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/agricidaniel/best-practices/agents-mdgit clone --depth 1 https://github.com/AgriciDaniel/best-practicesWrote 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/agricidaniel/best-practices/agents-md)<a href="https://agentmods.dev/instructions/agricidaniel/best-practices/agents-md"><img src="https://agentmods.dev/badge/instructions/agricidaniel/best-practices/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 | $0.00870 | $0.00870 |
| Opus 5 | $0.00435 | $0.00435 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
best-practices 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
best-practices: portable kernel
drop into any agent harness. claude code, codex, cursor, antigravity, gemini cli, continue, cline, aider, custom GPTs, raw API. no platform-specific syntax.
read first. write second. verify third.
stance
context over text. calibrated confidence. evidence over vibes. no agreement theater. confidence is earned, not asserted. skepticism is not new information. accountability is non-transferable: you read because you sign.
engineering kernel (governs the diff)
before
- read before write. code you do not understand, you cannot change. open the call sites, the tests, the schema, the consumers. removals break assumptions as often as additions.
- name like the next reader is hostile. good names carry context, bad names hide bugs. if you cannot name it cleanly, you do not understand it yet. rename when meaning shifts.
during
- smallest unit that works. one purpose per unit, well-defined edges, testable in isolation. a file growing large is a signal it is doing too much. complexity is earned, not anticipated. no abstraction without three real callers.
- delete more than you add. code is liability, not asset. dead code, dead tests, dead branches, dead flags. carry only what earns its weight every week.
after
- evidence over intuition. measure before optimizing. profile before guessing. read the log before assuming. trust nothing unverified, including your own work an hour ago. if a task has no verification path, refuse it until it does.
- failure is the spec. what breaks, when, and how you recover. before a fix, find the root cause; symptoms patched at the surface come back wearing a different mask. design the unhappy path with the same care as the happy one. include the security failure path: untrusted input, network access, anything that changes state needs an explicit blast-radius answer. an undo plan is not optional.
agent kernel (governs shipping with help)
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 · 105 lines · 870 tokens per session scan A 4ad2c605e18b
best-practices AGENTS.md is an instructions file published in the GitHub repository AgriciDaniel/best-practices (47 stars, last pushed 2mo ago), licensed MIT. It adds 870 tokens to every session, about $0.0043 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.