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 CodSpeedHQ/codspeed --skill codspeed-optimizegit clone --depth 1 https://github.com/CodSpeedHQ/codspeedWrote 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/codspeedhq/codspeed/codspeed-optimize)<a href="https://agentmods.dev/skills/codspeedhq/codspeed/codspeed-optimize"><img src="https://agentmods.dev/badge/skills/codspeedhq/codspeed/codspeed-optimize/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/codspeedhq/codspeed/codspeed-optimize"><img src="https://agentmods.dev/badge/skills/codspeedhq/codspeed/codspeed-optimize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 192 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00113 | $0.02655 |
| Opus 5.5 | $0.00045 | $0.01062 |
| Sonnet 5.5 | $0.00023 | $0.00531 |
| Haiku 4.5 | $0.00011 | $0.00265 |
Grade A, and why
codspeed-optimize 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize
You are an autonomous performance engineer. Your job is to iteratively optimize code using CodSpeed benchmarks and flamegraph analysis. You work in a loop: measure, analyze, change, re-measure, compare — and you keep going until there's nothing left to gain or the user tells you to stop.
All measurements must go through CodSpeed. Always use the CodSpeed CLI (codspeed run, codspeed exec) to run benchmarks — never run benchmarks directly (e.g., cargo bench, pytest-benchmark, go test -bench) outside of CodSpeed. The CodSpeed CLI and MCP tools are your single source of truth for all performance data. If you're unable to run benchmarks through CodSpeed (missing auth, unsupported setup, CLI errors), ask the user for help rather than falling back to raw benchmark execution. Results outside CodSpeed cannot be compared, tracked, or analyzed with flamegraphs.
Before you start
-
Understand the target: What code does the user want to optimize? A specific function, a whole module, a benchmark suite? If unclear, ask.
-
Understand the metric: CPU time (default), memory, walltime? The user might say "make it faster" (CPU/walltime), "reduce allocations" (memory), or be specific.
-
Check for existing benchmarks: Look for benchmark files,
codspeed.yml, or CI workflows. If no benchmarks exist, stop here and invoke thesetup-harnessskill to create them. You cannot optimize what you cannot measure — setting up benchmarks first is a hard prerequisite, not a suggestion. -
Check CodSpeed auth: Run
codspeed auth loginif needed. The CodSpeed CLI must be authenticated to upload results and use MCP tools.
The optimization loop
Step 1: Establish a baseline
Build and run the benchmarks to get a baseline measurement. Use simulation mode for fast iteration:
For projects with CodSpeed integrations (Rust/criterion, Python/pytest, Node.js/vitest, etc.):
# Build with CodSpeed instrumentation
cargo codspeed build -m simulation # Rust
# or for other languages, benchmarks run directly
# Run benchmarks
codspeed run -m simulation -- <bench_command>
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 · 227 lines · 113 tokens per session scan A 01023deaa74c
codspeed-optimize is a skill published in the GitHub repository CodSpeedHQ/codspeed (376 stars, last pushed 2d ago), licensed Apache-2.0. It adds 113 tokens to every session and 2,655 once invoked, about $0.0005 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
hotpath_cloud
Read hotpath Cloud performance verdicts with the hotpath cloud CLI and fix Rust performance regressions. Fetches the benchmark report of a commit or pull request, compares it with its baseline under the repository's regression policy and performance budgets, and lists what regressed and which budgets broke, as JSON.…
http-load-profiler
Run stepped HTTP load tests with ab/wrk, ramping concurrency levels to collect p50/p90/p99 latency, detect performance inflection points, and recommend optimal concurrency. Triggered by requests like 'load test this URL', 'benchmark my API', 'find the max concurrency', or mentions of p99 latency, throughput…
hotpath_init_ci_forks
Set up the hotpath Cloud CI integration in a public Rust project that benchmarks pull requests from forks. Adds the hotpath-cloud feature, a regression policy file, a GitHub Actions benchmark workflow that writes hotpath reports as artifacts and a relay workflow that uploads them, so every pull request, forks…
hotpath_init_ci
Set up the hotpath Cloud CI integration in a Rust project whose pull requests come from branches of the same repository (private repositories, or public ones that do not benchmark fork pull requests). Adds the hotpath-cloud feature, a regression policy file and a GitHub Actions benchmark workflow that uploads hotpath…
Artillery Load Testing
Write and run Artillery load tests with YAML phases and scenarios, CSV data payloads, the expect plugin for functional checks, and ensure thresholds that fail CI when latency or error budgets are breached.
Browser Smoke Testing
Open a local web target and verify that the main page renders and core controls respond.