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/akhayam99/goodboy/agents-mdgit clone --depth 1 https://github.com/akhayam99/goodboyWrote 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/akhayam99/goodboy/agents-md)<a href="https://agentmods.dev/instructions/akhayam99/goodboy/agents-md"><img src="https://agentmods.dev/badge/instructions/akhayam99/goodboy/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 | $0.01263 | $0.01263 |
| Opus 5 | $0.00632 | $0.00632 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
goodboy 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Read this when you're an agent about to write code here and need the working-memory floor and forbidden-patterns checklist. Not for monorepo process rules, which live in CONVENTIONS.md.
Agent-agnostic code conventions. Process and monorepo rules live in CONVENTIONS.md. Full layout and test placement live in docs/file-system.md.
Where new code goes
- One feature only:
features/<domain>/. - App routing, layout, or boot:
app/components/<Name>/. - Reusable and cross-feature placement follows the boundary in docs/file-system.md.
- Zustand state:
store/slices/<domain>/. - Database migrations follow docs/architecture.md.
Naming
- Components and their folders use
PascalCase. - Utilities, helpers, and hooks use
camelCase; hooks prefixuse. - A file matches its primary export. Constants use
SCREAMING_SNAKE_CASE. - Booleans prefix
is,has,can, orshould. - Components use a local
type Props. Function, hook, and utility parameter types follow the completeParamsrule in docs/typescript/components.md. - Domain and data types keep descriptive names.
Components and exports
Sub-components do not live inline in a parent component file. Extract them to
a sibling file in the same folder. A reusable utility goes to
shared/utils/; a domain-owned utility stays beside its owner.
Keep one main export per file. Keep public barrels minimal, and import internal cross-file dependencies from their source. Full component and export rules live in docs/typescript/components.md.
Store selectors and memoization
- A
useAppStoreselector returns a primitive or a reference the store owns. A fresh collection needsuseShallowor the required proof directive. - Select the keys a consumer needs, never a whole write-heavy slice.
useShallowdoes not make a broad subscription acceptable. - Memoize a list row only when its props are primitives or stable references, and memoize the work behind it.
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 · 115 lines · 1,263 tokens per session scan A 651db325b3db
goodboy AGENTS.md is an instructions file published in the GitHub repository akhayam99/goodboy (89 stars, last pushed today), licensed MIT. It adds 1,263 tokens to every session, about $0.0063 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
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
codedb copilot-instructions.md
Copilot instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
codedb CLAUDE.md
Claude Code instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
evolve AGENTS.md
AGENTS.md instructions for bitwise-media-group/evolve, covering agent orientation, what this is, layout, commands (cmd/evolve/) and packages (internal/).
imagine-mcp CLAUDE.md
Claude Code instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.
imagine-mcp AGENTS.md
AGENTS.md instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.