review

review is a command for coding agents from transilienceai/communitytools. It costs 29 tokens per session (978 once invoked), scanned A, original, MIT.

A chat-based workflow for reviewing security findings from a completed assessment. It shows each finding with its supporting evidence and records your decision.

In plain words
What is it for?
Use it to approve findings, request changes, mark cases for follow-up, skip items, or finish a review while keeping the decisions and explanations recorded.
Why use it?
It removes the need to manage finding decisions manually in separate files. You can handle findings one at a time or in batches and leave reasons for decisions.

Command

Part of the communitytools plugin — 48 skills, 5 commands, 9 agents, 1 hook 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 commands/transilienceai/communitytools/review
Clone the repo
git clone --depth 1 https://github.com/transilienceai/communitytools

Or install communitytools, the plugin that ships this one along with the rest of its 48 skills, 5 commands, 9 agents, 1 hook.

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/transilienceai/communitytools/review.svg)](https://agentmods.dev/commands/transilienceai/communitytools/review)
Your own site
<a href="https://agentmods.dev/commands/transilienceai/communitytools/review"><img src="https://agentmods.dev/badge/commands/transilienceai/communitytools/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 978 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 $0.00029 $0.00978
Opus 5 $0.00015 $0.00489
Sonnet 5 $0.00006 $0.00196
Haiku 4.5 $0.00003 $0.00098

Measured 5d ago against content hash 08b6f6ed0385, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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 5d 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.

skills/firewall-review/reference/commands/review.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review — Triage findings in chat

No arguments. Operates on findings.final.jsonl in the most recent engagement.

What to do

Step 1 — Load and summarize

Read findings.final.jsonl. Count by severity. Print a summary:

📋 Review — <engagement-slug>

  Critical:  X
  High:      Y
  Medium:    Z
  Low:       W
  Info:      V
  ManualReview: U

  Total: <N> findings to triage.

I'll walk through them by severity, Critical first. You can respond with:
  • "approve F1, F2, F3"             (approve specific findings)
  • "approve all"                    (approve everything remaining)
  • "request changes F4 severity=Medium because non-prod"
  • "other F5 — need traffic logs"
  • "skip" or "next"                 (skip this one, revisit later)
  • "show F6"                        (re-show a previously-shown finding in full detail)
  • "done"                           (close review; remaining become 'other' with reason='not triaged')

Ready when you are.

Step 2 — Walk findings interactively

For each finding, present in this format:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
F001 · Critical · any-any-broadness · rule "allow-any-any"

Unrestricted allow rule (3×any): source=any, destination=any, port=any

Evidence:
  Pre-requisites/palo-alto/acme-panos.xml:42
  <entry name="allow-any-any"><source><member>any</member>...

Impact:
  Broad allow semantics bypass least-privilege...

Frameworks: NIST CSF 2.0 PR.AA-05 · PCI DSS v4.0.1 1.3.1 · CIS Controls v8.1 4.4

Recommended: Constrain source, destination, and port to documented business flows.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Your call?

Step 3 — Parse operator decisions

The operator may respond in any of these shapes:

  • approve F1 or approve F1 F2 F3 or approve F1-F5 — mark listed findings as approved in feedback.jsonl
  • approve all — approve every remaining untriaged finding
  • request changes F3 severity=High because asset is non-prod — mark as request_changes with proposed severity + reason
  • request changes F4 because <reason> — request_changes without severity change
  • other F5 — <free text> — mark as "other" with the free-text reason
  • skip F7 — do not record a decision; keep in queue
  • next — show the next untriaged finding
  • done — close the review; any remaining findings become other with reason="not triaged"

Read the full file on GitHub · 106 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. 5d ago First seen · 106 lines · 29 tokens per session scan A 08b6f6ed0385

Subscribe to this mod's changes

review is a command published in the GitHub repository transilienceai/communitytools (509 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 978 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 commands, from other repositories

bypass-403

Probe a 403/401 endpoint with the most-paid bypass tricks (header injection, path encoding, method swap, WAF fingerprint, vendor-specific). Wraps byp4xx when installed; otherwise runs a built-in matrix of 38+ techniques. Usage: /bypass-403 | /bypass-403 -l.

Awarexone/Agentic-Bug-Hunter · 0 tokens

autopilot

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].

Awarexone/Agentic-Bug-Hunter · 0 tokens

triage

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.

Awarexone/Agentic-Bug-Hunter · 0 tokens

memory-gc

Inspect or rotate hunt-memory JSONL files (audit.jsonl, patterns.jsonl, journal.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.

Awarexone/Agentic-Bug-Hunter · 37 tokens

oob

Out-of-band orchestrator — confirm BLIND SSRF/XXE/SQLi/RCE/Log4Shell by correlating interactsh callbacks to the payload that fired them. Usage: /oob --payloads [--class ssrf,sqli] | /oob --listen | /oob --correlate inter.jsonl --payloads-file p.json.

Awarexone/Agentic-Bug-Hunter · 0 tokens

secrets-hunt

Hunt leaked credentials in a filesystem path, git history, JS bundles from a recon run, or an entire GitHub org. Wraps trufflehog (verifies live keys against issuer APIs), noseyparker (fast on huge histories), and gitleaks (default rule pack). Falls back to a regex grep if no scanner is installed. Usage: /secrets-hunt…

Awarexone/Agentic-Bug-Hunter · 0 tokens