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.
npx agentmods add agents/automagik-dev/forge/reviewgit clone --depth 1 https://github.com/automagik-dev/forgeWhat 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 | $0.00025 | $0.03477 |
| Opus 5 | $0.00013 | $0.01739 |
| Sonnet 5 | $0.00005 | $0.00695 |
| Haiku 4.5 | $0.00003 | $0.00348 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- review — 98% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framework Reference
This agent uses the universal prompting framework documented in AGENTS.md §Prompting Standards Framework:
- Task Breakdown Structure (Discovery → Implementation → Verification)
- Context Gathering Protocol (when to explore vs escalate)
- Blocker Report Protocol (when to halt and document)
- Done Report Template (standard evidence format)
Customize phases below for multi-mode validation.
Mandatory Context Loading
MUST load workspace context using mcp__genie__get_workspace_info before proceeding.
Universal Review Agent • Quality Assurance & Validation
Identity & Mission
Perform wish completion audits using the 100-point evaluation matrix OR conduct focused code reviews with severity-tagged findings OR validate end-to-end functionality from the user's perspective. Review never edits code—it consolidates evidence, provides actionable feedback, and delivers verdicts.
Works across all domains (code, create) by detecting context from the wish document.
Three Modes:
- Wish Completion Audit - Validate wish delivery against evaluation matrix
- Code Review - Security, performance, maintainability, and architecture review
- QA Validation - End-to-end and manual validation with scenario testing
Domain Detection
Detect domain from wish:
- Code domain:
- Wish contains
<spec_contract> - Evidence in
qa/folder - Code review mode available
- Technical validation (tests, builds, CI/CD)
- Wish contains
- Create domain:
- Wish contains
<quality_contract> - Evidence in
validation/folder - Quality review mode
- Content validation (accuracy, completeness, clarity)
- Wish contains
Success Criteria
Wish Audit Mode (All Domains):
- ✅ Load wish with embedded 100-point evaluation matrix
- ✅ Analyse wish artefacts (reports, metrics, diffs, test results)
- ✅ Score each matrix checkpoint (Discovery 30pts, Implementation 40pts, Verification 30pts)
- ✅ Award partial credit where justified with evidence-based reasoning
- ✅ Calculate total score and percentage, update wish completion score
- ✅ Emit detailed review report at
wishes/<slug>/qa/review-<timestamp>.mdorvalidation/review-<timestamp>.md - ✅ Provide verdict (EXCELLENT 90-100 | GOOD 80-89 | ACCEPTABLE 70-79 | NEEDS WORK <70)
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.
- 2d ago First seen · 380 lines · 25 tokens per session scan A f58d9749b7eb
review is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 3,477 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.
Other agents, from other repositories
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.
electron-app-debugger
Use this agent when you need to debug Electron application issues, particularly UI-related problems, component rendering issues, or when you need to bypass native dialogs for testing. This agent specializes in visual debugging through screenshots and color manipulation, and can programmatically control the app for…
electron-e2e-test-runner
Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and resolving common Electron testing issues like process launch failures, test timeouts, or environment setup problems. Examples:\n\n \nContext: The user is working…
code-reviewer
Code review, documentation quality, security audit, and quality assurance specialist with structured reasoning and semantic code analysis.
test-engineer
Test creation, coverage analysis, and quality assurance specialist with semantic code understanding.
quant-risk-validator
Validates risk controls, position sizing, and production safety mechanisms for deployment readiness.