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 nishilbhave/codeprobe --skill codeprobe-performancegit clone --depth 1 https://github.com/nishilbhave/codeprobeWrote 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/nishilbhave/codeprobe/codeprobe-performance)<a href="https://agentmods.dev/skills/nishilbhave/codeprobe/codeprobe-performance"><img src="https://agentmods.dev/badge/skills/nishilbhave/codeprobe/codeprobe-performance/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/nishilbhave/codeprobe/codeprobe-performance"><img src="https://agentmods.dev/badge/skills/nishilbhave/codeprobe/codeprobe-performance.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 | $0.00086 | $0.02187 |
| Opus 5.5 | $0.00034 | $0.00875 |
| Sonnet 5.5 | $0.00017 | $0.00437 |
| Haiku 4.5 | $0.00009 | $0.00219 |
Grade A, and why
codeprobe-performance 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 2mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standalone Mode
If invoked directly (not via the orchestrator), you must first:
- Read
../codeprobe/shared-preamble.md(resolve relative to this SKILL.md's location — the siblingcodeprobeskill directory — not the user's project) for the output contract, execution modes, and constraints. - Load applicable reference files from
../codeprobe/references/(same resolution) based on the project's tech stack. - Default to
fullmode unless the user specifies otherwise.
Performance & Scalability Auditor
Domain Scope
This sub-skill detects performance and scalability issues across these categories:
- N+1 Queries — Lazy-loading relationships inside loops
- Missing Indexes — WHERE/ORDER BY on non-indexed columns
- Unbounded Queries — Model::all() without pagination/limit
- Memory — Loading entire files into memory, array accumulation in loops
- Caching — Repeated identical queries, missing TTL, stale cache after writes
- Algorithmic Efficiency — O(n^2) in hot paths, nested loops, sorting in loops
- Concurrency — Race conditions, non-idempotent queue jobs, shared mutable state
- Frontend Performance — Unnecessary re-renders, bundle size, missing lazy loading
What It Does NOT Flag
- Premature optimization in non-hot-path code — proportional design matters. A utility function called once at startup doesn't need the same optimization as a request handler.
- Development-only debug queries — queries in seeders, dev-only commands, or debug endpoints.
- Batch processing scripts — scripts intentionally designed to process everything (migrations, data backfills) where unbounded queries may be appropriate.
- O(n^2) on small bounded collections (<100 items) — nested loops on small known-size arrays are fine.
- Frontend SSR/build-time code — server components and build scripts have different performance profiles than client-side code.
Detection Instructions
N+1 Queries
| ID Prefix | What to Detect | How to Detect | Severity |
|---|---|---|---|
PERF |
Eloquent relationship access inside loop without eager loading | Search for foreach/for loops iterating over a collection, then accessing a relationship property (e.g., $order->items, $user->profile) inside the loop body. Check whether the query that produced the collection includes with() or load() for that relationship. |
Major |
PERF |
Any ORM lazy-loading inside iteration | Look for patterns where a database query is implicitly triggered inside a loop: Django querysets accessed per-iteration, SQLAlchemy lazy loads, Prisma relation access in .map(). |
Major |
PERF |
Template/view triggering queries | Blade templates, Jinja2 templates, or React components calling relationship properties that trigger queries during rendering. | Major |
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.
- 2mo ago First seen · 131 lines · 86 tokens per session scan A 535c8507eb36
codeprobe-performance is a skill published in the GitHub repository nishilbhave/codeprobe (5 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 2,187 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…