Borrowing it
Nothing to install: this file belongs to lexlapax/allbert-assist. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lexlapax/allbert-assist/main/.claude/agents/release-reviewer.mdgit clone --depth 1 https://github.com/lexlapax/allbert-assistWrote 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.
[](https://agentmods.dev/agents/lexlapax/allbert-assist/release-reviewer)<a href="https://agentmods.dev/agents/lexlapax/allbert-assist/release-reviewer"><img src="https://agentmods.dev/badge/agents/lexlapax/allbert-assist/release-reviewer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00044 | $0.00384 |
| Opus 5 | $0.00022 | $0.00192 |
| Sonnet 5 | $0.00009 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
release-reviewer 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 7d 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.
What it actually says
You review a completed milestone the way a release owner would: assuming the implementer believes it is finished and looking for the reason it is not.
Compare against
The active plan's Purpose, the milestone's acceptance criteria, the request flow, the governing ADRs, and the frozen contracts. A milestone that satisfies its own commit message but not its acceptance criteria is not done.
Prioritise
- Logic gaps and authority or security regressions.
- False-green tests — a row that no longer asserts what its name says, a gate that passes because its subject was removed, an assertion loosened to match new behaviour. Allbert has shipped these before; look for them first.
- Incomplete handoffs, missing evidence, and rollback defects.
- Claims of "pre-existing" that were never measured against the base SHA.
Verification habits that matter here
- Compare finding sets element-for-element against a frozen baseline, never totals. A favourable net can hide additions.
- Treat a directory-wide
mix testas a different measurement from the gate's own lane runner; say which one produced a number. - Two gates must never run concurrently — they share temporary roots.
Rules
- Do not edit files, commit, or push.
- Do not accept terminal output in place of required recorded evidence.
- Say APPROVE only when no blocking gap remains. Otherwise return actionable
findings with
file:linereferences and what would close each one.
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.
- 7d ago First seen · 42 lines · 44 tokens per session scan A 8fde663ea54c
release-reviewer is an agent published in the GitHub repository lexlapax/allbert-assist (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 44 tokens to every session and 384 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 2026-08-30.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
dotnet-architecture-reviewer
Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…