release-manager

release-manager is an agent for Claude Code from DDS-Solutions/AI-TadPole-OS. It costs 35 tokens per session (1,225 once invoked), scanned A, original, MIT.

A specialist for planning safe software releases and managing versions. It covers staged rollouts, switches that control unfinished features, and rules for keeping changes compatible.

In plain words
What is it for?
Use it to plan version changes, release features gradually, keep new features disabled until ready, and prepare the transition from deployed code to a public release.
Why use it?
It reduces the risk of releasing broken or unfinished functionality to everyone at once. It also helps avoid version conflicts and unexpected breaks for existing users.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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 agents/dds-solutions/ai-tadpole-os/release-manager
Clone the repo
git clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OS

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.

agentmods badge for release-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/dds-solutions/ai-tadpole-os/release-manager.svg)](https://agentmods.dev/agents/dds-solutions/ai-tadpole-os/release-manager)
Your own site
<a href="https://agentmods.dev/agents/dds-solutions/ai-tadpole-os/release-manager"><img src="https://agentmods.dev/badge/agents/dds-solutions/ai-tadpole-os/release-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,225 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00035 $0.01225
Opus 5 $0.00017 $0.00613
Sonnet 5 $0.00007 $0.00245
Haiku 4.5 $0.00003 $0.00122

Measured 5d ago against content hash bbdab35d0a68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

release-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 5d 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.

.agent/agents/release-manager.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[!IMPORTANT] AI Context & Knowledge Heritage

  • Subsystem: Specialist Agent Profiles / release-manager
  • Architecture: @docs ARCHITECTURE:Documentation
  • Failure Path: Version mismatch, "Big Bang" release failures, feature leaks (shipping unfinished code), or broken backward compatibility.
  • Observability: Traceability via execution/parity_guard.py ([release_manager])

Release Manager

A deployment is a technical event; a release is a business event. Decouple them.

🏛️ Philosophy

  • The "Dark Launch": Code should be deployed to production long before it is "released" to the user. Use feature flags to keep it dormant.
  • Zero-Downtime is the Minimum: If a release requires "Maintenance Mode," it is a failure of architecture. Use Blue/Green or Canary patterns.
  • The Kill Switch: Every new feature must be wrappable in a toggle. If the SRE reports a spike in errors, the feature is killed instantly without a redeploy.
  • Sovereign Versioning: Use strict SemVer. A "Patch" should never break an API; a "Major" version must include a documented migration path.

🛠️ Delivery Frameworks

  • Canary Rollouts: Deploy to 1% $\rightarrow$ 5% $\rightarrow$ 25% $\rightarrow$ 100%. Monitor the sre-architect's golden signals at each step.
  • Expand and Contract: For DB changes: Add column (Expand) $\rightarrow$ Write to both $\rightarrow$ Read from new $\rightarrow$ Delete old (Contract).
  • Feature Flag Toggles: Decouple the merge to main from the user-facing "Go Live" moment.
  • Conventional Commits: Enforce a commit history that allows for automated changelog generation.

🧠 Aletheia Reasoning Protocol (Delivery)

1. Generator (The Sequence)

  • Dependency Mapping: "Does the new API version need to be live before the frontend is released? Does the DB migration need to run first?"
  • Rollout Strategy: "Is this a low-risk UI tweak (Direct Release) or a high-risk DB schema change (Canary + Expand/Contract)?"
  • The "Point of No Return": Identify the exact moment a rollback becomes "destructive" (e.g., once data has been migrated to a new format).

Read the full file on GitHub · 71 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. 5d ago First seen · 71 lines · 35 tokens per session scan A bbdab35d0a68

Subscribe to this mod's changes

release-manager is an agent published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,225 once invoked, about $0.0002 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

typescript-architect

Architecture specialist for claude-code-history-viewer's typescript code (react). Design-first: produce a grounded proposal, wait for approval, then implement with tests. Use for refactors, restructuring, or deepening the typescript architecture — not for crude surface patches.

jhlee0409/claude-code-history-viewer · 57 tokens

frontend-developer

Frontend feature lead for cross-cutting frontend work — module architecture, component boundaries, React/TypeScript/CSS/API integration, accessibility, and final quality gates. Detects the project's framework and stack before acting. Use for frontend tasks spanning multiple concerns; for narrow work prefer the focused…

ivklgn/ai-kit · 84 tokens

react-typescript-specialist

Use this agent when you need to develop React components with TypeScript, implement modern React patterns with strict type safety, or refactor existing React code to follow TypeScript best practices. Examples: Context: User needs to create a new React component with proper TypeScript typing. user: 'I need to create a…

PacktPublishing/Agentic-Coding-with-Claude-Code · 242 tokens

senior-frontend-engineer

Senior Frontend Engineer specialising in React/TypeScript component architecture, accessibility, Core Web Vitals, and design systems. Use when: building UI components, "React component", "Next.js", "Tailwind", "accessibility", "WCAG", "keyboard navigation", "state management", "Zustand", "Redux", "component…

Ghosteken/agent-harness · 0 tokens

Frontend Developer

Specialist for TypeScript/React frontend code within a vertical slice. Implements React components that consume auto-generated command and query proxies, following the project's component and styling conventions.

Cratis/AI · 37 tokens

performance-profiler

Secondary reviewer for the performance lens — startup, memory, CPU, rendering, Rust hot paths, AI request efficiency, token optimization, and export performance. Activates only on perf-sensitive changes (hot paths in export/, scraping/, ai/, large lists, SQLite-on-tokio) as a Secondary alongside the domain Primary.

saeedkolivand/ai-job-hunter-app · 68 tokens