agentmods.dev

wgm AGENTS.md

Repository instructions for wgm, a portable agent skill with validation scripts rather than a server to run. They describe its build, validation, operational notes, and code patterns.

In plain words
What is it for?
Running the project's validation harness, checking shell behavior, and working safely with Podman, Docker, temporary home directories, and platform-boundary tests.
Why use it?
They tell a coding agent how to verify changes and avoid treating simulated test results or real user files as reliable test evidence.

Instructions file for CodexOpenCode

3 3d ago A scan 314 tokens original MIT
View the source file agent-frontier/wgm
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/agent-frontier/wgm/agents-md
Clone the repo
git clone --depth 1 https://github.com/agent-frontier/wgm

Made for: Codex, OpenCode.

Per session 314 This file is loaded in full into every session.
When invoked 314 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 $0.00314 $0.00314
Opus 5 $0.00157 $0.00157
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00031 $0.00031

Measured 2d ago against content hash ba5a43bee594, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wgm 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 2d 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 · 32 lines

What it actually says

AGENTS.md

Build & run

This repository is a portable Agent Skill; it has no application server to start. Work from the repository root.

make validate

Validate (backpressure)

make validate

For focused work, run the named harness directly, then rerun make validate before handoff. The devcontainer harness prefers Podman and uses a disposable test tag; it may visibly skip real-engine cases only when neither Podman nor Docker is installed.

Operational notes

  • CONTRIBUTING.md is the canonical local-development SOP.
  • scripts/wgm_plugin_registry.py is a proposed/unwired host-adapter helper. The portable scripts/loop.sh does not invoke plugin hooks.
  • Use temporary HOME fixtures for plugin-registry tests; never depend on or mutate the operator's real ~/.copilot/skills.
  • WSL boundary harnesses may report simulated/unverified results. Do not call them Windows-origin field evidence unless a real Windows process ran the probe.

Codebase patterns

  • Shell behavior checks live in scripts/test-*.sh, use ok:/FAIL: output, and exit nonzero on any failed assertion.
  • Test comments explain the behavior each assertion protects.
  • Prefer existing Podman-first/Docker-fallback helpers and standard-library Python; avoid new runtime dependencies.
  • Documentation changes must keep docs/README.md, CONTRIBUTING.md, and docs/reference/gates.md aligned.
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. 2d ago First seen · 32 lines · 314 tokens per session scan A ba5a43bee594

Subscribe to this mod's changes

wgm AGENTS.md is an instructions file published in the GitHub repository agent-frontier/wgm (3 stars, last pushed 3d ago), licensed MIT. It adds 314 tokens to every session, about $0.0016 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.

Code GenerationLLMagent-skillagentskillsai-codingcopilot
Related

Other instructions, from other repositories

memorix GEMINI.md

Instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.

AVIDS2/memorix · 846 tokens

Ctxo CLAUDE.md

Instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).

alperhankendi/Ctxo · 5,885 tokens

nopua AGENTS.md

Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.

wuji-labs/nopua · 546 tokens

specialist-agent CLAUDE.md

Instructions for herbert-julio-azion/specialist-agent, covering claude.md - specialist agent, about, auto-dispatch rules, available agents and core agents.

herbert-julio-azion/specialist-agent · 3,558 tokens

Perigon.CLI copilot-instructions.md

Instructions for AterDev/Perigon.CLI, covering github copilot instructions, general guidelines, 技术栈, 项目结构与分层 and 代码风格约定.

AterDev/Perigon.CLI · 1,254 tokens

wove copilot-instructions.md

Instructions for mits-pl/wove, covering wave terminal — copilot instructions, project rules, skill guides and preview server.

mits-pl/wove · 816 tokens