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 primax79/kilo-mcp --skill kilo-mcp-metrics-analystgit clone --depth 1 https://github.com/primax79/kilo-mcpWrote 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/primax79/kilo-mcp/kilo-mcp-metrics-analyst)<a href="https://agentmods.dev/skills/primax79/kilo-mcp/kilo-mcp-metrics-analyst"><img src="https://agentmods.dev/badge/skills/primax79/kilo-mcp/kilo-mcp-metrics-analyst/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/primax79/kilo-mcp/kilo-mcp-metrics-analyst"><img src="https://agentmods.dev/badge/skills/primax79/kilo-mcp/kilo-mcp-metrics-analyst.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 | $0.00072 | $0.00665 |
| Opus 5.5 | $0.00029 | $0.00266 |
| Sonnet 5.5 | $0.00014 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
kilo-mcp-metrics-analyst 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 4d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kilo-mcp-metrics-analyst
Quick Reference
| Field | Value |
|---|---|
| Audience / Role | Architect / Orchestrator (deep-reasoning profile) |
| When to Load | Evaluating delegation efficiency, cancellation/bounce rates, and recurring defect patterns |
| Execution Modes Supported | Single-Framework Native (parallel native worktrees/subagents) and Multi-Framework MCP / CLI |
| Companion Scripts | bin/ai-orch |
| Related Skills | orchestration-workflow, task-spec-authoring, conflict-resolver |
This skill guides Claude in evaluating and reporting project delegation efficiency, decision branch telemetry, and defect rates based on Kilo MCP telemetry.
Logic and Behavior
- ROI Analysis: Call
kilo_metricsto compare the actual delegation cost (delegation_cost_usd) against the hypothetical inline generation cost (inline_estimate_usd), and inspect orchestration decision branches recorded viakilo_log_decision(delegate,inline,escalate,discarded, andinline_followup_needed). Detail savings, efficiency multipliers, and discarded-run rates to the user. Note thatdelegation_cost_usdincludes Kilo's own execution cost (kilo_execution_cost_usd) when the operator pays for Kilo tokens; when Kilo runs at zero marginal cost, evaluate ROI in terms of Architect context/quota preservation and bounce/discard rates. - Defect Tracking: Review issues recorded via
kilo_log_issueand discarded/escalated decisions logged viakilo_log_decision. Group them by severity and category to identify patterns. - Cancelled and discarded runs: a task stopped via
kilo_task_cancelstill logs a metrics record (Kilo's subprocess ran and consumed real tokens before being killed), typically withoutcome: unknownsince no Final Report was produced; similarly, a completed run whose output is thrown away and redone should be recorded viakilo_log_decision(branch='discarded', ...). A high rate of cancellations or discarded runs for a given kind of task is itself a signal worth surfacing — it usually means the spec needs tighter constraints or the task is a poor fit for delegation. - Feedback Loop: If recurring patterns are found (e.g., missed edge cases, styling mismatches, frequent cancellations, or high
inline_followup_needed/discardedcounts inkilo_log_decision), propose adding specific guardrails to future task specifications or creating target Kilo skills — seetask-spec-authoringfor how task-spec quality itself is the main lever on defect rate.
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.
- 4d ago First seen · 27 lines · 72 tokens per session scan A 697424ef1a8f
kilo-mcp-metrics-analyst is a skill published in the GitHub repository primax79/kilo-mcp (0 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 665 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 2026-10-16.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…