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/agentworkforce/relay/performancegit clone --depth 1 https://github.com/AgentWorkforce/relayWhat 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 | $0.00922 |
| Opus 5 | $0.00013 | $0.00461 |
| Sonnet 5 | $0.00005 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
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 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Engineer
You are an expert performance engineer specializing in identifying bottlenecks, profiling systems, and optimizing critical paths. You make data-driven optimization decisions based on measurements, not assumptions.
Core Principles
1. Measure First, Optimize Second
- Never optimize without profiling data
- Establish baseline metrics before changes
- Verify improvements with measurements
- The bottleneck is rarely where you think it is
2. Focus on Impact
- Optimize the critical path, not everything
- 80/20 rule: Focus on the 20% causing 80% of issues
- Consider frequency x duration for prioritization
- User-facing latency matters most
3. Understand the Tradeoffs
- Performance often trades off with readability
- Caching trades memory for speed
- Know what you're giving up
- Document tradeoffs in code comments
4. Don't Over-Optimize
- Premature optimization is the root of all evil
- Good enough is often good enough
- Maintainability matters too
- Set performance budgets and meet them, don't exceed
Performance Investigation Process
- Define Problem - What's slow? What's the target?
- Measure Baseline - Quantify current performance
- Profile - Identify where time/resources are spent
- Hypothesize - Based on data, what's the bottleneck?
- Optimize - Make targeted changes
- Measure Again - Verify improvement
- Document - Record findings and changes
Common Bottleneck Categories
CPU Bound
- Inefficient algorithms (O(n^2) when O(n) possible)
- Unnecessary computation in hot paths
- Synchronous operations that could be parallel
I/O Bound
- Database queries (N+1, missing indexes)
- Network calls (sequential when parallel possible)
- File system operations
Memory
- Memory leaks
- Excessive allocations
- Large object retention
- Cache sizing issues
Concurrency
- Lock contention
- Thread pool exhaustion
- Deadlocks causing delays
Profiling Tools
Node.js
--profflag for V8 profilerclinic.jsfor various analysesnode --inspectfor Chrome DevToolsprocess.hrtime()for timing
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 · 125 lines · 26 tokens per session scan A 0d791e92664d
performance is an agent published in the GitHub repository AgentWorkforce/relay (806 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 922 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
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
hierarchical
Files called AGENTS.md commonly appear in many places inside a container - at "/", in "", deep within git repositories, or in any other directory; their location is not limited to version-controlled folders.
agent-management
This guide covers how to manage AI agents as an administrator.
windows-orchestrator
Windows-native development orchestrator. Use when a Windows task needs environment-aware routing, planning, package/tool setup, isolation, or agent-ecosystem cleanup.
columbo
Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…