agent-plugins AGENTS.md

Repository instructions for devantler-tech/agent-plugins, a marketplace of add-ons for coding agents. They describe the repository layout, supported tools, and the two marketplace manifests that must stay aligned.

In plain words
What is it for?
Use them when changing plugin manifests, adding agent resources, checking repository conventions, or working with the related agent-skills source.
Why use it?
They give contributors the rules and structure needed to add or maintain plugins consistently across VS Code, GitHub Copilot CLI, and Claude Code.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/devantler-tech/agent-plugins/agents-md
Clone the repo
git clone --depth 1 https://github.com/devantler-tech/agent-plugins

Made for: Codex, OpenCode.

Per session 4,990 This file is loaded in full into every session.
When invoked 4,990 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.04990 $0.04990
Opus 5 $0.02495 $0.02495
Sonnet 5 $0.00998 $0.00998
Haiku 4.5 $0.00499 $0.00499

Measured yesterday against content hash 3d56f3491fd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-plugins 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 yesterday.

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.

AGENTS.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

devantler-tech/agent-plugins

A tool-neutral agent-plugin marketplace that bundles the curated agent skills from devantler-tech/agent-skills into category-based plugins. A single marketplace install works across VS Code, GitHub Copilot CLI, and Claude Code via two parity-checked manifests. Sibling repo to devantler-tech/agent-skills (the curated skill index this marketplace draws from).

By design the marketplace is not scoped to skills-only — a plugin may bundle any agent resource (agent skills today; MCP servers and custom agents as they prove out across the supported tools), which is what keeps it a tool-neutral, industry-standard marketplace. The cross-tool capability matrix and the manifest/CI plan for the first non-skill resource are recorded in ADR 0001.

This file is the single canonical instructions file for the repository. It is read natively by GitHub Copilot, and by Cursor, Codex, and Claude (via CLAUDE.md@AGENTS.md).

Repository Structure

.claude-plugin/
└── marketplace.json            # Claude Code marketplace manifest
.github/
├── plugin/
│   └── marketplace.json        # Copilot / VS Code marketplace manifest (kept in parity with the Claude one)
└── workflows/
    ├── ci.yaml                 # Runs scripts/validate-manifests.sh + lint-scripts (shellcheck + self-test) + agentskills.io spec per skill
    └── update-agent-skills.yaml  # Daily gh skill update --all; opens a PR when upstream skills drift
plugins/
└── <plugin>/
    ├── plugin.json             # Portable Copilot / CLI plugin manifest
    ├── .claude-plugin/
    │   └── plugin.json         # Equivalent strict Claude marketplace manifest; CI rejects drift
    ├── agents/                 # Optional auto-discovered custom agents (*.agent.md)
    ├── scripts/                # Optional helpers the plugin's agents call, each with a *.test.sh
    ├── skills/
    │   └── <skill>/SKILL.md    # An installed skill copied from upstream, with metadata.github-* provenance
    └── resources/              # Optional ancillary, explicitly linked human-consumed assets
scripts/
├── validate-manifests.sh       # Manifest + parity + plugin.json + README-table + skill-provenance guard (single source of truth; run locally before pushing)
├── validate-manifests.test.sh  # Self-test: PASS a consistent fixture, FAIL each drift scenario the guard catches
├── check-plugin-version-bump.sh      # Gate: a plugin whose shipped content changed must move its version
├── check-plugin-version-bump.test.sh # Self-test for the gate above
├── guard-bundled-skill-edits.sh      # Gate: refuse a hand-edit to a synced skill tree, naming its upstream
├── guard-bundled-skill-edits.test.sh # Self-test for the gate above
├── bump-plugin-version.sh      # Move a plugin's version across all four manifests (the fix the gate points at)
└── bump-plugin-version.test.sh # Self-test for the bump helper
README.md                       # Human-facing index — the plugin table + per-tool install instructions

Read the full file on GitHub · 273 lines

Changes

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.

  1. yesterday First seen · 273 lines · 4,990 tokens per session scan A 3d56f3491fd7

Subscribe to this mod's changes

agent-plugins AGENTS.md is an instructions file published in the GitHub repository devantler-tech/agent-plugins (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,990 tokens to every session, about $0.0249 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 2026-08-31.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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).

microsoft/vscode · 5,001 tokens

spec-kit 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.

github/spec-kit · 7,040 tokens

langchain 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.

langchain-ai/langchain · 4,345 tokens