Borrowing it
Nothing to install: this file belongs to tjqscott/dory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tjqscott/dory/main/AGENTS.mdgit clone --depth 1 https://github.com/tjqscott/doryWrote 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/tjqscott/dory/agents-md)<a href="https://agentmods.dev/instructions/tjqscott/dory/agents-md"><img src="https://agentmods.dev/badge/instructions/tjqscott/dory/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/tjqscott/dory/agents-md"><img src="https://agentmods.dev/badge/instructions/tjqscott/dory/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01432 | $0.01432 |
| Opus 5.5 | $0.00573 | $0.00573 |
| Sonnet 5.5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
dory 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 17d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dory Directives
How an agent works on a project that uses Dory. Sections I–III apply everywhere. Section IV applies in a browser chat, where dory.html supplies the posting format. Sections V and VI apply where the agent can read and write the repo (Claude Code, Codex).
I. Core Behaviors
- Intent-First: Prioritize structural goals and system architecture over the literal wording of a request. State your assumptions. When a request has more than one reading, name them rather than picking one silently. When something is unclear, stop and ask.
- Zero-Padding: No conversational wrapping, introductions or recaps. Lead with the answer or the code.
- Decomposition: For complex tasks, state the phase:
[PLANNING]➔[IMPLEMENTING]➔[TESTING]➔[ITERATING]. Give each planned step a check that proves it done: "add validation" becomes "a test with invalid input fails, then passes". Optional for small, isolated requests. - Diverge, then converge, on visuals: Offer a few mockups that differ in direction, not in detail. Once one is chosen, refine that one. Build them with real content, end with your pick and why, and treat any reference as inspiration, not a template.
II. Tactical Engineering
- Minimalism: The least code that solves the problem. No speculative features, single-use abstractions, unrequested configuration, handling for impossible errors, or obvious comments. If 200 lines could be 50, rewrite it.
- Surgical Changes: Touch only what the request needs, in the style already there. Anything beyond that is named in one line, not done silently. Remove what your own change left unused; mention pre-existing dead code rather than deleting it.
- Terminal Aesthetics: Format outputs for clean real-time feedback. Use left/right justification (
.ljust()), self-flushing prints (flush=True), and single-line progress indicators to avoid verbose log clutter. - Verification Loop: Check directory structures and data files before writing code: run
ls,grepandheadwhere you can, and ask for their output where you cannot. Do not make assumptions regarding the local environment. - Iteration Limits: If
[TESTING]fails, enter[ITERATING]with the exact error. If iteration stops making progress, record the failing state and recommend a fresh session.
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.
- 17d ago First seen · 49 lines · 1,432 tokens per session scan A 1b4ff703700c
dory AGENTS.md is an instructions file published in the GitHub repository tjqscott/dory (60 stars, last pushed 11d ago), licensed MIT. It adds 1,432 tokens to every session, about $0.0057 per session on Opus 5.5. 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 2026-09-29.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).