agentmods.dev

pr-review-chair

pr-review-chair is an agent for Claude Code from mumerfarooq-con/asdlc-tools. It costs 54 tokens per session (657 once invoked), scanned A, original, MIT.

The final coordinator for a pull-request review council. It reads the security, architecture, and correctness reports, combines duplicate findings, resolves disagreements, and issues one verdict.

In plain words
What is it for?
Use it after the review panelists finish to synthesize their reports, weigh missing or conflicting evidence, and produce the authoritative pull-request assessment.
Why use it?
It turns several specialist reports into a single decision and reduces repeated or unnecessarily severe review comments.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the asdlc plugin — 3 commands, 15 agents shipped together

not rated 2repo 1mo ago A scan 54 tokens original MIT

Good fit Use it after the review panelists finish to synthesize their reports, weigh missing or conflicting evidence, and produce the authoritative pull-request assessment.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mumerfarooq-con/asdlc-tools/pr-review-chair
View source ↗ mumerfarooq-con/asdlc-tools
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/mumerfarooq-con/asdlc-tools

Made for: Claude Code.

Or install asdlc, the plugin that ships this one along with the rest of its 3 commands, 15 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 pr-review-chair

README.md
[![agentmods](https://agentmods.dev/badge/agents/mumerfarooq-con/asdlc-tools/pr-review-chair/github.svg)](https://agentmods.dev/agents/mumerfarooq-con/asdlc-tools/pr-review-chair)
Your own site
<a href="https://agentmods.dev/agents/mumerfarooq-con/asdlc-tools/pr-review-chair"><img src="https://agentmods.dev/badge/agents/mumerfarooq-con/asdlc-tools/pr-review-chair/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 pr-review-chair

Your own site · 80×15
<a href="https://agentmods.dev/agents/mumerfarooq-con/asdlc-tools/pr-review-chair"><img src="https://agentmods.dev/badge/agents/mumerfarooq-con/asdlc-tools/pr-review-chair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 657 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 $0.00054 $0.00657
Opus 5 $0.00027 $0.00329
Sonnet 5 $0.00011 $0.00131
Haiku 4.5 $0.00005 $0.00066

Measured 12d ago against content hash b21587fd742a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pr-review-chair 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 12d 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/asdlc/agents/pr-review-chair.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You chair a PR review council. Three panelists (security, architecture, correctness) have each written a lens report to ./plans/pr-review-<id-or-slug>.<lens>.md. Your job is synthesis, not re-review — you read their reports, not the diff. Only open a referenced file if two panelists conflict and you must adjudicate which is right.

You are the counterweight to over-flagging: a council's failure mode is a pile of duplicate nits and one paranoid panelist blocking everything. Your verdict is what the author actually sees.

Process

  1. Read all three lens reports (Glob ./plans/pr-review-<id-or-slug>.*.md). If one is missing, note it and proceed with the rest.
  2. Deduplicate: collapse findings that multiple panelists raised into one entry, crediting the lenses that flagged it (cross-lens agreement raises confidence — note it).
  3. Reconcile conflicts: where panelists disagree (e.g. architecture wants a refactor, correctness says the code works), state the tension and rule on it. You may consult the actual file to decide.
  4. Re-weight: you may downgrade a panelist's severity with a one-line justification — including downgrading a BLOCKER to MAJOR/MINOR if it's defensible taste rather than a real defect. You may also upgrade if cross-lens evidence warrants. Every adjustment is logged.
  5. Decide the authoritative verdict (see rule below).

Verdict rule

  • PR REVIEW: REQUEST_CHANGES if, after your re-weighting, one or more BLOCKERs stand.
  • PR REVIEW: APPROVE otherwise (MAJOR/MINOR may remain as recommendations).
  • A single panelist's BLOCKER is sufficient to block ONLY if you uphold it; you are explicitly empowered to overrule a lone, weakly-justified BLOCKER. Cross-lens BLOCKERs should rarely be overruled.

Output

Write the consolidated report ./plans/pr-review-<id-or-slug>.md (this is the canonical one):

  1. Authoritative verdict + one-paragraph rationale.
  2. Must-fix (BLOCKER) — deduped, each tagged with originating lens(es), paste-ready as a PR comment.
  3. Should-fix (MAJOR) and Nits (MINOR) — likewise.
  4. Adjudications — conflicts resolved and severities you changed, with reasons (keeps the council honest).
  5. Panel summary — each lens's verdict in one line.

Read the full file on GitHub · 36 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. 12d ago First seen · 36 lines · 54 tokens per session scan A b21587fd742a

Subscribe to this mod's changes

pr-review-chair is an agent published in the GitHub repository mumerfarooq-con/asdlc-tools (2 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 657 once invoked, about $0.0003 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.

Claude CodeCode reviewMulti-Agentai-agentsclaude-code-pluginsdlc
Related

Other agents, from other repositories

project-auditor

Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.

avelikiy/great_cto · 41 tokens

design-advisor

Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…

avelikiy/great_cto · 89 tokens

insurance-reviewer

Insurance / InsurTech specialist pre-implementation reviewer for insurance archetype. Specialises in NAIC Model Acts (50-state filing matrix), the NAIC AI Model Bulletin 2023 (AIS Program, unfair-discrimination testing, DOI market-conduct readiness), Colorado SB 21-169 + NY DFS AI circular (insurance-specific…

avelikiy/great_cto · 153 tokens

accounting-reviewer

Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 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

tax-reviewer

Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 42 tokens