdf.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 | $0.00096 | $0.01094 |
| Opus 5 | $0.00048 | $0.00547 |
| Sonnet 5 | $0.00019 | $0.00219 |
| Haiku 4.5 | $0.00010 | $0.00109 |
Grade A, and why
octoperf-export-bench-report-pdf 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 12d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OctoPerf — Export a benchReport as PDF
OctoPerf prints reports server-side with a headless Playwright render. The work is async: the MCP tool submits the task, the LLM polls until it settles, then pulls the PDF off the report's first bench result.
When this applies
The user wants a static, shareable artefact of an existing bench
report — a stakeholder review, an attachment to a ticket, an offline
archive. If the user just wants to read metrics, use the report
value tools (get_report_summary_values, get_report_table_values,
…) instead. The PDF is for hand-off, not analysis.
Prerequisites
- A
benchReportId(find it withlist_bench_reports_by_project). - The underlying bench run is terminal (FINISHED / ABORTED / ERROR). Printing a report whose run is still RUNNING is allowed but the metrics inside the PDF will be partial.
- The report's data is up to date.
export_bench_report_pdfrefuses otherwise, rather than rendering a document of empty report items: runget_report_data_status, thenupdate_report_data, and print once the update tasks reach SUCCESS. Seeoctoperf-bench-reports.
The three-step chain
1. Submit the print task
export_bench_report_pdf(benchReportId)
# returns { benchReportId, taskId }
The tool returns immediately with a taskId. Defaults are sensible
(portrait A4, empty cover page, en-US locale, UTC timezone) — no extra
parameters needed for the common case.
2. Poll until the task settles
get_task_result(taskId)
# returns { taskId, status, message }
status cycles through PENDING while Playwright is rendering. Stop on:
SUCCESS→ the PDF has been uploaded to the report's first bench result. Continue with step 3.FAILED→messagecarries the backend stack trace. Surface it to the user verbatim and stop.
Typical render time is 10–30 seconds; expect more on large reports
(many report items, long trend series). For the polling cadence and the
sleep-between-polls discipline, read octoperf-async-polling — the
PDF task is in its table (3s between polls, ~5 min outer deadline).
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.
- 12d ago First seen · 105 lines · 96 tokens per session scan A 3d5cfae2b9e4
octoperf-export-bench-report-pdf is a skill published in the GitHub repository OctoPerf/octoperf-claude-plugins (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,094 once invoked, about $0.0005 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 skills, from other repositories
recipe-bulk-download-folder
List and download all files from a Google Drive folder.
nutrient-document-processing
Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images.
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.