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 atuljha23/holocron --skill perf-checklistgit clone --depth 1 https://github.com/atuljha23/holocronWrote 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/atuljha23/holocron/perf-checklist)<a href="https://agentmods.dev/skills/atuljha23/holocron/perf-checklist"><img src="https://agentmods.dev/badge/skills/atuljha23/holocron/perf-checklist/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/atuljha23/holocron/perf-checklist"><img src="https://agentmods.dev/badge/skills/atuljha23/holocron/perf-checklist.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 | $0.00032 | $0.00787 |
| Opus 5 | $0.00016 | $0.00394 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
perf-checklist 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance checklist
Measure first. Opinion second.
Frontend — Core Web Vitals
LCP (Largest Contentful Paint) — ≤ 2.5s
- Hero image preloaded, sized,
fetchpriority="high". - Critical CSS inlined or loaded before render-blocking resources.
- Fonts:
font-display: swap, preloaded if above the fold. - No render-blocking JS on the critical path.
deferorasync.
CLS (Cumulative Layout Shift) — ≤ 0.1
-
width/heighton images and iframes. - Reserved space for async content (skeletons, aspect-ratio boxes).
- No ads / embeds inserted above existing content without reservation.
- No web-font swap without matching metrics.
INP (Interaction to Next Paint) — ≤ 200ms
- No long tasks (>50ms) on interaction paths.
- Break up work:
scheduler.yield(), idle callbacks, debounced expensive calcs. - Virtualize long lists.
- Event handlers don't do layout thrash — batch reads then writes.
Frontend — bundle
- Tree-shake-friendly imports.
import { x } from 'lib'— notimport lib from 'lib'unless required. - No
moment— usedate-fnsorTemporalpolyfill. - No full
lodash— uselodash-esnamed imports or dropping to native. - Code-split routes. Lazy-load heavy components that aren't above the fold.
- Images: modern formats (WebP/AVIF), responsive
srcset, served from a CDN.
Backend — query layer
- No query inside a loop over a result set (N+1). Batch with
IN/JOIN/dataloader. - Every
WHERE/ORDER BY/JOINcolumn used on large tables is indexed. -
SELECT *replaced with specific columns on hot paths. - Pagination uses cursors, not offset, on tables that grow.
- Queries have statement timeouts.
Backend — request
- Timeouts on every outbound call.
- Retries capped with backoff. Never infinite.
- Circuit breakers for dependencies you can't trust.
- Response compression enabled (gzip/brotli).
- Static assets behind a CDN with long
Cache-Control.
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.
- 9d ago First seen · 71 lines · 32 tokens per session scan A 591578786220
perf-checklist is a skill published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 787 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
batch-orchestration
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
skill-router
The index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-run or auto-triggered. Use when you are not sure which skill fits, want the full map, or ask "what can this do", "which skill for X", "list the workflow".
sprint-status
Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.
survey-generator
Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in /derived/surveys/…
thoroughness-scoring
Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.
wiki-research-loop
Auto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from the queue, fetches sources, drafts a wiki page, dedupes claims against existing pages, enqueues follow-up seeds. Halts on budget cap, depth cap, or…