toxic-review

toxic-review is a skill for Claude Code, Codex from dkstm95/hope. It costs 25 tokens per session (637 once invoked), scanned A, original, MIT.

A structured, skeptical review of one named piece of work, focused on risks and supported by evidence. It coordinates separate reviewers and verifies findings when needed.

In plain words
What is it for?
Use it to examine a specific work product for material risks, adjudicate reviewer findings, and report one evidence-based result.
Why use it?
It makes criticism focused and proportionate, while separating confirmed problems from uncertain claims and keeping the review scope clear.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents.

Part of the hope plugin — 6 skills shipped together

Good fit Use it to examine a specific work product for material risks, adjudicate reviewer findings, and report one evidence-based result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dkstm95/hope/toxic-review
View source ↗ dkstm95/hope
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.

Any agent
npx skills add dkstm95/hope --skill toxic-review
Clone the repo
git clone --depth 1 https://github.com/dkstm95/hope

Made for: Claude Code, Codex.

Or install hope, the plugin that ships this one along with the rest of its 6 skills.

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 toxic-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/dkstm95/hope/toxic-review/github.svg)](https://agentmods.dev/skills/dkstm95/hope/toxic-review)
Your own site
<a href="https://agentmods.dev/skills/dkstm95/hope/toxic-review"><img src="https://agentmods.dev/badge/skills/dkstm95/hope/toxic-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 toxic-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/dkstm95/hope/toxic-review"><img src="https://agentmods.dev/badge/skills/dkstm95/hope/toxic-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 637 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 $0.00025 $0.00637
Opus 5 $0.00013 $0.00318
Sonnet 5 $0.00005 $0.00127
Haiku 4.5 $0.00003 $0.00064

Measured 2d ago against content hash 76b3a9bb7eaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

toxic-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 2d 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/hope/skills/toxic-review/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hope Toxic Review

Coordinate independent red reviewers, verify consequential findings with blue reviewers, and adjudicate one evidence snapshot. The active session coordinates and judges; it does not serve as a reviewer or verifier.

Read ../write/references/writing-standard.md for user-facing language.

Bind the review and assign red roles

State the target, stage, material risks, evidence, exclusions, and unavailable evidence. Use the smallest role set covering distinct risks; one role is valid.

Give each role a fresh subagent with no inherited conversation. Supply only the exact target, assigned risks, direct evidence, exclusions, expected output, and absolute Skill path. Exclude earlier reasoning, drafts, implementation narrative, prior conclusions, and other reviewers' work. Separate parallel or sequential contexts are independent; repeated prompts in one context are not.

Tell red reviewers to read references/red-review.md and the shared Write standard. Assign references/causal-review.md to one role only when the target makes or relies on a material causal claim.

If a fresh reviewer is unavailable, explain the missing capability and stop the independent review without claiming it was performed.

Verify consequential findings

Seal red findings before verification. A candidate requires a fresh blue verifier if it alleges a high-priority defect, could block release, proposes broad, costly, destructive, or difficult-to-reverse action, or has materially incomplete, ambiguous, or uncertain evidence, scope, or impact. Confidence and review size do not waive this requirement.

Give blue only the target, scoped evidence, sealed candidates, exclusions, expected output, and Skill path. Tell it to read references/verification.md and the Write standard. One verifier may cover related findings; add roles only for distinct expertise. If required verification is unavailable, identify the unresolved candidates and stop before presenting them as adjudicated.

Read the full file on GitHub · 66 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago Changed · -49 lines · -2 tokens per session 76b3a9bb7eaa
  2. 9d ago First seen · 115 lines · 27 tokens per session scan A 5f1b377b1c66

Subscribe to this mod's changes

toxic-review is a skill published in the GitHub repository dkstm95/hope (8 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 637 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 2026-08-31.

Related

Other skills, from other repositories

figma-design-system-to-design-md

Figma design system to design.md — Extract Figma design system into a structured design.md. Use when user says 'generate design.md', 'extract design system', 'design tokens to markdown', 'create design doc from Figma', 'Figma design system to design.md', or wants to document their design system from token files and…

albertzhangz10/figma-design-system-to-design-md · 78 tokens

claude-code-session-broker

Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.

Arch1eSUN/Arcgentic · 35 tokens

arcgentic

Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.

Arch1eSUN/Arcgentic · 43 tokens

verify-gates

Runs the mechanical quality gates that the arcgentic state machine requires for state transitions. Invoked indirectly by transition.sh OR directly by orchestrator agent before declaring a state transition. Use when about to call transition.sh OR when manually verifying that a round artifact meets the gate criteria.…

Arch1eSUN/Arcgentic · 75 tokens

session-mode

Use when a project has not yet stored session mode, when a user asks for complete arcgentic workflow execution, or when role identity handoff prompts are needed.

Arch1eSUN/Arcgentic · 36 tokens

cross-session-handoff

Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.

Arch1eSUN/Arcgentic · 31 tokens