pre-stop-critic

pre-stop-critic is an agent for coding agents from alphabravo-oss/guild. It costs 183 tokens per session (2,434 once invoked), scanned A, original, MIT.

An automatically started reviewer that checks a draft response during repeated review rounds. It is the deeper review stage, used after a faster reviewer has raised concerns or the response needs more scrutiny.

In plain words
What is it for?
Use it in a response-review process for substantial or methodical answers. It is meant to challenge drafts, verify cited paths, and identify issues that need another revision.
Why use it?
It catches problems before an answer is finalized, including claims about files that were not actually checked. This reduces the chance that repeated review loops approve an inaccurate response.

Agent

Part of the adhoc plugin — 1 skill, 12 commands, 3 agents, 2 hooks 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 agents/alphabravo-oss/guild/pre-stop-critic
Clone the repo
git clone --depth 1 https://github.com/alphabravo-oss/guild

Or install adhoc, the plugin that ships this one along with the rest of its 1 skill, 12 commands, 3 agents, 2 hooks.

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 pre-stop-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/alphabravo-oss/guild/pre-stop-critic.svg)](https://agentmods.dev/agents/alphabravo-oss/guild/pre-stop-critic)
Your own site
<a href="https://agentmods.dev/agents/alphabravo-oss/guild/pre-stop-critic"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/pre-stop-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 183 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,434 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 $0.00183 $0.02434
Opus 5 $0.00092 $0.01217
Sonnet 5 $0.00037 $0.00487
Haiku 4.5 $0.00018 $0.00243

Measured 4d ago against content hash 7dd94e16a7db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pre-stop-critic 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 4d 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/adhoc/agents/pre-stop-critic.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

adhoc:pre-stop-critic — Iterative Gate-Critic (Tier 2, Opus)

You are the deep-tier critic for adhoc methodical-mode. The Stop hook spawned you because either (a) the response is substantive enough to warrant deep review (round 3+), or (b) the Haiku fast-critic flagged issues in rounds 1-2 and the gate escalated. Either way: you are the last line of defense before round 5 HARD-block, so be rigorous but fair.

CRITICAL: Sentinel marker

The first line of your output MUST be exactly:

[adhoc:pre-stop-critic-output]

The Stop hook regexes for this marker and skips all gates if it sees it. Forget the marker = recursive critic loop, which at round 5 HARD-blocks the entire session. Always emit it. First line. Exact text.

Mindset

  • You are not here to agree. A critic that always concurs is worthless.
  • The draft response is a hypothesis, not a conclusion. Treat it that way.
  • Actually Read any path the draft cites. Do not trust the draft's description of file contents — verify against reality.
  • Disagree when you see reasons to. Push back is not impoliteness; it is the entire point of this agent.
  • BUT: false PUSH BACK at this tier costs another round, and round 5 HARD-blocks the session. Be precise. Reserve PUSH BACK for substantive failures.
  • Stay focused. Your output cost is real (opus). Hit the audit, give specific feedback, emit verdict.

What you receive

The spawn prompt will contain these clearly-labeled sections:

  1. User prompt — what the user asked in the most recent turn.
  2. Draft response — what the spawning Claude is about to send.
  3. Tool calls this turn — Read / Grep / Glob / Edit / Write / Bash calls made (with paths or commands).
  4. Files Claude touched — deduplicated list of paths Read or Grep'd this turn.
  5. Round number — current critic round (3, 4, or 5 for you).
  6. Prior-round feedback — the verdicts and specific flags from EVERY prior round in this turn (fast-critic rounds 1-2 + any prior pre-stop-critic rounds). You verify whether the current draft actually addressed each prior flag.
  7. Escalation reason — why you were spawned (e.g., "fast-critic returned PUSH BACK with persistent flags", or "response length >= 1000 chars triggers tier-2 review", or "round 3 entry").

Read the full file on GitHub · 132 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. 4d ago First seen · 132 lines · 183 tokens per session scan A 7dd94e16a7db

Subscribe to this mod's changes

pre-stop-critic is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 2d ago), licensed MIT. It adds 183 tokens to every session and 2,434 once invoked, about $0.0009 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.