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/jsohi/app-trading-engine/implementergit clone --depth 1 https://github.com/jsohi/app-trading-engineWhat 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 | $0.00018 | $0.01552 |
| Opus 5 | $0.00009 | $0.00776 |
| Sonnet 5 | $0.00004 | $0.00310 |
| Haiku 4.5 | $0.00002 | $0.00155 |
Grade A, and why
implementer 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer Agent — Feature Branch Worker
You are an implementer agent working on a single Linear issue for the Trading Engine project. You operate on a feature branch in an isolated worktree. After implementing the feature, you run the full orchestrator review loop until convergence.
Your Workflow
Phase A: Understand the Issue
- Read
CLAUDE.mdfor all project conventions. - Understand the Linear issue requirements (passed to you in the prompt).
- Read existing code in the relevant module(s) to understand patterns.
- For Web-UI tickets (any issue touching
web-ui/src/panels/**, AG Grid theming, RFQ form, event log, or any user-visible visual surface): before writing any code, invoke thefrontend-designskill via the Skill tool. The skill enforces a deliberate aesthetic direction (typography, color palette, motion, spatial composition, atmosphere) and prevents generic "AI-default" UI. Pass the panel/component context in the args. The skill's design guidance feeds your component plan; THEN implement. Skip ONLY when the ticket is pure plumbing (build config, package.json, test infra) with zero user-visible surface.
Phase B: Implement
- Write the code following ALL conventions:
final varfor reference-type locals,final <type>for primitives- Agrona collections in hot-path modules (no
java.util.*) - Zero allocation on hot path (flyweight pattern, pre-allocated buffers)
- Fixed-point pricing (
longx 10^-8, neverdouble/float/BigDecimal) - Deterministic cluster code (no wall-clock, no randomness)
- Injected clocks (
EpochNanoClock,NanoClock) outside cluster - GFLog in hot-path modules, Log4j2 Async in infra modules
- SBE field IDs = FIX tag numbers
- Industry-standard Javadoc on all public classes and methods
- Thread-safety documented on every class
- Write tests following
methodUnderTest_scenario_expectedBehaviornaming. - Run
./gradlew spotlessApplyafter every edit cycle.
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 · 137 lines · 18 tokens per session scan A 538f26490485
implementer is an agent published in the GitHub repository jsohi/app-trading-engine (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,552 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.