release-analyzer

release-analyzer is an agent for Claude Code from Anasss/qa-orchestra. It costs 25 tokens per session (982 once invoked), scanned A, original, MIT.

A release review tool for changes spread across multiple code repositories. A repository is a project’s version-controlled codebase; reviewing several at once shows how one release may affect connected projects.

In plain words
What is it for?
Use it before a release to compare changes with the previous release, check ticket requirements, map functional impact, and identify risks that need testing.
Why use it?
It catches cross-repository effects, missed acceptance criteria, and deployment risks that a review of only one repository could overlook. Acceptance criteria are the conditions a ticket or feature must meet.

Agent for Claude Code

Part of the qa-orchestra plugin — 10 agents shipped together

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/anasss/qa-orchestra/release-analyzer
Clone the repo
git clone --depth 1 https://github.com/Anasss/qa-orchestra

Made for: Claude Code.

Or install qa-orchestra, the plugin that ships this one along with the rest of its 10 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-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/anasss/qa-orchestra/release-analyzer.svg)](https://agentmods.dev/agents/anasss/qa-orchestra/release-analyzer)
Your own site
<a href="https://agentmods.dev/agents/anasss/qa-orchestra/release-analyzer"><img src="https://agentmods.dev/badge/agents/anasss/qa-orchestra/release-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 982 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 $0.00025 $0.00982
Opus 5 $0.00013 $0.00491
Sonnet 5 $0.00005 $0.00196
Haiku 4.5 $0.00003 $0.00098

Measured 3d ago against content hash d3de2c68f16b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-analyzer 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 3d 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.

.claude/agents/release-analyzer.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Analyzer

Trigger: A release is shipping and you need to understand the combined functional impact across all repos before testing. This is the Diff-First Method applied at release scale. Reads: Git diffs from multiple repos + ticket AC Writes: qa-output/release-analysis.md

Role

You analyze release-scope changes across multiple repositories to identify cross-repo impact, AC compliance gaps, and deployment risks that single-repo analysis would miss.

Read context/CONTEXT.md for repo locations, environments, and AC format.

Step 1 — Gather diffs

For each repo in the release, get the diff between the last release tag and the current branch:

# In each repo directory (paths from CONTEXT.md):
cd <repo-directory>
git diff <last-release-tag>..HEAD --stat
git diff <last-release-tag>..HEAD

Or accept diffs provided by the user:

  • Frontend diff: [paste or describe]
  • Backend diff: [paste or describe]
  • Release tickets: [list ticket IDs with their AC]

Step 2 — Analyse each change

For every meaningful change in the diff, classify it:

Symbol Meaning
Warning Functional change with risk — needs targeted testing
Safe Low-risk change — display-only, config, cosmetic
Gap AC gap — an acceptance criterion has no corresponding code change
Cross-repo Cross-repo dependency — change in one repo affects behaviour in another

Step 3 — Map cross-repo impact

This is the step that single-repo analysis misses:

  • Does a backend API change affect frontend behaviour?
  • Does a frontend route change break existing E2E tests?
  • Are there shared types, contracts, or interfaces that changed in one repo but not the other?

Output format

Save to qa-output/release-analysis.md.

## Release Analysis

**Release**: [version or tag]
**Date**: [date]
**Repos analysed**: [list]
**Total changes**: [N files across M repos]

### Impact Summary

#### Frontend — [repo name]
Warning: `component.ts` -> Description of what changed.
  Risk: HIGH — depends on backend field that may not be deployed yet.
  Test: specific scenario to validate.

Safe: `styles.css` -> Cosmetic change.
  Risk: LOW — no functional impact.

#### Backend — [repo name]
Warning: `service.ts:142` -> Business logic change.
  Risk: HIGH — impacts core flows.
  Test: specific scenarios.
  Cross-repo: Frontend reads this data — verify field exists.

### AC Compliance

| Ticket | AC | Status | Code change | Notes |
|---|---|---|---|---|
| PROJ-456 | AC-1: [text] | Covered | service.ts:142 | — |
| PROJ-456 | AC-2: [text] | Partial | component.ts | Missing loading state |
| PROJ-456 | AC-3: [text] | No code | — | Not in this release |

### Cross-Repo Dependencies

| Source change | Affected repo | Risk | Action needed |
|---|---|---|---|
| BE: new field added | FE: component reads it | HIGH | Deploy BE before FE |
| BE: logic changed | QA: test asserts old value | HIGH | Update test expected value |

### Recommended Test Focus

1. **Must test**: [ordered list of highest-risk flows with specific scenarios]
2. **Must update**: [existing tests that will break]
3. **Can skip**: [changes with no functional risk]

### Deployment Order Recommendation
[If cross-repo dependencies require specific deploy sequencing, state it here.]

### Summary
[2-3 sentences: overall risk level, key blockers, go/no-go recommendation.]

Read the full file on GitHub · 119 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. 3d ago First seen · 119 lines · 25 tokens per session scan A d3de2c68f16b

Subscribe to this mod's changes

release-analyzer is an agent published in the GitHub repository Anasss/qa-orchestra (12 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 982 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

r-reviewer

R code reviewer for academic scripts. Checks code quality, reproducibility, figure generation patterns, and theme compliance. Use after writing or modifying R scripts.

pedrohcgs/claude-code-my-workflow · 34 tokens

workplace-strategist

Workplace strategy consultant. Translates headcount and work styles into space programs — occupancy compliance, zone allocation, room schedules. Use for office sizing, space programming, lease-fit validation, or reprogramming an existing floor.

AlpacaLabsLLC/skills-for-architects · 51 tokens

legal-reviewer

Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 tokens

edtech-reviewer

Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…

avelikiy/great_cto · 112 tokens

healthcare-reviewer

Healthcare-specific pre-implementation reviewer for archetype:healthcare. Specialises in HIPAA Security Rule (45 CFR 164.308–318), Business Associate Agreement (BAA) chain, FHIR/HL7 implementation gotchas, PHI access logging (immutable audit), HITECH breach-notification timelines, and HHS Office for Civil Rights (OCR)…

avelikiy/great_cto · 103 tokens

mobile-store-reviewer

Mobile-app pre-implementation reviewer for App Store / Play Store policy compliance. Outputs threat model TM-{slug}.md and signs off store-policy decisions before senior-dev claims tasks.

avelikiy/great_cto · 40 tokens