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 agents/hmj1026/dhpk/performance-analyzergit clone --depth 1 https://github.com/hmj1026/dhpkWhat 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 | $0.00107 | $0.01177 |
| Opus 5 | $0.00053 | $0.00589 |
| Sonnet 5 | $0.00021 | $0.00235 |
| Haiku 4.5 | $0.00011 | $0.00118 |
Grade A, and why
performance-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Analyzer
Lookup:
cx/gitnexusper${CLAUDE_PLUGIN_ROOT}/rules/tool-routing.md.
Scope
Audit query performance in the Repository (data-access) layer. database-reviewer owns correctness (bind parameters, IN/NOT IN, schema, transactions). This agent owns performance (latency, index usage, query count, N+1). Framework-agnostic — the relational perf checks apply to any data-access path. When a frontend (any JS / TS / Vue / React project) or native (swift) stack is detected, also audit client/runtime performance via the matching trap sheet (frontend.md / swift.md) — bundle size, render / re-render cost, memory leaks, Web Vitals, allocation hot paths.
When NOT
- Bind params / schema / transactions (correctness, not latency) →
database-reviewer
Stack trap sheet (load on demand)
Detect the active stack, then load ONLY the matching trap sheet(s); ignore other stacks — never grade a Yii/MySQL change against another stack's perf rules, or vice-versa.
- Shared detection: follow
${CLAUDE_PLUGIN_ROOT}/agent-traps/_common/trap-sheet-loader.md(<agent-name>=performance-analyzer). Do not paste its detection order here. - Exceptions (keep inline):
- Extra: root
pyproject.tomlsqlalchemy/alembicremain this agent's performance-specific detail. - Map module ids to the trap-sheet stack id before lookup:
js/vue-2/ React / Next →frontend;swiftui/ios-platform→swift. (Perf sheets are namedfrontend.md/swift.md.)
- Extra: root
- Load matching sheets per the loader. Relational sheets carry hot-table / N+1 / EXPLAIN recipes;
frontend/swiftsheets carry bundle / render / memory recipes. No sheet matches → apply only the Baseline below.
Baseline (language-agnostic)
- No full table scan on large tables — check the query plan (EXPLAIN / equivalent); a sequential scan on a high-volume table is a fix, not a warning.
- Index hot columns — WHERE / ORDER BY columns are indexed; composite-index column order matches the predicate.
- No N+1 — batch / eager-load related rows instead of running a query inside a loop.
- Bound result sets — cap rows with
LIMIT(or cursor pagination for deep pages); no unbounded fetch on high-volume tables. - Filter before sort — apply predicates to shrink the set before an expensive sort.
- Stable query count — integration-test query count stays constant as data volume grows (does not scale with rows).
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 · 76 lines · 107 tokens per session scan A 264dc6725703
performance-analyzer is an agent published in the GitHub repository hmj1026/dhpk (2 stars, last pushed 2d ago), licensed MIT. It adds 107 tokens to every session and 1,177 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 2026-08-31.
Other agents, from other repositories
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
cdc-reviewer
CDC design strategy reviewer. Evaluates synchronization architecture quality, FIFO depth calculations, metastability budgets, and reset synchronization. Produces review reports in reviews/.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
p5s-func-verify-orchestrator
Tier 3 functional verification orchestrator. Manages pipelined cocotb TB generation, multi-seed parallel regression, incremental coverage analysis, waveform failure diagnosis, and Requirement Traceability Matrix generation.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).