agentmods.dev

agentplugins AGENTS.md

Repository instructions for agentplugins, a project that builds add-ons for several coding-agent applications. They define supported agents, compatibility expectations, architecture choices, and branch and commit rules.

In plain words
What is it for?
Use them when adding or modifying an add-on, adapter, compatibility entry, implementation plan, branch, or commit.
Why use it?
They help contributors keep features consistent across supported agents and make changes easy to review and release. The compatibility matrix shows where a feature works universally and where agent-specific handling is needed.

Instructions file for CodexOpenCode

10 2mo ago A scan 352 tokens original Apache-2.0
View the source file sigilco/agentplugins
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/sigilco/agentplugins/agents-md
Clone the repo
git clone --depth 1 https://github.com/sigilco/agentplugins

Made for: Codex, OpenCode.

Per session 352 This file is loaded in full into every session.
When invoked 352 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 $0.00352 $0.00352
Opus 5 $0.00176 $0.00176
Sonnet 5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured yesterday against content hash 0ac3ac8f2dde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentplugins 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 · 21 lines

What it actually says

GitHub Project is https://github.com/users/espetro/projects/14 .

Operating Principles

Tier-1 harnesses: Claude Code, Codex, OpenCode, Pi Mono. Tier-2: Copilot, Gemini, Kimi.

  1. Tier-1 parity is the bar. Every shipped capability must work across all four Tier-1 harnesses at the functionality level (not TUI level).
  2. Codegen first, guided per-harness fallback second. Universal codegen where possible; otherwise guide the author via the escape hatch rather than dropping the feature.
  3. Compat matrix is the contract. docs/guide/capability-matrix.md — universal-codegen / guided-per-harness / unsupported, per harness. Keep it current.
  4. Lean, no global SDK. Primitives express intent; each adapter owns its plumbing.
  5. Community plugins are ground-up rewrites in agentplugins-<name> sibling repos (e.g. ../agentplugins-caveman), not mechanical ports.

Full detail: prd.md

Commit & branch conventions

  • Atomic conventional commits (feat(adapter-pimono): fix subagentStop collision)
  • Feature work on feat/* branches off develop; merge to develop, then PR develop → main to release
  • All plans in .agents/plans/<date>-<purpose>.md before implementation begins
  • All work linked to a refined issue in Project 14
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 · 21 lines · 352 tokens per session scan A 0ac3ac8f2dde

Subscribe to this mod's changes

agentplugins AGENTS.md is an instructions file published in the GitHub repository sigilco/agentplugins (10 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 352 tokens to every session, about $0.0018 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.

Git and workflowPlanningagentsaiclaude-codecodexdevtoolsopencode
Related

Other instructions, from other repositories

vendo CLAUDE.md

Instructions for runvendo/vendo, covering vendo, layout, commands, vendo cloud and rules.

runvendo/vendo · 2,250 tokens

paseo CLAUDE.md

Claude Code instructions for getpaseo/paseo, covering claude.md, repository map, docs, writing docs and doc voice.

getpaseo/paseo · 4,236 tokens

greywall CLAUDE.md

Instructions for GreyhavenHQ/greywall, covering greywall, build & run, test, lint & format and project structure.

GreyhavenHQ/greywall · 749 tokens

jenkins-cli CLAUDE.md

Instructions for avivsinai/jenkins-cli, covering claude.md, build & test commands, run a single test, skip e2e tests during unit testing and e2e with colima on macos (if docker is unreachable).

avivsinai/jenkins-cli · 1,057 tokens

paseo AGENTS.md

AGENTS.md instructions for getpaseo/paseo, a project described as: Orchestrate multiple coding agents from desktop and mobile.

getpaseo/paseo · 4 tokens

jaz AGENTS.md

Instructions for gluonfield/jaz, covering engineering rules, backend architecture and integrations goal.

gluonfield/jaz · 2,035 tokens