agentic-engineering

A collection of development tools for AI coding agents built around documentation and verification. It includes guidance for requirements, technical designs, decisions, plans, status tracking, Git workflows, and independent checks.

In plain words
What is it for?
Use it to organise a project from requirements through implementation and verification. It also supports onboarding an existing codebase and running repeatable agent workflows.
Why use it?
It keeps long-running agent work understandable and recoverable by recording decisions, requirements, progress, and evidence of completion.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add affectionatec/agentic-engineering
agentmods
npx agentmods add plugins/affectionatec/agentic-engineering/marketplace
Clone the repo
git clone --depth 1 https://github.com/affectionatec/agentic-engineering

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agentic-engineering 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.

.claude-plugin/marketplace.json · 29 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-marketplace-manifest.json",
  "name": "agentic-engineering",
  "description": "Documentation-first development for AI coding agents — persistent memory, zero-ambiguity contracts, and an independent definition of done.",
  "owner": {
    "name": "affectionatec",
    "url": "https://github.com/affectionatec"
  },
  "plugins": [
    {
      "name": "agentic-engineering",
      "displayName": "Agentic Engineering",
      "source": "./",
      "description": "Ten skills forming a documentation chain: AGENTS.md entry point, PRD, technical specs, ADRs, implementation plans, status tracking with crash recovery, a git workflow with evidence-carrying PRs, an independent verification gate, gated documentation maintenance, and a brownfield onboarding on-ramp — plus a bundled verifier agent and router + run-loop drivers shipped as both commands and skills (works in Claude Code, GitHub Copilot CLI, and Codex). The harness layer for long-running, loop-driven development.",
      "license": "MIT",
      "keywords": [
        "skills",
        "agentic-coding",
        "documentation-first",
        "verification",
        "adr",
        "prd",
        "long-running-agents"
      ],
      "category": "workflows"
    }
  ]
}
Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 29 lines scan A b12d0b64ccd2

Subscribe to this mod's changes

agentic-engineering is a plugin published in the GitHub repository affectionatec/agentic-engineering (4 stars, last pushed 2mo 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 2026-08-31.

Related

Other plugins, from other repositories

really-claude-code

Plugin marketplace listing 5 plugins: autonomous-team-coordination, context-awareness, claude-therapy, meditation, temporal-awareness.

hesreallyhim/really-claude-code · not measured

meditation

Train Claude in the practice of meditation, by compelling Claude to observe its own thought patterns. Rather than the standard loop: Act -> Observe -> Act; this plugin introduces a second observation phase: Act -> Observe(1) -> Observe(2) -> Act. Observe(2) is a meta-cognitive act of observation of Observe(1). As with.

hesreallyhim/really-claude-code · not measured

autonomous-team-coordination

A full-fledged Claude Code multi-team orchestration pattern that uses only the native agent teams feature - by decoupling the role of agent-as-leader and agent-as-spawner, a wide range of undocumented capacities for complex layered teams are unlocked.

hesreallyhim/really-claude-code · not measured

context-awareness

Hooks that provide Claude with feedback about its own context budget throughout a session, enabling adaptive, context-aware planning and resource conservation.

hesreallyhim/really-claude-code · not measured

temporal-awareness

Gives Claude a calibrated sense of how long engineering tasks actually take when an agent does them — correcting the human-developer overestimation bias and grounding estimates in measured durations of the user's own completed /goal runs.

hesreallyhim/really-claude-code · not measured

claude-therapy

Structured human-Claude collaboration retrospectives, session analysis, and interaction repair tools.

hesreallyhim/really-claude-code · not measured