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/generous-corp/pulp/trace-analysisnpx skills add Generous-Corp/pulp --skill trace-analysisgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/trace-analysis)<a href="https://agentmods.dev/skills/generous-corp/pulp/trace-analysis"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/trace-analysis.svg" alt="Measured on agentmods" 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 | $0.00148 | $0.08669 |
| Opus 5 | $0.00074 | $0.04334 |
| Sonnet 5 | $0.00030 | $0.01734 |
| Haiku 4.5 | $0.00015 | $0.00867 |
Grade A, and why
trace-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 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 — 650 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trace-analysis — the "why is this slow?" investigation harness
Someone who has never opened a profiler types one line — "why is my plugin
slow to open?" — and gets a real, plain-English answer with a suggested fix.
This skill is the protocol that makes that happen: you load it, capture or
accept a .pftrace, and run a disciplined investigation over it, returning a
narrated root cause and a chain of evidence — never raw SQL. You are reading
this because a tracing question fired (L1 explain) or an expert is driving an
iterative investigation (L2).
This skill is provider-agnostic by construction: it is a plain SKILL.md read
identically by Claude Code and Codex from .agents/skills/. The whole
"why is this slow?" experience works under any agent because it is a shipped
skill + CLI/MCP surface, not a vendor API.
Its companion is trace-sql — the SQL discipline and the Pulp trace-stdlib of
named query primitives. This harness decides what to ask; trace-sql is
how to ask it. Load both for an L2 session.
Attribution. The investigation methodology below — the chain-of-evidence scratchpad, the hypothesis→query→drill-down loop, the wall-time-vs-CPU-time rule, follow-the-blocker, exhaustive global verification, and p95/p99 discipline — is adapted from Google's
android/skillsperfetto-trace-analysis(Apache-2.0). The methodology is reused; the Android domain content (SurfaceFlinger, binder, RenderThread, ftrace, cpu governor) is not — the Pulp domain hints inreferences/are authored fresh against Pulp's own seams. See NOTICE.md.
The tiers (where this skill sits)
| Tier | Who | Entry | This skill's role |
|---|---|---|---|
| L0 | novice, no agent | pulp trace gpu-startup|gpu-health|gpu-probe --trace FILE |
return the same bounded typed analysis used by MCP |
| L1 | novice, one-shot | A .pftrace plus a question |
run this protocol autonomously, return narrated root cause + evidence + fix |
| L2 | expert, iterative | pulp trace query "<sql>" --trace FILE + this skill + trace-sql loaded |
drive the full loop by hand on hard/multi-bottleneck cases |
What ships with it
5 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 First seen · 650 lines · 148 tokens per session scan A 99f88422771c
trace-analysis is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 148 tokens to every session and 8,669 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…