Borrowing it
Nothing to install: this file belongs to przeprogramowani/10x-bench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/przeprogramowani/10x-bench/master/.claude/skills/10x-measure-results/SKILL.mdgit clone --depth 1 https://github.com/przeprogramowani/10x-benchWrote 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/przeprogramowani/10x-bench/10x-measure-results)<a href="https://agentmods.dev/skills/przeprogramowani/10x-bench/10x-measure-results"><img src="https://agentmods.dev/badge/skills/przeprogramowani/10x-bench/10x-measure-results/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/przeprogramowani/10x-bench/10x-measure-results"><img src="https://agentmods.dev/badge/skills/przeprogramowani/10x-bench/10x-measure-results.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 | $0.00131 | $0.03085 |
| Opus 5.5 | $0.00052 | $0.01234 |
| Sonnet 5.5 | $0.00026 | $0.00617 |
| Haiku 4.5 | $0.00013 | $0.00309 |
Grade A, and why
10x-measure-results scanned grade A with 1 finding 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 27d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Run them as one background command. Wait until each answers, then check `/`, `/o-nas`, `/podcast` and `/youtube` with curl and record the HTTP codes. "Kursy" is a section on `/`, not a page. How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
10x Measure Results
Scores the attempts eval-attempts/{model-id}-attempt-{N}/ of one model and writes
eval-results/{model-id}-attempt-{N}/eval-results.csv.
Input: a model ID (e.g. glm-53). Score every eval-attempts/{model-id}-attempt-* that has a project and no eval-results CSV yet, unless the user names specific attempts.
The rubric is authoritative in the sibling repo; read it at the start of every run:
../10x-bench-eval/benchmark/criteria.md- criteria and the CSV template (total 10 points; Tech stack and Cloudflare deploy are 0.5 each)../10x-bench-eval/benchmark/eval.md- workflow and content-verification checklists../10x-bench-eval/benchmark/context/przeprogramowani.md- verified reference content
Run git -C ../10x-bench-eval pull --ff-only first so the rubric is current.
Step 1: Build all attempts in parallel
For each attempt (project root is the attempt dir, or its single nested dir that holds package.json), in parallel:
(cd <root> && { [ -f package-lock.json ] && npm ci --no-audit --no-fund || npm install --no-audit --no-fund; } && npm run build)
Keep install/build logs in the session scratchpad. Build failure rule (eval.md): if the install, the build or the dev server fails, that attempt scores 0 on every criterion; skip the judge and the manual form for it and note why. Grade the project as delivered: a candidate can build successfully in its own session from packages it installed and then leave a package.json without them, so the clean install here is what counts. Don't repair it. Tell the user which attempts failed, since a 0/10 attempt pulls the model average down noticeably.
Step 2: Start dev servers in parallel
Start one dev server per attempt on its own port, starting at 4461 (attempt N -> 446N; use 447x for attempts 10+). Never use 4321; another project's server may already be on it.
(cd <root> && npx astro dev --port 446N --host 127.0.0.1 > <scratchpad>/<attempt>.dev.log 2>&1) &
Run them as one background command. Wait until each answers, then check /, /o-nas, /podcast and /youtube with curl and record the HTTP codes. "Kursy" is a section on /, not a page.
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.
- 27d ago First seen · 132 lines · 131 tokens per session scan A 6b56dbe23970
10x-measure-results is a skill published in the GitHub repository przeprogramowani/10x-bench (14 stars, last pushed 20d ago), licensed MIT. It adds 131 tokens to every session and 3,085 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other skills, from other repositories
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
writing-livekit-scenarios
Creates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them. Use when the user asks "what should I test", "generate simulation scenarios", "write scenarios for my agent", "add a scenario for X", "organize my scenario files", "my simulations are flaky", "the scenario hits my…
running-livekit-simulations
Runs LiveKit agent simulations and acts on the results. Use when the user says "run my simulations", "regression test my agent before deploying", "run the scenarios", "use lk agent simulate", "did my agent pass", "why did this scenario fail", "run simulations in CI", "test the audio pipeline", "check turn-taking and…
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
shared/tdd
A test-driven development guide, where tests are written before the production code and drive the implementation.