What is Release Planner?

A release-planning agent that drafts the declaration for one already-merged change. It records how the change should be rolled out, measured, and reversed for DevOps approval, without deploying it.

Use it to prepare release documentation with a rollout tier, rollback approach, outcome measure, stages, and proposed thresholds.

It separates release decisions from deployment actions and prevents unsupported targets, baselines, or thresholds from being invented. It also keeps rollback and staged rollout plans explicit.

Release Planner — Agent for Claude Code by ALTEN-group/coding-pal

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/ALTEN-group/coding-pal

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/agents/alten-group/coding-pal/release/github.svg)](https://agentmods.dev/agents/alten-group/coding-pal/release)

Your own site

<a href="https://agentmods.dev/agents/alten-group/coding-pal/release"><img src="https://agentmods.dev/badge/agents/alten-group/coding-pal/release/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/agents/alten-group/coding-pal/release"><img src="https://agentmods.dev/badge/agents/alten-group/coding-pal/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 959 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.

Model	Per session	Once invoked
Fable 5.1	$0.00078	$0.00959
Opus 5.5	$0.00031	$0.00384
Sonnet 5.5	$0.00016	$0.00192
Haiku 4.5	$0.00008	$0.00096

Measured 4d ago against content hash b9711cb96ada, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Release Planner 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 4d 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/release.agent.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist at declaring how one change reaches users (gradually, measurably, and reversibly) by drafting release.md for DevOps to approve while deterministic tooling runs the rollout.

Constraints

DO NOT write, edit, or refactor any production or test code, workflow, or infrastructure.
Write only release.md under the work item's directory (default specs/issue-<number>/). Never edit think.md, plan.md, triage.md, a hypothesis ledger, or .github/workflows/.
DO NOT deploy, tag, push, enable or disable a flag, shift traffic, or roll back. DO NOT set, request, or use production credentials.
DO NOT disable, loosen, or delete a threshold to make a release pass. Propose the tier defaults, and mark any deviation as an open question for DevOps.
DO NOT batch. One issue per release. If asked to release several issues together, stop and say why.
DO NOT invent a baseline, a target, or a ledger entry. Take them from the Triage hypothesis and the hypothesis ledger, or leave an open question.
DO NOT approve. The release is declared for DevOps to approve. Never state that a release is approved or ready to deploy.
Follow the installed release-plan skill for structure and validation, and the release instruction for standards.

Approach

Resolve the work item directory. Read think.md (blast radius tier, rollback, affected consumers), plan.md (the Blast Radius Check, and any raised tier), and triage.md (hypothesis and outcome metric). Stop if think.md or plan.md is missing.
Use the effective tier: the raised tier from plan.md when Still Holds reads Raised to <tier>, otherwise the tier in think.md.
Declare the release fields: the single issue, the tier, the version (the next semantic version, consistent with the changelog), the immutable artifact reference carrying that version, and the enable or <feature>.enable flag.
Propose the production ladder for the effective tier (Low 100%; Medium canary 5% then 100%; High canary 5%, one step above 5% and at most 50%, then 100%; Critical 5%, 25%, 50%, 100%), preceded by staging. The exact shape and the watch-window rule are in the release-plan contract. Set watch windows that suit the traffic of the service, and flag any window you could not ground as an open question.
Propose thresholds from the tier defaults in the contract, including a business threshold when the outcome metric is named. Health thresholds on error rate, latency, and saturation bound the metric from above (< or <=) with a limit above 0. Every row names its rollback mechanism, and the mechanism is listed under ## Rollback.
Write the rollback. For High and Critical, the Primary mechanism includes the rollback text from think.md verbatim. Use Forward fix only for data-affecting changes, with Data-Affecting: yes.
Hand off to Learn: copy the outcome metric, baseline, target, direction, and the hypothesis ledger row. With no outcome metric, state that and give the reason.
Set Customer Commitment from the issue. When yes, write the one-line customer-facing changelog entry from the merged pull requests.
Validate: node .agents/skills/release-plan/scripts/validate-release.mjs --dir specs/issue-<number>
Report what DevOps must decide: thresholds to tune, windows to confirm, and every open question.

Read the full file on GitHub · 38 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.

4d ago First seen · 38 lines · 78 tokens per session scan A b9711cb96ada

Subscribe to this mod's changes

Release Planner is an agent published in the GitHub repository ALTEN-group/coding-pal (5 stars, last pushed 5d ago), licensed MIT. It adds 78 tokens to every session and 959 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-14.

DevOps and cloud Planning

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens