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 monoes/monomind --skill performance-analysisgit clone --depth 1 https://github.com/monoes/monomindWrote 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/monoes/monomind/performance-analysis)<a href="https://agentmods.dev/skills/monoes/monomind/performance-analysis"><img src="https://agentmods.dev/badge/skills/monoes/monomind/performance-analysis/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/monoes/monomind/performance-analysis"><img src="https://agentmods.dev/badge/skills/monoes/monomind/performance-analysis.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 | $0.00021 | $0.02690 |
| Opus 5.5 | $0.00008 | $0.01076 |
| Sonnet 5.5 | $0.00004 | $0.00538 |
| Haiku 4.5 | $0.00002 | $0.00269 |
Grade A, and why
performance-analysis 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
performance-analysis — Measure, Don't Guess
Overview
Performance work without measurement is superstition. This skill wires a disciplined
methodology to monomind's real performance and analyze command surfaces.
Core principle: ALWAYS measure before optimizing. ALWAYS confirm a bottleneck is real before fixing it. Symptoms are not root causes.
Iron Law:
NO OPTIMIZATION WITHOUT A MEASURED BOTTLENECK FIRST
When to Use
- Something feels slow (swarm run, memory search, build, MCP tool call)
- Before/after a change that could affect performance
- A regression report or user complaint about latency
- Capacity planning — picking
maxAgents, topology, or memory backend - Token burn higher than expected
Use ESPECIALLY when: the fix "feels obvious". Obvious fixes without measurement are the most common source of fake optimizations.
The Real Command Surface
These are the ONLY performance/analysis commands. Anything else is wrong.
| Command | What it does |
|---|---|
monomind performance benchmark |
Run benchmarks (wasm/neural/memory/search) |
monomind performance profile |
Profile CPU/memory/IO over a window |
monomind performance metrics |
View/export metrics (1h/24h/7d/30d) |
monomind performance bottleneck |
Identify bottlenecks (quick or full) |
monomind analyze diff |
Git diff risk + change classification |
monomind analyze code |
Static code analysis |
monomind analyze deps |
Dependency analysis (--security for CVEs) |
monomind analyze ast |
AST analysis via tree-sitter |
monomind analyze complexity |
Code complexity metrics |
monomind analyze symbols |
Extract functions/classes/types |
monomind analyze imports |
Import dependency graph |
monomind doctor |
28 health-check categories |
monomind hooks metrics |
Learning metrics dashboard |
monomind tokens dashboard |
Token usage (today/week/30days/month) |
Use
npx monomind@latest ...from outside the repo; inside the reponode packages/@monomind/cli/bin/cli.js ...works too. Never usemonomind@alpha.
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 · 305 lines · 21 tokens per session scan A c4ef67af8654
performance-analysis is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 21 tokens to every session and 2,690 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 2026-10-26.
Other skills, from other repositories
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
neuron-monitoring
Monitor Neuron AI agents and workflows with events observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, or needs to understand why an agent is behaving a certain way. Also trigger for tasks involving agent…
rest-graphql-debug
Debug REST and GraphQL APIs layer by layer: connectivity, timeouts, TLS, auth, request format, parsing and semantics, with a status-code playbook and a clean repro for every finding.
oma-observability
Design or troubleshoot telemetry, SLOs, and incident diagnostics. Route to the relevant signal, system boundary, or vendor guide.
score-harness
5-dimension scorecard (0-100, grade A/B/C/F) for a scaffolded harness. Dimensions: Repo understanding (25%), Agent usefulness (25%), MCP safety (20%), Test coverage (15%), Publish readiness (15%). Emits a 6-field badges block (score + mcpRisk + 4 booleans) ready for the harness README. Exit 0 A/B, 1 C, 2 F.