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/luisfelipemoro/harness-devkit/performance-profilingnpx skills add LuisFelipeMoro/Harness-devkit --skill performance-profilinggit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWhat 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 | $0.00070 | $0.00459 |
| Opus 5 | $0.00035 | $0.00230 |
| Sonnet 5 | $0.00014 | $0.00092 |
| Haiku 4.5 | $0.00007 | $0.00046 |
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 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.
What it actually says
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
- 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.
What ships with it
2 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.
- 2d 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 (10 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 459 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
layered-architecture-types
Enforce primitive-at-edges / strong-types-in-Business layering and the toBus/fromBusResponse/toDB converter pattern. Use when writing, editing, or auditing Go files under app/, business/domain/, or .../stores/db.
golang-testing
Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI…
golang-observability
Golang everyday observability — the always-on signals in production. Covers structured logging with slog, Prometheus metrics, OpenTelemetry distributed tracing, continuous profiling with pprof/Pyroscope, server-side RUM event tracking, alerting, and Grafana dashboards. Apply when instrumenting Go services for…
golang-data-structures
Golang data structures — slices (internals, capacity growth, preallocation, slices package), maps (internals, hash buckets, maps package), arrays, container/list/heap/ring, strings.Builder vs bytes.Buffer, generic collections, pointers (unsafe.Pointer, weak.Pointer), and copy semantics. Use when choosing or optimizing…
golang-dependency-management
Dependency management for Golang projects — go.mod and go.sum, go get install and upgrade flows, Minimal Version Selection, conflict resolution with replace/exclude/retract, govulncheck scanning of the module tree, outdated dependency and binary size auditing, vendoring, tool directives, and go.work workspaces. Use…
golang-spf13-viper
Golang configuration library using spf13/viper — layered precedence (flag > env > file > KV > default), BindPFlag/BindPFlags, SetEnvPrefix + SetEnvKeyReplacer + AutomaticEnv, ReadInConfig + ConfigFileNotFoundError, Unmarshal + mapstructure struct tags, Sub for sub-trees, WatchConfig + OnConfigChange for hot reload…