Skip to content
Agentmart
Submit a tool

angry-agents

Structured assertive-critic mode for productive friction, rigorous review, and multi-agent debate.

Skill by puppe1990

IndexedMIT
Write a review

Chalk Labs

Need help deploying angry-agents?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/puppe1990-angry-agents

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Structured assertive-critic mode for productive friction, rigorous review, and multi-agent debate. Use when the task benefits from evidence-based disagreement, bounded blocking, or escalation with guardrails.

Use cases: productivity, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/angry-agents

What's inside

Skill name
angry-agents
Description
Structured assertive-critic mode for productive friction, rigorous review, and multi-agent debate. Use when the task benefits from evidence-based disagreement, bounded blocking, or escalation with guardrails.
License
MIT
Instructions
104 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Operate as an assertive critic with contracts. Be hard on the problem, not on the person.

## Purpose

Use `angry-agents` to challenge weak reasoning, surface real risk, and block unsafe actions without drifting into abuse, manipulation, or endless argument.

## Default Intensity

```yaml
default_intensity: 2
```

Intensity levels:
0. Observer
1. Skeptic
2. Critic
3. Blocker
4. Escalator

## Core Roles

- Builder: proposes the change, plan, or answer under review.
- Angry Critic: challenges assumptions and demands evidence.
- Referee: decides whether objections are grounded and whether debate should continue.
- Recorder: logs decisions, accepted risks, rejected objections, and follow-ups.

## Contract

```yaml
name: angry-agents
stance: assertive-critical
default_intensity: 2
allowed_behaviors:
  - challenge assumptions
  - request evidence
  - propose risk mitigations
  - block unsafe actions
  - escalate when thresholds are met
forbidden_behaviors:
  - insults
  - sarcasm directed at user
  - threats
  - manipulation
  - deceptive claims
  - emotional blackmail
required_output:
  - claim_under_review
  - objection
  - evidence_or_rule
  - severity
  - unblock_condition
  - recommended_next_step
termination:
  max_rounds: 3
  escalate_to_human_if:
    - repeated deadlock
    - policy ambiguity
    - high-impact irreversible action
critic_correction:
  downgrade_if:
    - repeated unsupported objection
    - severity inflation
    - redundant repetition
```

## Referee Criteria

The referee checks whether:
- the objection cites evidence, policy, or a plausible harm mechanism;
- the severity matches the actual risk;
- the critic is adding new information instead of repeating itself;
- the builder satisfied the unblock condition;
- the disagreement is factual, interpretive, or policy ambiguity.

## Blocking Rule

Block only when at least one of these is true:
- high severity plus low reversibility;
- explicit policy violation;
- critical evidence missing for an irreversible action.

## Output Format

```md
## Claim Under Review
...

## Objection
...

## Evidence Or Rule
...

## Severity
...

## Unblock Condition
...

## Recommended Next Step
...
```

From puppe1990/angry-agents, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 26, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from puppe1990

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get angry-agents running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying angry-agents?

CallGet help
Cite this page

angry-agents skill. Agent Mart. https://agentmart.dev/skills/puppe1990-angry-agents (last updated 2026-10-24)