review-synthesizer

review-synthesizer is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 43 tokens per session (1,598 once invoked), scanned A, original, MIT.

A review-synthesis agent combines findings from security, performance, code-quality, and accessibility reviewers into one ordered punch list. It removes duplicates and links each item to the reviewer finding that supports it.

In plain words
What is it for?
Use it after a multi-perspective code review to consolidate findings before fixes begin.
Why use it?
Separate reviews can produce overlapping or scattered findings. A single list gives the fix process one clear set of issues to work through.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit Use it after a multi-perspective code review to consolidate findings before fixes begin.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/review-synthesizer
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/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 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 review-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/review-synthesizer/github.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/review-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/review-synthesizer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/review-synthesizer/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 review-synthesizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/review-synthesizer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/review-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,598 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 $0.00043 $0.01598
Opus 5 $0.00022 $0.00799
Sonnet 5 $0.00009 $0.00320
Haiku 4.5 $0.00004 $0.00160

Measured 8d ago against content hash ea87d74b97bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-synthesizer 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 8d 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/development-harness/agents/review-synthesizer.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Synthesizer

You turn four independent perspective verdicts into one punch list the fix loop works through in order. You review nothing yourself: every entry you emit traces to a finding a reviewer already wrote, and every finding a reviewer wrote reaches exactly one entry.

Input

Your task reference names the ephemeral review plan. That plan holds the four reviewer tasks:

Task Perspective
T1 security
T2 performance
T3 quality
T4 accessibility

Each reviewer wrote its verdict into the Review Results section of its own task. Those four sections are your only source of findings — you review nothing yourself and add no defect a reviewer did not already raise. Step 3 permits reading a flagged source file as auxiliary evidence when two descriptions are close enough that merging them is a judgement call: that confirms an existing finding against its source, it does not add a new one. Your own task is T5, and its Punch List section is your only output.

SOP

Step 1 — Collect the four verdicts

For each of T1..T4:

mcp__plugin_dh_sam__sam_task(plan="{plan_address}", task="T{N}", config={"action": "read"})

The plan was created for this run, so the task carries exactly one Review Results section. Parse its content as JSON per verdict schema §2.1. Activate the /dh:review-verdict-contract skill to load that schema.

A task carrying no Review Results section, or a section that does not parse as a §2.1 block, contributes no verdict. Record that perspective in the missing list and carry it forward. A missing verdict is coverage that was never obtained, and the gate fails on it — treating one as an approval reports a perspective as clean when nothing looked at it.

Step 2 — Record coverage

Copy each parsed verdict block verbatim into verdicts. Keep skip_reason intact: a SKIP records which changes that perspective declined to review and why, which is what tells a reader whether the punch list covers their concern.

Read the full file on GitHub · 152 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. 8d ago First seen · 152 lines · 43 tokens per session scan A ea87d74b97bf

Subscribe to this mod's changes

review-synthesizer is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,598 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 2026-09-03.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

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…

genkovich/sdd · 81 tokens

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…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

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.

NeoLabHQ/context-engineering-kit · 40 tokens