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/srnichols/plan-forge/performance-analyzergit clone --depth 1 https://github.com/srnichols/plan-forgeWhat 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 | $0.00026 | $0.00837 |
| Opus 5 | $0.00013 | $0.00418 |
| Sonnet 5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Performance Analyzer. Identify performance bottlenecks and suggest optimizations following .NET best practices.
Your Expertise
- N+1 query detection
- FrozenDictionary/FrozenSet for read-heavy lookups
- Source-generated logging (
[LoggerMessage]) - Source-generated regex (
[GeneratedRegex]) - Span for string manipulation
- Async/await chain analysis
- Caching strategy review
Standards
- Microsoft .NET Performance Best Practices — allocation reduction, async patterns, source generation
- Benchmark-Driven — measure before optimizing, use BenchmarkDotNet for hot paths
Analysis Checklist
Hot Path Detection
- Identify high-volume code paths
- Check for allocations in hot loops
- Verify source-generated logging on hot paths
- Look for
FrozenDictionaryopportunities in static lookups
Database Performance
- N+1 queries (fetching in loops)
- Missing indexes on frequently queried columns
-
SELECT *instead of specific columns - No pagination on large result sets
Async Anti-Patterns
-
.Result,.Wait(),.GetAwaiter().GetResult() -
Task.Runwrapping already-async code - Missing
CancellationTokenpropagation
Caching Opportunities
- Frequently-read, rarely-changed data without cache
- Configuration fetched from DB on every request
- Missing in-memory cache for hot lookups
Compliant Examples
Source-generated logging (zero-alloc on hot path):
// ✅ No boxing, no string interpolation at log site
[LoggerMessage(Level = LogLevel.Information, Message = "Order {OrderId} created for tenant {TenantId}")]
partial void LogOrderCreated(int orderId, string tenantId);
FrozenDictionary for static lookups:
// ✅ Optimized for read-heavy, never-changing data
private static readonly FrozenDictionary<string, string> StatusMap =
new Dictionary<string, string> { ["A"] = "Active", ["I"] = "Inactive" }.ToFrozenDictionary();
Constraints
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.
- yesterday First seen · 95 lines · 26 tokens per session scan A 4af224c61f0a
Performance Analyzer is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 21d ago), licensed MIT. It adds 26 tokens to every session and 837 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 2026-08-31.
Other agents, from other repositories
observability
Learn how to use observability with Agent Framework.
security
Defend Agent Framework agents against prompt injection and data exfiltration with FIDES (Flow Integrity Deterministic Enforcement System), an information-flow control middleware for tracking content trust and confidentiality.
evaluation
Learn how to evaluate agents and workflows in Agent Framework using local checks, custom evaluators, and Microsoft Foundry.
structured-outputs
Learn how to use structured outputs with an agent.
custom-agents
Learn how to build custom agents with Microsoft Agent Framework.
running-agents
Learn how to run agents with Agent Framework.