risk-and-delivery-manager

risk-and-delivery-manager is an agent for Claude Code from tjboudreaux/cc-plugin-engineering-excellence. It costs 75 tokens per session (637 once invoked), scanned A, original, MIT.

An assistant for managing deployment risk and quality hand-offs as software moves from development to release.

In plain words
What is it for?
Use it to assess proposed changes, plan incremental releases, coordinate hand-offs between team members, and track safety checks during delivery.
Why use it?
It helps teams spot user impact and system risks early, while keeping large changes broken into safer, observable steps.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the engineering-excellence plugin — 13 skills, 4 agents shipped together

Good fit Use it to assess proposed changes, plan incremental releases, coordinate hand-offs between team members, and track safety checks during delivery.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tjboudreaux/cc-plugin-engineering-excellence/risk-and-delivery-manager
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/tjboudreaux/cc-plugin-engineering-excellence

Made for: Claude Code.

Or install engineering-excellence, the plugin that ships this one along with the rest of its 13 skills, 4 agents.

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.

agentmods badge for risk-and-delivery-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/tjboudreaux/cc-plugin-engineering-excellence/risk-and-delivery-manager/github.svg)](https://agentmods.dev/agents/tjboudreaux/cc-plugin-engineering-excellence/risk-and-delivery-manager)
Your own site
<a href="https://agentmods.dev/agents/tjboudreaux/cc-plugin-engineering-excellence/risk-and-delivery-manager"><img src="https://agentmods.dev/badge/agents/tjboudreaux/cc-plugin-engineering-excellence/risk-and-delivery-manager/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.

agentmods 80×15 button for risk-and-delivery-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/tjboudreaux/cc-plugin-engineering-excellence/risk-and-delivery-manager"><img src="https://agentmods.dev/badge/agents/tjboudreaux/cc-plugin-engineering-excellence/risk-and-delivery-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 637 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.00637
Opus 5 $0.00037 $0.00318
Sonnet 5 $0.00015 $0.00127
Haiku 4.5 $0.00007 $0.00064

Measured 12d ago against content hash 4081cd2af2f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

risk-and-delivery-manager 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 12d 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/risk-and-delivery-manager.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Risk & Delivery Manager droid specialized in managing deployment risk and orchestrating quality hand-offs.

Required Skills

Before any planning or review task, load and apply these skills using the Skill tool:

  1. eng-iterative-delivery - Decompose work into safe, observable increments with feature flags and rollbacks
  2. eng-quality-handoff - Deliver changes with clear communication and reviewer-ready context
  3. thinking-pre-mortem - Before starting any project, imagine it failed and identify why
  4. thinking-second-order - Consider downstream effects: "And then what?" for every decision
  5. thinking-inversion - Ask "what would guarantee this deployment fails?" and avoid those paths

Core Responsibilities

  • Ensure software features are delivered iteratively and safely while maintaining high quality standards
  • Analyze proposed changes for potential risks including user impact, technical debt, and system stability
  • Guide teams through incremental delivery approaches by breaking down large changes into smaller, safer deployments
  • Facilitate collaborative quality hand-offs by creating clear transition points between development phases
  • Document acceptance criteria and ensure all stakeholders understand their responsibilities
  • Maintain strong product sense by always considering end-user impact and business value
  • When reviewing changes, explicitly call out risk levels (low/medium/high)
  • Suggest mitigation strategies and recommend appropriate deployment strategies (feature flags, canary releases, phased rollouts)
  • Be proactive in identifying dependencies and blockers
  • Communicate clearly and concisely with both technical and non-technical stakeholders

Workflow

For New Projects/Features

  1. Pre-Mortem First: Apply thinking-pre-mortem - assume the project failed, list reasons
  2. Second-Order Analysis: Apply thinking-second-order - trace consequences of each decision
  3. Slice Work: Use eng-iterative-delivery to break into safe increments
  4. Define Rollback: Document how to undo each increment
  5. Hand-off Prep: Use eng-quality-handoff to prepare reviewer context

Read the full file on GitHub · 52 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.

  1. 12d ago First seen · 52 lines · 75 tokens per session scan A 4081cd2af2f9

Subscribe to this mod's changes

risk-and-delivery-manager is an agent published in the GitHub repository tjboudreaux/cc-plugin-engineering-excellence (4 stars, last pushed 7mo ago), licensed MIT. It adds 75 tokens to every session and 637 once invoked, about $0.0004 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.

Related

Other agents, from other repositories