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 skills/alphalab-ustc/ohmycode/benchnpx skills add AlphaLab-USTC/OhMyCode --skill benchgit clone --depth 1 https://github.com/AlphaLab-USTC/OhMyCodeWhat 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 | $0.00032 | $0.00996 |
| Opus 5 | $0.00016 | $0.00498 |
| Sonnet 5 | $0.00006 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
bench 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 2d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OhMyCode Benchmark
One-command benchmarking: run 8 SWE-bench-style coding tasks through OhMyCode, track token usage (in/out), and produce a scorecard.
Works with any provider and model — uses whatever is configured in ~/.ohmycode/config.json or overridden via CLI args.
When to Use
- User says "run benchmark", "bench", "score", "evaluate", "test performance"
- User wants to compare models or providers
- After major code changes, to verify agent capabilities still work
Input
$ARGUMENTS — optional filters and overrides.
| Argument | Example | Effect |
|---|---|---|
| (empty) | /bench |
Full suite, current config |
| task filter | /bench fib,bug |
Only matching tasks |
--dry-run |
/bench --dry-run |
Validate task definitions without LLM |
Step 1 — Run the Benchmark
python3 benchmarks/run_bench.py $ARGUMENTS 2>&1 | tee bench_run.log
Override provider/model for comparison
# Test with a different model
python3 benchmarks/run_bench.py --provider openai --model gpt-4o-mini 2>&1 | tee bench_run.log
# Test with Anthropic
python3 benchmarks/run_bench.py --provider anthropic --model claude-sonnet-4-20250514 2>&1 | tee bench_run.log
# Test with custom endpoint
python3 benchmarks/run_bench.py --base-url http://localhost:8080/v1 --api-key test 2>&1 | tee bench_run.log
Step 2 — Read Results
The harness outputs:
- Terminal report — table with per-task pass/fail, tokens, time
bench_results.json— machine-readable results for comparison
Key metrics to report:
- Score: X/8 tasks passed
- Tokens in: total prompt tokens across all tasks
- Tokens out: total completion tokens across all tasks
- Total tokens: in + out
- Time: wall-clock seconds
Step 3 — Analyze Failures
If any tasks failed:
- Read the
reasoncolumn in the report - Check
bench_results.jsonfor theerrorfield - Classify: is it a model capability issue, or an OhMyCode bug?
- For OhMyCode bugs → fix and re-run
/bench(closed-loop)
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.
- 2d ago First seen · 116 lines · 32 tokens per session scan A 6ecf075d6d1e
bench is a skill published in the GitHub repository AlphaLab-USTC/OhMyCode (131 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 996 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…