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 skills add devantler-tech/agent-plugins --skill agent-instructionsgit clone --depth 1 https://github.com/devantler-tech/agent-pluginsWrote 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/skills/devantler-tech/agent-plugins/agent-instructions)<a href="https://agentmods.dev/skills/devantler-tech/agent-plugins/agent-instructions"><img src="https://agentmods.dev/badge/skills/devantler-tech/agent-plugins/agent-instructions/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/skills/devantler-tech/agent-plugins/agent-instructions"><img src="https://agentmods.dev/badge/skills/devantler-tech/agent-plugins/agent-instructions.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 | $0.00127 | $0.02905 |
| Opus 5.5 | $0.00051 | $0.01162 |
| Sonnet 5.5 | $0.00025 | $0.00581 |
| Haiku 4.5 | $0.00013 | $0.00291 |
Grade A, and why
agent-instructions 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 16d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Most AI coding tools read project guidance from a file in the repo — historically each looked in a
different place (AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, …). Copy the same
guidance into each one and the copies drift: a command changes in one file and the others keep
telling agents the old way. The fix is one canonical source plus thin tool-specific shims
(which include the canonical file). Give each durable rule one canonical home: the root core,
a linked topic guide, or a nested instruction file. Keep genuine tool-specific quirks in a tool's own file.
The good news: AGENTS.md is now read by nearly every major tool — including GitHub Copilot — so
shared guidance can have one maintained source without a per-tool copy.
The canonical file: AGENTS.md
AGENTS.md is the cross-tool standard — a plain-Markdown file at the repo root, read natively by a
growing set of agents and editors (Codex, Cursor, Gemini CLI, and GitHub Copilot). Make it the
entrypoint for durable, tool-neutral guidance:
- What the project is — one-paragraph purpose, the stack, where the important code lives.
- How to build, test, validate, and run — the exact commands an agent should use (and which one gates a PR). Be specific; agents run these verbatim.
- Conventions — code style, naming, commit/PR format, branch model, "definition of done".
- Do / don't — guardrails (never hand-edit generated files, never push to
main, secret handling) and the project's non-obvious gotchas. - Pointers — links to deeper docs rather than inlining them.
Write it tool-neutral: no "when you are Claude…" assumptions. Anything true only for one tool goes in that tool's file, not here. Keep it readable and scoped: always-loaded guidance consumes context even when most of it is unrelated to the task.
Nested AGENTS.md. In a monorepo or a large sub-package, drop an AGENTS.md in the subdirectory:
tools that support the standard read the nearest one and let it take precedence over the root on
conflicts. Reach for this before a path-scoped tool-specific file when the guidance is itself
tool-neutral.
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.
- 16d ago Changed · +48 lines a623f30eca67
- 1mo ago First seen · 127 lines · 127 tokens per session scan A cddd5e98732e
agent-instructions is a skill published in the GitHub repository devantler-tech/agent-plugins (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 127 tokens to every session and 2,905 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…
cold-start-problem
Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…