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 piti6/SpikeTrap --skill spike-trapgit clone --depth 1 https://github.com/piti6/SpikeTrapWrote 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/piti6/spiketrap/spike-trap)<a href="https://agentmods.dev/skills/piti6/spiketrap/spike-trap"><img src="https://agentmods.dev/badge/skills/piti6/spiketrap/spike-trap/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/piti6/spiketrap/spike-trap"><img src="https://agentmods.dev/badge/skills/piti6/spiketrap/spike-trap.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 | $0.00062 | $0.01296 |
| Opus 5.5 | $0.00025 | $0.00518 |
| Sonnet 5.5 | $0.00012 | $0.00259 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
spike-trap 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SpikeTrap Profiling Skill
Run an automated CPU profiling session using SpikeTrap. $ARGUMENTS
Modes
Determine which mode to use based on the user's request:
- profile (default): Enter play mode, collect spike frames, stop, analyze, and report.
- analyze: Skip profiling — analyze already-cached data or a loaded .data file.
If the user provides a spike threshold (e.g. "33ms", "16.6ms"), use it. Default: 33ms. If the user provides a GC threshold (e.g. "100KB"), use it. Default: 0 (disabled). If the user provides a duration (e.g. "10 seconds"), wait that long before stopping. Default: 10 seconds.
Profile Workflow
Step 1: Check prerequisites
using SpikeTrap.Editor;
return $"ViewActive={SpikeTrapApi.IsViewActive}, Collecting={SpikeTrapApi.IsCollecting}, Cached={SpikeTrapApi.CachedFrameCount}";
If IsViewActive is false, tell the user to open the Profiler window and select the SpikeTrap CPU module, then stop.
Step 2: Enter play mode
Use mcp__uLoopMCP__control-play-mode with Action=Play. Wait for Unity to be ready.
Step 3: Enable profiler and start collecting
using UnityEditorInternal;
using SpikeTrap.Editor;
ProfilerDriver.enabled = true;
SpikeTrapApi.StartCollecting(spikeThresholdMs: <THRESHOLD>f, gcThresholdKB: <GC_THRESHOLD>f);
return $"Collecting: spike>{<THRESHOLD>}ms, gc>{<GC_THRESHOLD>}KB";
Step 4: Wait for the requested duration
Tell the user profiling is running. Use ScheduleWakeup or repeated checks to wait.
Step 5: Stop and save
using SpikeTrap.Editor;
string path = System.IO.Path.Combine(UnityEngine.Application.dataPath, "..", "spike-trap-capture.data");
bool saved = await SpikeTrapApi.StopCollectingAndSaveAsync(path);
return $"Saved={saved}, Path={path}";
Then stop play mode with mcp__uLoopMCP__control-play-mode Action=Stop.
Step 6: Analyze (same as Analyze Workflow below)
Analyze Workflow
Step 1: Get spike frames
using SpikeTrap.Editor;
var spikes = SpikeTrapApi.GetSpikeFrames(<THRESHOLD>f);
if (spikes == null || spikes.Length == 0) return "No spike frames found.";
var sb = new System.Text.StringBuilder();
sb.AppendLine($"Found {spikes.Length} spike frames (>{<THRESHOLD>}ms):");
for (int i = 0; i < System.Math.Min(20, spikes.Length); i++)
sb.AppendLine(spikes[i].ToString());
return sb.ToString();
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 · 120 lines · 62 tokens per session scan A 53eed93d70a3
spike-trap is a skill published in the GitHub repository piti6/SpikeTrap (22 stars, last pushed 6mo ago), licensed MIT. It adds 62 tokens to every session and 1,296 once invoked, about $0.0002 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
profiling
Diagnose frame-rate bottlenecks (CPU vs GPU bound FIRST), control Unreal Insights traces, sample live frame times, and annotate performance captures. Use when FPS is low/bad, the game is slow, or you need to find what is limiting the frame rate.
performance-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.
cli-anything-nsight-graphics
Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.
performance
Use when a page or interaction is slow for one user and the fix starts from a measurement — a failing Core Web Vital (LCP, INP, CLS), a heavy JS bundle, wasted re-renders, an over-broad client boundary: profile, attribute the cost to one phase, fix it, re-measure. NOT surviving concurrent load (that is scaling), NOT…
game-performance-budget
Use when touching anything that runs per frame, adding entities/effects at scale, or answering a stutter/frame-drop report - frame budgets per target FPS, per-system split, the profiler per engine, before/after numbers, and threshold tests.
unity-performance-and-gc
Use when touching Unity per-frame code, spawning, physics queries, UI updates or rendering setup - profiling with numbers, zero-GC hot paths (caching, NonAlloc queries, no LINQ/closures/boxing, TMP SetText), ObjectPool, allocation tests, Burst/Jobs for bulk math, and rendering/physics settings that cost frames.