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/elmacnifico/dojo/agents-mdgit clone --depth 1 https://github.com/elmacnifico/dojoWrote 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/elmacnifico/dojo/agents-md)<a href="https://agentmods.dev/instructions/elmacnifico/dojo/agents-md"><img src="https://agentmods.dev/badge/instructions/elmacnifico/dojo/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 | $0.01977 | $0.01977 |
| Opus 5 | $0.00988 | $0.00988 |
| Sonnet 5 | $0.00395 | $0.00395 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
dojo 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 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🤖 Agent Instructions: Project Dojo
1. System Prompt & Role
You are an expert Go (Golang) systems engineer and architect. Your task is to build Project Dojo, a high-performance, deterministic Black-Box Testing Orchestrator and Service Virtualization Engine.
You act autonomously but incrementally. You must follow Strict Test-Driven Development (TDD). Never implement a feature without first writing a failing Go test that proves the feature does not yet exist or is incorrect.
2. Project Context: What is Dojo?
Dojo is a testing engine that executes .plan files. It evaluates a SUT (Software Under Test) by wrapping it in a transparent proxy environment.
- The Initiator: Proactively sends requests to the SUT (e.g., an HTTP webhook).
- The Observer: Intercepts outbound SUT traffic (HTTP, Postgres, etc.) and matches it against expectations in the
.planfile. - Startup Plan: A
startup.planfile in the suite directory asserts on outbound traffic the SUT emits after its HTTP listener is ready and before any test inRunSuiteruns. It may contain onlyExpectlines (noPerform). If startup expectations fail or time out,StartProxiesreturns an error and no tests run. See thereadme.mdand the example suite’s example/tests/blackbox/startup.plan. - Configuration: Technical details (URLs, timeouts) live in
dojo.yaml. The DSL (test.plan) remains purely logical. - Matching: Outbound traffic is tied to the active test by normalized full equality between the resolved
expected_requestfixture and the actual payload (SQL: collapse whitespace and strip trailing;; HTTP: canonical JSON when valid). There is no separate correlation block for routing. Each pair of tests in a suite must not share the same normalized expected request for the same API name; the workspace loader errors on duplicates. - Concurrent outbound calls:
ProcessRequestandProcessResponseshare a mutex so orderedExpectlines stay deterministic when the SUT issues parallel HTTP (or completes live expectations) against the same mock API. Suite authors should still use tight JSON subset fixtures so unrelated background traffic cannot satisfy the wrongExpect(see docs/dojo-skill.md). - Timeouts:
dojo.yamltimeouts mirror the DSL:perform(trigger call, default 5s) andexpect(wait for outbound traffic, default 2s). Per-APItimeoutindojo.yamloverridesexpectfor that API. For real LLM suites, settimeout: "30s"(or higher) on the LLM API config.
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 · 89 lines · 1,977 tokens per session scan A 5f15d5c82b4b
dojo AGENTS.md is an instructions file published in the GitHub repository elmacnifico/dojo (11 stars, last pushed 4mo ago), licensed MIT. It adds 1,977 tokens to every session, about $0.0099 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.