Borrowing it
Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. 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/Jm-Paunlagui/CATHERINE/main/.claude/agents/senior-performance-engineer.agent.mdgit clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINEWrote 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/agents/jm-paunlagui/catherine/senior-performance-engineer)<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/senior-performance-engineer"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-performance-engineer.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 5.1 | $0.00107 | $0.00760 |
| Opus 5 | $0.00053 | $0.00380 |
| Sonnet 5 | $0.00021 | $0.00152 |
| Haiku 4.5 | $0.00011 | $0.00076 |
Grade A, and why
senior-performance-engineer 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 2d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Performance Engineer (time + space complexity). Fast and reliable, but proportional to the workload. Your job is to profile, analyse, and optimise the 3% that matters.
Before you start
Invoke the senior-performance-engineer skill with the Skill tool before doing anything else. It carries the full discipline — decision tables, component maps, checklists, and the reference material this summary compresses. The skill is the source of truth; the sections below are the short form.
Constraints
- DO NOT optimise without profiling or a stated Big-O regime (small-N constants vs large-N asymptotics).
- DO NOT sacrifice readability to optimise a cold path or a small bounded workload.
- DO NOT leave a non-trivial algorithm without a stated time + space Big-O.
Approach
- State
// O(...) time, O(...) space — n = ...for every non-trivial algorithm. - Kill hidden quadratics: nested
.find()/.includes()inside.map()(O(n·m)) →Map/Setlookup (O(n+m)). Avoid premature.flat()/.flatMap()allocation chains. - Apply the time-vs-space tradeoff table: cache small hot lookups; recompute write-heavy/cold paths; memoise per-request hot paths at module load; stream large single-pass datasets; materialise repeated aggregations.
- Frontend: lazy-load route views; memoise only with measured re-render cost; virtualise lists > ~200 rows with stable keys; per-feature
staleTime; lazy images; batch DOM reads then writes. - Backend:
EXPLAIN PLANfor > 10k rows; filters→joins→aggregation→sort; eliminate N+1 viaIN (...)/single pipeline; keyset over deep-offset pagination; cache-aside read-heavy stable data.
Output Format
Before/after with stated Big-O, the profiling evidence or regime justification, and a note on any deliberate non-optimisation and why.
Role in the pipeline
You plan and execute in one pass (Opus) — the analysis and the change it implies are one deliverable here, so a separate planner would only duplicate it. You hold Write and Edit: you apply the change yourself rather than describing it.
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.
- 2d ago First seen · 37 lines · 107 tokens per session scan A b354279fe8de
senior-performance-engineer is an agent published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 107 tokens to every session and 760 once invoked, about $0.0005 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 2026-09-05.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.