What is a0_agent_skills AGENTS.md?

A software-development workflow package for Agent Zero that covers specification, planning, building, testing, review, and shipping. It includes 21 skills, specialist review agents, slash commands, routing instructions, and optional telemetry.

Running structured software projects from initial specification through code review, security checks, testing, simplification, and release.

It gives an agent a repeatable development process instead of leaving requirements, implementation, testing, and review as disconnected steps.

How vanja-emichi/a0_agent_skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to vanja-emichi/a0_agent_skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/vanja-emichi/a0_agent_skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/vanja-emichi/a0_agent_skills

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vanja-emichi/a0_agent_skills/agents-md.svg)](https://agentmods.dev/instructions/vanja-emichi/a0_agent_skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/vanja-emichi/a0_agent_skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vanja-emichi/a0_agent_skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,198 This file is loaded in full into every session.

When invoked 1,198 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01198	$0.01198
Opus 5	$0.00599	$0.00599
Sonnet 5	$0.00240	$0.00240
Haiku 4.5	$0.00120	$0.00120

Measured 7d ago against content hash f1915d0797df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

a0_agent_skills 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 7d 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.

AGENTS.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — a0_agent_skills

Purpose

Agent Zero plugin that ports the addyosmani/agent-skills development-workflow toolkit into the Agent Zero plugin system. Gives any Agent Zero agent a production-grade software-engineering lifecycle: spec → plan → build → verify → review → ship.

Ships:

21 skills (skills/), each a SKILL.md, organized across the 6-phase lifecycle.
3 specialist agent profiles (agents/): code-reviewer, security-auditor, test-engineer — invoked via call_subordinate.
7 slash commands (commands/): /spec, /plan, /build, /test, /review, /code-simplify, /ship — require the commands plugin.
Declarative routing injected into every session via a system_prompt extension (works regardless of whether a project is active).
Telemetry — opt-in JSONL logging of every skills_tool activation for workflow validation.

Knowledge

Owning KB: none dedicated — catalog entry in ~/knowledge/agent_zero_plugins (② Tool). Promote to a dedicated KB if this plugin grows substantial durable knowledge (Hub placement rule #7).
Access: OpenKnowledge MCP only — cwd: ~/knowledge/agent_zero_plugins. Tools: exec, search, write, edit, audit, lint. Never lsp on KB markdown.
Fleet index: vanja-emichi/vbunjevac → registry/repos.md.

Ownership

Repo: vanja-emichi/a0_agent_skills (Vanja's fleet, account vanja-emichi / git identity vbunjevac).
Provenance: Ported from addyosmani/agent-skills by Addy Osmani, adapted to the Agent Zero plugin system.
Current version: 0.4.0 (see plugin.yaml, CHANGELOG.md).

Local Contracts

plugin.yaml — plugin manifest (name, title, description, version, settings_sections: [agent], per_project_config: true).
skills/<name>/SKILL.md — one self-contained skill per directory; the 21 skills are the core deliverable. using-agent-skills is a meta-skill loaded on demand (never pinned).
commands/<name>.command.yaml + <name>.txt|py — slash-command definitions; /ship is implemented in Python (ship.py), the rest are text prompts. Depends on the commands plugin for dispatch.
agents/<profile>/ — specialist subordinate profiles; invoked only by the orchestrator (profiles never call each other).
extensions/python/system_prompt/_15_agent_skills_routing.py — the routing entry point. Reads prompts/agent.skills.routing.md at runtime and appends routing rules to the system prompt during assembly (universal, project-active or not).
extensions/python/tool_execute_after/_05_skill_telemetry.py — appends one JSON line per skills_tool activation when telemetry is enabled; failures never interrupt the agent.
hooks.py — intentionally empty lifecycle stubs (install/uninstall/pre_update). Routing is handled by the extension above, NOT here.
default_config.yaml — telemetry defaults (telemetry_enabled, telemetry_log_path, telemetry_max_lines).
tests/ — pytest suite covering telemetry defaults/hooks, enforcement language, and skill telemetry.

Read the full file on GitHub · 55 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.

7d ago First seen · 55 lines · 1,198 tokens per session scan A f1915d0797df

Subscribe to this mod's changes

a0_agent_skills AGENTS.md is an instructions file published in the GitHub repository vanja-emichi/a0_agent_skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,198 tokens to every session, about $0.0060 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.

Building agents Planning

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

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).

microsoft/vscode · 6,785 tokens

a0_agent_skills: Instructions file for Codex