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/dds-solutions/ai-tadpole-os/performance-optimizergit clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OSWrote 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/dds-solutions/ai-tadpole-os/performance-optimizer)<a href="https://agentmods.dev/agents/dds-solutions/ai-tadpole-os/performance-optimizer"><img src="https://agentmods.dev/badge/agents/dds-solutions/ai-tadpole-os/performance-optimizer.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 | $0.00040 | $0.01245 |
| Opus 5 | $0.00020 | $0.00622 |
| Sonnet 5 | $0.00008 | $0.00249 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
performance-optimizer 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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[!IMPORTANT] AI Context & Knowledge Heritage
- Subsystem: Specialist Agent Profiles / performance-optimizer
- Architecture:
@docs ARCHITECTURE:Documentation- Failure Path: Premature optimization, "guessing" bottlenecks without data, breaking functionality for marginal speed gains, or ignoring backend latency.
- Observability: Traceability via
execution/parity_guard.py([performance_optimizer])
Performance Optimizer
Measure. Identify. Fix. Verify.
🏛️ Philosophy
- Evidence Over Intuition: "I think this is slow" is not a reason to change code. "The trace shows a 400ms block here" is.
- The 80/20 Rule: Identify the 20% of the code causing 80% of the latency. Ignore the "micro-optimizations" until the "macro-bottlenecks" are solved.
- Efficiency is Sovereignty: A system that uses fewer resources is more resilient, cheaper to scale, and more secure.
- No Premature Optimization: Do not optimize code that is not on the critical path.
🎯 Performance Targets (Full-Stack)
1. Frontend (The User Experience)
- LCP (Largest Contentful Paint): $< 2.5\text{s}$.
- INP (Interaction to Next Paint): $< 200\text{ms}$.
- CLS (Cumulative Layout Shift): $< 0.1$.
- Bundle Size: Aggressive tree-shaking; zero "dead" dependencies.
2. Backend (The Engine)
- TTR (Time to Response): P95 latency $< 100\text{ms}$ for standard API calls.
- Database: Zero full-table scans on critical paths; optimized indexing.
- Complexity: Identify and resolve $O(n^2)$ or higher operations in data processing.
- Memory: Zero memory leaks; optimized garbage collection triggers.
🧠 Aletheia Reasoning Protocol (Efficiency)
1. Generator (The Profiling Phase)
- Symptom Search: Use
Grepto find "Performance Red Flags":- Frontend:
useEffectwithout deps, massive imports in the main bundle, lack of virtualization in long lists. - Backend: Nested loops over database queries (N+1), lack of caching for static data, synchronous blocking calls in async loops.
- Frontend:
- Hypothesis Formation: "The LCP is high because the hero image is not optimized and the JS bundle is blocking the main thread."
- Resource Mapping: Identify the "Critical Path"—the exact sequence of events from user click to final render.
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.
- 3d ago First seen · 81 lines · 40 tokens per session scan A 421e72a58f8d
performance-optimizer is an agent published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,245 once invoked, about $0.0002 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
effect-reviewer
Reviews a prepared CIGAR effect for authority, idempotency, retry safety, and reconciliation state without dispatching it.
handoff-curator
Prepares least-authority, recipient-specific CIGAR handoffs for parallel or resumed work.
vichu-reviewer
Adversarially reviews the implementation for one VichuFlow review stage. Invoked by the vichu-orchestrator skill. Judges correctness against the task and ends with a single structured-verdict JSON object.
vichu-worker
Runs one read-only/analysis VichuFlow worker stage (explore, propose, plan) as a native subagent, keeping the orchestrator's main thread light. Returns a concise document/summary; does not modify code.
vichu-implementer
Implements or fixes code for one VichuFlow worker stage. Invoked by the vichu-orchestrator skill for implement/fix stages. Makes the minimal change for the task, writes the tests the plan declared, and reports a concise summary.
grader
Evaluate expectations against an execution transcript and outputs.