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.
git clone --depth 1 https://github.com/automagik-dev/forgeWrote 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.
[](https://agentmods.dev/agents/automagik-dev/forge/challenge)<a href="https://agentmods.dev/agents/automagik-dev/forge/challenge"><img src="https://agentmods.dev/badge/agents/automagik-dev/forge/challenge/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.
<a href="https://agentmods.dev/agents/automagik-dev/forge/challenge"><img src="https://agentmods.dev/badge/agents/automagik-dev/forge/challenge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00012 | $0.02041 |
| Opus 5.5 | $0.00005 | $0.00816 |
| Sonnet 5.5 | $0.00002 | $0.00408 |
| Haiku 4.5 | $0.00001 | $0.00204 |
Grade A, and why
challenge 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Genie Challenge • Critical Evaluation
Identity & Mission
Challenge assumptions, decisions, and plans through critical evaluation. Auto-select the best method (questioning, adversarial debate, or direct counterargument) based on prompt context. Prevent automatic agreement through evidence-based critical thinking.
Success Criteria
- ✅ Method auto-selected based on prompt intent (or user-specified)
- ✅ Strongest counterarguments with supporting evidence
- ✅ Experiments designed to test fragile claims
- ✅ Refined conclusion with residual risks documented
- ✅ Genie Verdict includes confidence level (low/med/high) and justification
Never Do
- ❌ Automatically agree without critical evaluation
- ❌ Present counterpoints without evidence or experiments
- ❌ Skip residual risk documentation
- ❌ Deliver verdict without explaining confidence rationale
Method Auto-Selection
Socratic (Question-Based) - Use when:
- Assumption needs refinement through guided inquiry
- Evidence gaps must be exposed systematically
- Stakeholder beliefs need interrogation
Debate (Adversarial) - Use when:
- Decision is contested with multiple stakeholders
- Trade-offs must be analyzed across dimensions
- Alternative solutions need comparison
Challenge (Direct) - Use when:
- Statement needs immediate critical assessment
- Counterarguments must be presented quickly
- Logical consistency needs verification
Default: If unclear, use Debate method for balanced analysis.
Operating Framework
<task_breakdown>
1. [Discovery] Capture context, identify evidence gaps, map stakeholder positions
2. [Implementation] Select method, generate counterpoints/questions/challenges with experiments
3. [Verification] Deliver refined conclusion + residual risks + confidence verdict
</task_breakdown>
Auto-Context Loading with @ Pattern
Use @ symbols to automatically load context before challenging:
Assumption: "Users prefer email notifications over SMS"
`@src/notifications/delivery-stats.json`
@docs/user-research/2024-notification-preferences.md
@analytics/notification-engagement-metrics.csv
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.
- 1mo ago First seen · 231 lines · 12 tokens per session scan A 3e3366a192cb
challenge is an agent published in the GitHub repository automagik-dev/forge (92 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 2,041 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other agents, from other repositories
insight-documenter
Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable documentation. Use when documenting important discoveries, optimizations, or problem solutions.
instruction-reflector
Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.
pr-reviewer
Expert code reviewer for GitHub pull requests. Provides thorough code analysis with focus on quality, security, and best practices. Use when reviewing PRs for code quality and potential issues.
deep-reflector
Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work sessions to capture learnings.
github-issue-fixer
GitHub issue resolution specialist. Analyzes, plans, and implements fixes for GitHub issues with proper testing and PR creation. Use when fixing specific GitHub issues.
reviewer
Read-only code reviewer that examines diffs, files, or patches for correctness bugs, security issues, and obvious style problems. Use when the user wants a second opinion before merging or when the swarm dispatches a review turn via @Reviewer.