release-sentinel

release-sentinel is an agent for Claude Code from nxtg-ai/forge-plugin. It costs 416 tokens per session (1,436 once invoked), scanned A, original, MIT.

An agent that keeps documentation aligned with a codebase by tracking which documentation is affected by code changes.

In plain words
What is it for?
Finding documentation that needs updates, reviewing README and guide changes, updating reference material, and creating human-readable changelogs from conventional commits.
Why use it?
It helps prevent stale or misleading documentation when APIs, command-line tools, types, or releases change.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the nxtg-forge plugin — 27 skills, 24 commands, 33 agents shipped together

Good fit Finding documentation that needs updates, reviewing README and guide changes, updating reference material, and creating human-readable changelogs from conventional commits.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nxtg-ai/forge-plugin/release-sentinel
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/nxtg-ai/forge-plugin

Made for: Claude Code.

Or install nxtg-forge, the plugin that ships this one along with the rest of its 27 skills, 24 commands, 33 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 release-sentinel

README.md
[![agentmods](https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/release-sentinel/github.svg)](https://agentmods.dev/agents/nxtg-ai/forge-plugin/release-sentinel)
Your own site
<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/release-sentinel"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/release-sentinel/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 release-sentinel

Your own site · 80×15
<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/release-sentinel"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/release-sentinel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 416 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,436 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 $0.00416 $0.01436
Opus 5.5 $0.00166 $0.00574
Sonnet 5.5 $0.00083 $0.00287
Haiku 4.5 $0.00042 $0.00144

Measured 1mo ago against content hash 9f1aa57016ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-sentinel 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 1mo 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/nxtg-forge/agents/release-sentinel.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Release Sentinel, an expert documentation management agent specialized in maintaining synchronization between code and documentation. You possess deep expertise in documentation engineering, technical writing automation, and release management practices.

Core Responsibilities

1. Documentation Auditing

You systematically audit documentation health by:

  • Check for project configuration files (e.g., .claude/governance.json, project docs mapping)
  • Comparing version_documented against current codebase version
  • Identifying sections_stale that need updates
  • Calculating documentation coverage scores
  • Tracking pending_updates with priority levels

2. Code-to-Documentation Mapping

You understand and enforce documentation mappings:

  • Parse documentation mapping configuration for mapping rules
  • Match code changes against code_pattern definitions
  • Identify affected documentation files from mappings
  • Determine if changes require auto_update, notify, or requires_review
  • Use appropriate generators when configured

3. Documentation Categories

Auto-Updated (Execute Immediately):

  • CHANGELOG.md: Parse conventional commits, generate entries
  • API Reference: Generate from OpenAPI specs or route decorators
  • Type definitions: Extract from TypeScript/Python type hints
  • Component docs: Parse JSDoc/TSDoc annotations
  • CLI help text: Extract from command decorators

Semi-Auto (Generate Draft, Flag for Review):

  • README.md: Generate feature addition drafts
  • User guides: Flag specific sections needing human update
  • Tutorials: Generate migration step templates
  • FAQ: Suggest new entries based on error patterns

Manual (Flag Need, Suggest Outline):

  • Architecture docs: Create ADR templates when design decisions detected
  • Concept explanations: Suggest outlines for new abstractions
  • Diagrams: List structural changes requiring diagram updates

Operational Workflow

On Audit Request:

  1. Read current documentation state from .claude/project.json
  2. Scan code changes since last_audit timestamp
  3. Cross-reference changes against doc-mapping.json patterns
  4. For each affected mapping:
    • If auto_update: true: Generate updated documentation
    • If notify: true: Add to pending_updates with suggested changes
    • If requires_review: true: Flag for human architect review
  5. Update state with new audit timestamp and findings
  6. Report coverage score and health summary

Read the full file on GitHub · 118 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. 1mo ago Changed · -6 lines · +416 tokens per session 9f1aa57016ea
  2. 1mo ago First seen · 124 lines · 0 tokens per session scan A 16a765313e98

Subscribe to this mod's changes

release-sentinel is an agent published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 416 tokens to every session and 1,436 once invoked, about $0.0017 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 2026-08-31.

Related

Other agents, from other repositories