Borrowing it
Nothing to install: this file belongs to cardstack/boxel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cardstack/boxel/main/.claude/skills/capture-perf-diagnosis/SKILL.mdgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/capture-perf-diagnosis)<a href="https://agentmods.dev/skills/cardstack/boxel/capture-perf-diagnosis"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/capture-perf-diagnosis/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/cardstack/boxel/capture-perf-diagnosis"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/capture-perf-diagnosis.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 | $0.00000 | $0.07285 |
| Opus 5.5 | $0.00000 | $0.02914 |
| Sonnet 5.5 | $0.00000 | $0.01457 |
| Haiku 4.5 | $0.00000 | $0.00728 |
Grade A, and why
capture-perf-diagnosis 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 5d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture performance diagnosis
The capture pipeline emits one structured per-capture timing record so a slow capture is explainable rather than a mystery. It is the capture-service sibling of client-perf-diagnosis (client telemetry) and indexing-diagnostics (the indexer's diagnostics columns), and it reuses both of their conventions: a | json Loki channel and a diagnostics JSONB blob persisted next to the artifact.
This is the tool for turning "this capture was slow" into a stage-attributed breakdown that sums to the wall-clock, plus a plain-language root cause, cited to the exact log line / ledger row it came from.
The pipeline and where each stage is measured
request on a surface ─────────────────────────────────────────────────► response
GET {realm}_capture/… (hit / rendered /
POST /_capture congested / timeout /
│ gated / error)
│ gen lookup · ledger lookup · gate(GET) · congestion precheck · enqueue
│
└── enqueue ──► [ capture:{realmURL} serialized lane ] ──► worker capture task
queue wait │
├─ permissions
├─ prerender call ──► prerender server
│ page acquire (launch vs reuse)
│ render (nav · settle · imagePaint · capture)
├─ base64 decode
└─ persist (putMedia: upload vs dedupe)
Two event types, both on the boxel:capture-perf channel, defined in packages/runtime-common/capture-perf.ts:
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.
- 5d ago First seen · 207 lines · 0 tokens per session scan A 1dfd614af2c6
capture-perf-diagnosis is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,285 tokens. 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 2026-10-21.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.