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 LuisFelipeMoro/Harness-devkit --skill performance-profilinggit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWrote 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/luisfelipemoro/harness-devkit/performance-profiling)<a href="https://agentmods.dev/skills/luisfelipemoro/harness-devkit/performance-profiling"><img src="https://agentmods.dev/badge/skills/luisfelipemoro/harness-devkit/performance-profiling/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/luisfelipemoro/harness-devkit/performance-profiling"><img src="https://agentmods.dev/badge/skills/luisfelipemoro/harness-devkit/performance-profiling.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 | $0.00078 | $0.00535 |
| Opus 5.5 | $0.00031 | $0.00214 |
| Sonnet 5.5 | $0.00016 | $0.00107 |
| Haiku 4.5 | $0.00008 | $0.00053 |
Grade A, and why
performance-profiling 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 today.
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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimization must never change behaviour: a characterization test pins the current output before any change and must stay GREEN through every optimization. The pprof endpoint must stay on an internal port, never a public one.
Contract
- Input: a Go service with a suspected performance problem.
- Output: a profiled diagnosis plus an optimization guarded by a characterization test and a before/after benchmark.
- Tool boundary: profiling is read-only; optimizations land only behind a GREEN characterization test and a measured benchmark.
- Done when: the benchmark shows before/after numbers and the characterization test stays GREEN.
Steps
Latency spread across layers or services rather than one hot function: start with references/latency-budget.md (trace first, then fix by layer); it routes back to steps 4-5 for the fix.
- Enable the pprof endpoint on an internal port per
references/pprof-setup-and-capture.md. - Capture CPU, heap, goroutine, block, and mutex profiles with the commands in
references/pprof-setup-and-capture.md. - Analyse the profiles at the pprof prompt (
top10,list, flame graph) perreferences/pprof-setup-and-capture.md; the widest bars at the top of the flame mark the hot path. - Lock behaviour first: a characterization test pins the hot path's current output, per
references/optimize-and-benchmark.md. - Apply the matching entry from the common-fixes table in
references/optimize-and-benchmark.md. - Benchmark before and after per
references/optimize-and-benchmark.md, then report the numbers in the PR description. - For production visibility, the continuous-profiling options in
references/pprof-setup-and-capture.mdapply.
References
references/pprof-setup-and-capture.md— endpoint setup, capture commands, pprof-shell analysis, continuous profiling.references/optimize-and-benchmark.md— characterization test, common-fixes table, before/after benchmark.references/latency-budget.md— trace-first, layer-by-layer latency budget and the fix per layer.
What ships with it
3 files 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.
- today Changed · +2 lines 8f57d883bd23
- 1mo ago Changed · +8 tokens per session 52473254cbb6
- 1mo ago First seen · 26 lines · 70 tokens per session scan A 154acd7db282
performance-profiling is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (13 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 535 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
go-linters
Add and validate custom Go analysis linters in gh-aw.
printing-press-polish
Polish a generated CLI to pass verification and become publish-ready. Runs diagnostics (dogfood, verify, scorecard, go vet, gosec), automatically fixes all issues (verify failures, static-analysis findings, dead code, descriptions, README, MCP tool quality), reports the before/after delta, and offers to publish. Use…
stack-trace-go-probe
Internal helper for meta-stack-trace-investigator. Use when a Go panic or stack trace needs Go-specific nil/error checks, go test reproducer guidance, and patch targets.
golang-troubleshooting
Troubleshoot Golang programs systematically - find and fix the root cause. Use when encountering bugs, crashes, deadlocks, races, or unexpected behavior in Go code. Covers debugging methodology, common Go pitfalls, test-driven debugging, pprof setup and capture, Delve, race detection, GODEBUG tracing, and production…
golang-error-handling
Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log…
tree-sitter-language-pack-extracting-code-structure
Use when the user wants structured code metadata from a source file — functions, classes, imports, exports, symbols, docstrings, comments, or syntax diagnostics. Covers ts-pack process feature flags, the JSON result shape, and the default feature set.