A collection of add-ons for developing and extending AI agents. It covers capabilities such as skills, memory, issue workflows, long-running pipelines, and multi-agent coordination.

It helps add agent features, manage GitHub work, run staged pipelines, coordinate multiple agents, share canonical data, and assess or migrate agent fleets.

It provides documented workflows for organising agent development and managing larger agent systems over time.

agent-dev — Plugin for Claude Code by Abilityai/abilities

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.

Clone the repo

git clone --depth 1 https://github.com/Abilityai/abilities

Made for: Claude Code.

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/plugins/abilityai/abilities/agent-dev/github.svg)](https://agentmods.dev/plugins/abilityai/abilities/agent-dev)

Your own site

<a href="https://agentmods.dev/plugins/abilityai/abilities/agent-dev"><img src="https://agentmods.dev/badge/plugins/abilityai/abilities/agent-dev/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/abilityai/abilities/agent-dev"><img src="https://agentmods.dev/badge/plugins/abilityai/abilities/agent-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 47 skills cost 2,340 tokens a session between them.

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.

Security

Grade A, and why

agent-dev 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 3d 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.

plugins/agent-dev/.claude-plugin/plugin.json · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "agent-dev",
  "description": "Develop and extend existing agents — add skills, memory systems, GitHub Issues development workflow (backlog, roadmap, groom, claim, autoplan, commit, sprint, work-loop — standalone skills the add-backlog installer copies), cross-actor project management — GitHub-tracked or internal task files per project (project-init / project-task / project-steward / project-reconcile / project-intake / project-status — standalone skills configured by the standard's §0 block, copied by the add-project-management and add-orchestrator installers alike; both families are mirrored into the trinity-skills library for assignment on Trinity), long-running multi-stage pipelines (add-pipeline + heartbeat / status / recover / pause / resume runtime skills), system-aware orchestration (add-orchestrator — discover / compose / orchestrate a multi-agent system via Trinity's SystemManifest), a shared canonical-data layer (add-canon — a fleet canon repo with publish / consume / reconcile / doctor runtime skills and per-counterpart relations memory; add-canon-lint — deterministic consistency linting of the canon repo: two-zone schema, one-home-per-key facts, CI on every push), and fleet analysis + migration (agent-fleet-analysis — scan directories of agents in any paradigm, score fleet maturity / migration readiness, recommend a fleet architecture, map every gap to an installable marketplace skill, and emit a PDF report plus an agent-executable markdown work order; agent-fleet-migrate — execute that work order non-destructively: copy sources into a fresh workspace, extract logic per paradigm (n8n nodes / framework code / freeform prompts), delegate every fix to a named marketplace skill, verify each copy through the review gate, and report the before/after maturity delta with a gated Trinity deploy offer)",
  "version": "1.22.3",
  "author": {
    "name": "Ability.ai",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/abilityai/abi

Read the full file on GitHub · 68 lines

Contents

What it installs

The manifest is a name and a version. 47 skills travel with it, and installing the plugin installs all of them — 2,340 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

3d ago Changed 95b34a2f62ed
6d ago Changed 1541939e6a38
7d ago Changed 1374d12d527c
9d ago Changed f888c5782950
11d ago Changed 8175f4fa4b93
15d ago Changed · -3 lines 94aec0f45297
16d ago Changed · +3 lines 2e5033e32b5d
24d ago Changed 0aff43852a64
26d ago Changed f67e2beeaf2d
29d ago First seen · 68 lines scan A 23defd4b6cfd

Subscribe to this mod's changes

agent-dev is a plugin published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.

Building agents Project management

before-you-build

Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.

wshobson/agents · not measured

obw

Obsidian Workspace — project-scoped vault productivity (capture / notes / PM). Skills own folder layout and templates; /obw:pm splits a spec into blocking tickets; /issue is a Claude Mod pane that lists a view of the project's dashboard, draws Mermaid as text diagrams, and can open a card in the browser through viz.…

musingfox/cc-plugins · not measured

agent-dev

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

How it starts

What it installs

What this file has done since we first saw it

Other plugins, from other repositories

before-you-build

obw

feature-to-pr-factory

mission-control

feishu-calendar

gse