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 instructions/jsohi/app-trading-engine/agents-mdgit clone --depth 1 https://github.com/jsohi/app-trading-engineWrote 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/instructions/jsohi/app-trading-engine/agents-md)<a href="https://agentmods.dev/instructions/jsohi/app-trading-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/jsohi/app-trading-engine/agents-md.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 | $0.03887 | $0.03887 |
| Opus 5 | $0.01944 | $0.01944 |
| Sonnet 5 | $0.00777 | $0.00777 |
| Haiku 4.5 | $0.00389 | $0.00389 |
Grade A, and why
app-trading-engine AGENTS.md 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 4d 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Implementation Plan — Trading Engine
Context
Plan the sequence, agent roles, and verification strategy for implementing 66 Linear issues (APP-5 through APP-70, non-contiguous) using AI coding agents. The project is greenfield (no code exists). The goal is to maximize parallelism, ensure quality via review/test agents, and deliver a working trading engine end-to-end.
Note: See
docs/wave-plan.mdfor the authoritative wave-by-wave issue list (13 waves, 66 issues). This file focuses on agent roles, prompts, and operational protocol.
Agent Roles
1. Implementer Agent
- Writes code for a single issue
- Runs in an isolated worktree (git branch per issue)
- Has full context: issue description, CLAUDE.md, dependency code from merged branches
- Creates a PR when done
2. Reviewer Agent
- Reviews PRs created by Implementer agents
- Checks: correctness, patterns consistency, CLAUDE.md conventions, security, performance
- Posts review comments or approves
- Flags: allocation in hot path, non-deterministic code in cluster, floating-point instead of fixed-point
3. Test Agent
- Runs after Implementer completes, before PR merge
- Executes:
./gradlew build,./gradlew test, type-checks - For integration test issues: spins up the full stack and runs the test suite
- Reports pass/fail with logs
4. Orchestrator (You / Human)
- Manages the wave sequence below
- Merges approved PRs in dependency order
- Triggers next wave when current wave's PRs are merged
- Resolves conflicts between parallel branches
Implementation Waves
Wave 1 — Foundation (1 issue, serial)
Must complete first. Everything depends on this.
| Issue | Title | Agent Config |
|---|---|---|
| APP-5 | Scaffold Gradle multi-module project | Implementer → Reviewer → Test (./gradlew projects && ./gradlew build) |
Verification: ./gradlew projects shows all 14 subprojects, ./gradlew build succeeds, CLAUDE.md exists.
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.
- 4d ago First seen · 342 lines · 3,887 tokens per session scan A 8b0f443999e1
app-trading-engine AGENTS.md is an instructions file published in the GitHub repository jsohi/app-trading-engine (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 3,887 tokens to every session, about $0.0194 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 instructions, from other repositories
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.
bullet-bots AGENTS.md
Instructions for bulletxyz/bullet-bots, covering bullet-bots, build & test, run the faucet curl printed by keygen, then, or (base58 from phantom/delegation export, or hex) and architecture — the harness, feeds, and actors.
romaco-mcp AGENTS.md
AGENTS.md instructions for romaco-labs/romaco-mcp, covering purpose, read first, product boundaries, architecture invariants and development method.
financial-services-plugins-new CLAUDE.md
Claude Code instructions for yuping322/financial-services-plugins-new, covering financial services plugins, repository structure, plugin structure, key files and development workflow.
zenmoney-mcp CLAUDE.md
Claude Code instructions for sakost/zenmoney-mcp, covering zenmoney mcp server — development guidelines, project overview, build & test, architecture and coding standards.