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 drn/dots --skill perfgit clone --depth 1 https://github.com/drn/dotsWrote 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/drn/dots/perf)<a href="https://agentmods.dev/skills/drn/dots/perf"><img src="https://agentmods.dev/badge/skills/drn/dots/perf/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/drn/dots/perf"><img src="https://agentmods.dev/badge/skills/drn/dots/perf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00645 |
| Opus 5.5 | $0.00011 | $0.00258 |
| Sonnet 5.5 | $0.00006 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
perf 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Benchmark
Run a command multiple times on the current branch and the base branch, then compare with statistical analysis.
Arguments
$ARGUMENTS- Required: the command to benchmark (e.g., "go test -bench=. ./pkg/..." or "npm run build"). Optional:--runs <count>for number of runs (default 5),--base <ref>to override base branch.
Context
- Current branch: !
git branch --show-current - Base ref: !
git branch -r 2>/dev/null | grep -oE 'origin/(main|master)' | head -1 - Git status: !
git status --short
Your task
Run before/after benchmarks comparing the current branch against the base branch.
Step 1: Parse arguments and run the benchmark script
Extract the benchmark command and optional flags (--runs N, --base <ref>) from $ARGUMENTS.
IF no command is provided, ask: "What command should I benchmark?"
Resolve the script path — use the first that exists:
~/.claude/skills/perf/scripts/perf.sh(deployed via symlink)agents/skills/perf/scripts/perf.sh(repo-relative, for development/workspaces)
bash <script-path> "<command>" [--runs N] [--base <ref>]
Handle the exit code:
- Exit 0 — Format the output as the report below and show it as your final response.
- Exit 1 — Report the error from stderr.
- Exit 2 — Report: "Benchmark command failed. Verify the command works:
<command>"
Step 2: Format the report
Parse the script's structured output and present it as:
## Benchmark Results
**Command:** `<command>`
**Runs:** <N> (+ 1 warmup)
### Timing
| Metric | Base (<ref>) | Current (<branch>) | Delta |
|--------|-------------|-------------------|-------|
| Min | <X>s | <Y>s | <diff> |
| Max | <X>s | <Y>s | <diff> |
| Mean | <X>s | <Y>s | <diff> |
| Median | <X>s | <Y>s | <diff> |
| Stddev | <X>s | <Y>s | — |
### Raw Data
**Base:** <comma-separated times>
**Current:** <comma-separated times>
### Verdict: <REGRESSION / IMPROVEMENT / NEUTRAL>
<1-2 sentence explanation>
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 77 lines · 28 tokens per session scan A b8f905795ed1
perf is a skill published in the GitHub repository drn/dots (23 stars, last pushed 11d ago), licensed MIT. It adds 28 tokens to every session and 645 once invoked, about $0.0001 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…