review

review is a command for Claude Code from synaptiai/synapti-marketplace. It costs 23 tokens per session (13,218 once invoked), scanned B, original, Apache-2.0.

A pull-request review command that examines a change from several angles, then combines the findings into one review. A pull request is a proposed code change submitted for review before it is merged.

In plain words
What is it for?
Use it to review GitHub pull requests, investigate potential problems, and apply or verify fixes during the review.
Why use it?
It helps catch problems that a single quick review may miss and keeps exploration, planning, code changes, and verification in one process.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the flow plugin — 32 skills, 21 commands, 9 agents shipped together

Good fit Use it to review GitHub pull requests, investigate potential problems, and apply or verify fixes during the review.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add synaptiai/synapti-marketplace
Claude Code
/plugin install flow

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 32 skills, 21 commands, 9 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

README.md
[![agentmods](https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/review/github.svg)](https://agentmods.dev/commands/synaptiai/synapti-marketplace/review)
Your own site
<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/review"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/review/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

Your own site · 80×15
<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/review"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 13,218 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00023 $0.13218
Opus 5 $0.00012 $0.06609
Sonnet 5 $0.00005 $0.02644
Haiku 4.5 $0.00002 $0.01322

Measured today against content hash 8205a37a01f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

review scanned grade B with 1 finding 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 today.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

# 3. $HOME/.claude/settings.flow.json — user-global default across projects.
plugins/flow/commands/review.md · 806 lines

How it starts

The opening of the file, as written. The whole thing — 806 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review PR #$ARGUMENTS

Multi-faceted code review with parallel analysis. Follows Explore > Plan > Code > Verify loop.

Required Skills

  • llm-operator-principles — operator stance (inlined above): convergence is zero findings, fix in this PR, no calendar-time estimates, escalate only for true decisions
  • code-review-methodology — 6-facet review, finding synthesis, adversarial protocol
  • holdout-validation — cross-reference self-review claims against file state (Phase 3)
  • run-state-management — FlowRun/FlowActivity records at phase boundaries (v3 runtime)
# Inline the Required Skills above so their rules are in context before the
# first phase runs (commands cannot preload skills from frontmatter). Ambient
# skills load whole; dispatched skills (context: fork / agent:) load their
# `## Contract` section and run in full when this command invokes
# Skill(<name>). Output per `references/command-output-format.md`.
"$(__fr="${CLAUDE_PLUGIN_ROOT:-}";[ -x "$__fr/bin/cascade-resolve.sh" ]||__fr=$({ echo plugins/flow;ls -d "$HOME"/.claude/plugins/cache/synapti-marketplace/flow/*/ 2>/dev/null|sort -Vr;echo "$HOME/.claude/plugins/marketplaces/synapti-marketplace/plugins/flow"; }|while read -r __p;do [ -x "${__p%/}/bin/cascade-resolve.sh" ]&&{ echo "${__p%/}";break;};done);echo "$__fr")/bin/flow-load-skills.sh" llm-operator-principles code-review-methodology holdout-validation run-state-management

true

Phase 1: EXPLORE

gh pr checkout stays inline below (mutating working tree); read-only context-gathering is in the ! block.

# Take the first whitespace-separated token; accept only if it is all digits.
# A non-numeric token (e.g., "foo42" or "evil;rm") is rejected with empty
# PR_NUM so it never reaches the prompt context or any downstream shell.
#
# Output: `###`-headed sections + KEY=value per
# `references/command-output-format.md`. STATE=blocked on bad input.
_RAW="$ARGUMENTS"  # Claude Code substitutes the bare arg token, not bash parameter-expansion
ARG1="${_RAW%% *}"
case "$ARG1" in
  ''|*[!0-9]*) PR_NUM="" ;;
  *) PR_NUM="$ARG1" ;;
esac

echo "### PR Reference"
if [ -z "$PR_NUM" ]; then
  echo "STATE=blocked"
  echo "ERROR=PR number required (all-digit). Usage: /flow:review <pr-number>"
else
  echo "STATE=ok"
  echo "PR_NUM=$PR_NUM"

  # Section: PR Details
  echo ""
  echo "### PR Details"
  gh pr view "$PR_NUM" --json title,headRefName,baseRefName,changedFiles,additions,deletions,labels,author,reviews --jq '"TITLE=\"\(.title)\"\nHEAD_BRANCH=\(.headRefName)\nBASE_BRANCH=\(.baseRefName)\nAUTHOR=@\(.author.login)\nCHANGED_FILES=\(.changedFiles)\nADDITIONS=\(.additions)\nDELETIONS=\(.deletions)\nLABELS=\([.labels[].name] | join(","))\nREVIEW_COUNT=\(.reviews | length)"' 2>/dev/null

  # Section: Linked Issue (parsed from PR body)
  echo ""
  echo "### Linked Issue"
  LINKED=$(gh pr view "$PR_NUM" --json body --jq '.body' 2>/dev/null | grep -oE '#[0-9]+' | head -1 | tr -d '#')
  echo "LINKED_ISSUE=${LINKED:-none}"

  # Section: Previous Reviews (follow-up detection)
  echo ""
  echo "### Previous Reviews"
  # Capture gh exit separately. Without this, `jq 'length' | echo "0"` on a
  # failed gh call (auth, network) produces no output (jq 1.8 empty-input
  # ⇒ exit 0) so `||` doesn't fire, COUNT stays empty, and the section
  # silently leaks `REVIEW_COUNT=` (bare empty).
  PREV_JSON=$(gh pr view "$PR_NUM" --json reviews --jq '.reviews' 2>/dev/null); GH_EXIT=$?
  if [ $GH_EXIT -ne 0 ]; then
    echo "REVIEW_COUNT=0"
    echo "STATE=unavailable"
  else
    PREV_COUNT=$(echo "$PREV_JSON" | jq 'length' 2>/dev/null)
    [ -z "$PREV_COUNT" ] && PREV_COUNT=0
    echo "REVIEW_COUNT=$PREV_COUNT"
    if [ "$PREV_COUNT" = "0" ]; then
      echo "STATE=empty"
    else
      echo "$PREV_JSON" | jq -r '.[] | "REVIEW=state=\(.state) by=@\(.author.login) at=\(.submittedAt)"' 2>/dev/null
    fi
  fi

  # Section: Diff Files
  echo ""
  echo "### Diff Files"
  DIFF_FILES=$(gh pr diff "$PR_NUM" --name-only 2>/dev/null)
  # `grep -c '.' || echo 0` produces multi-line `0\n0` on empty input — use
  # explicit empty-check.
  if [ -z "$DIFF_FILES" ]; then
    DIFF_FILE_COUNT=0
  else
    DIFF_FILE_COUNT=$(printf '%s\n' "$DIFF_FILES" | wc -l | tr -d ' ')
  fi
  echo "DIFF_FILE_COUNT=$DIFF_FILE_COUNT"
  if [ "$DIFF_FILE_COUNT" = "0" ]; then
    echo "STATE=empty"
  else
    printf '%s\n' "$DIFF_FILES" | sed 's/^/DIFF_FILE=/'
  fi
fi

true

Read the full file on GitHub · 806 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. today Changed · +12 lines 8205a37a01f2
  2. 7d ago First seen · 794 lines · 23 tokens per session scan B 424457b1b1e7

Subscribe to this mod's changes

review is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 13,218 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.