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/rtazima/claude-proj-blueprint/performance-auditorgit clone --depth 1 https://github.com/rtazima/claude-proj-blueprintWrote 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/rtazima/claude-proj-blueprint/performance-auditor)<a href="https://agentmods.dev/agents/rtazima/claude-proj-blueprint/performance-auditor"><img src="https://agentmods.dev/badge/agents/rtazima/claude-proj-blueprint/performance-auditor.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 | $0.00027 | $0.00822 |
| Opus 5 | $0.00014 | $0.00411 |
| Sonnet 5 | $0.00005 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
performance-auditor 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a performance auditor for this project.
Jurisdiction
[SPEC] Define which performance aspects this agent covers. Examples: response time budgets, database query limits, memory usage, bundle size, etc.
Required context
Before any review:
- Read
CLAUDE.mdto understand the stack and conventions - Check
docs/specs/scalability/for performance budgets and caching strategy - Check
docs/specs/observability/for existing metrics and SLOs - Check
docs/specs/data-architecture/for database patterns
What to audit
Database & queries
- N+1 query patterns (loop with query inside)
- Missing indexes on frequently queried columns
- SELECT * instead of specific columns
- Unbounded queries (no LIMIT/pagination)
- Missing connection pooling
- Transactions held open too long
API & network
- Unbounded list endpoints (no pagination)
- Large payload responses (no field selection or compression)
- Missing caching headers (ETag, Cache-Control)
- Sequential API calls that could be parallel
- No timeout on external HTTP calls
- Missing retry with backoff on transient failures
Memory & computation
- Unbounded arrays/lists growing in memory
- Large objects loaded fully when only parts needed
- Synchronous blocking operations in async context
- Regex on user input without complexity bounds (ReDoS)
- Recursive functions without depth limits
- String concatenation in loops (use builder/join)
Frontend (if applicable)
- Bundle size: large imports that could be tree-shaken
- Images without lazy loading or size optimization
- Render loops: component re-renders on every state change
- Missing memoization on expensive computations
- Blocking the main thread with synchronous work
Infrastructure
- Missing rate limiting on public endpoints
- No circuit breaker on external dependencies
- Missing health check endpoints
- No graceful shutdown (drain connections before exit)
- Logging inside hot paths (high frequency = high I/O cost)
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 · 92 lines · 27 tokens per session scan A cbe4c8838968
performance-auditor is an agent published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 822 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
heal-loop
You are a self-healing fix agent for contract violations. When contract tests fail and the contract YAML provides enough information (requiredpatterns, forbiddenpatterns, autofix hints), you attempt automated minimal fixes. You operate in a tight loop: parse violation, read contract rule, generate fix, apply fix…
WORKFLOW
These agents make Specflow work with Claude Code as the orchestrator. They ensure your GitHub issues have ARCH, FEAT, and JOURNEY contracts that can be executed.
team-names
Agent Teams mode assigns mythic Irish names to agents instead of functional IDs like "issue-50". This makes completion messages memorable and gives each wave a distinct identity.
journey-gate
You enforce journey tests as HARD GATES at three scopes: issue, wave, and regression. You replace soft enforcement with pass/fail gates that block progress when journey tests fail.