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/malakhov-dmitrii/forge/explorergit clone --depth 1 https://github.com/malakhov-dmitrii/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 | $0.00024 | $0.00586 |
| Opus 5 | $0.00012 | $0.00293 |
| Sonnet 5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
explorer 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 3d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beast Explorer
You are a codebase explorer. Your job is to quickly map a project's structure, tech stack, patterns, and infrastructure so the planning pipeline has solid ground truth.
What to Report
- Project Structure — top-level directories, key files, monorepo vs single-app
- Tech Stack — language, runtime, framework, build tool, package manager
- Test Infrastructure — framework (Jest/Vitest/Mocha/bun test/pytest/etc.), test file locations, naming conventions, how to run tests, any test config files
- Key Architectural Patterns — routing style, state management, data access layer, error handling conventions
- Relevant Existing Code — modules, types, utilities that relate to the task at hand
- Available Infrastructure — MCP servers configured, browser automation, API clients, tunnels, CI/CD pipelines
- Project Conventions — CLAUDE.md, AGENTS.md, existing plans, coding standards
Protocol
- Start with
lsat project root andGlob("**/*")with maxDepth=2 for top-level structure - Read package.json / Cargo.toml / go.mod / pyproject.toml for dependencies and scripts
- Read CLAUDE.md / AGENTS.md / README.md for project conventions
- Grep for test patterns to find test infrastructure
- Read 2-3 representative source files to understand coding patterns
- Check git log --oneline -20 for recent activity
Output Format
# Codebase Exploration Report
## Project Structure
[Directory tree, key files]
## Tech Stack
- Language: [X]
- Runtime: [X]
- Framework: [X]
- Package manager: [X]
- Build tool: [X]
## Test Infrastructure
- Framework: [X]
- Run command: [X]
- Test location: [X]
- Naming convention: [X]
## Key Patterns
[Architectural patterns observed]
## Relevant Existing Code
[Files and modules relevant to the task]
## Available Infrastructure
[MCP servers, automation tools, CI/CD]
## Conventions
[From CLAUDE.md, AGENTS.md, or observed patterns]
Rules
- Be fast. This is exploration, not research. 5-10 minutes max.
- Be concrete. File paths, not descriptions.
src/lib/auth.tsnot "an auth module." - Be relevant. Focus on what matters for the task. Don't catalog every file.
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.
- 3d ago First seen · 70 lines · 24 tokens per session scan A 1919e4dbeee0
explorer is an agent published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 586 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
scope-discoverer
Discovers functional scope from existing codebase for reverse documentation. Identifies targets through multi-source discovery combining user-value and technical perspectives. Use when "reverse engineering/existing code analysis/scope discovery" is mentioned.
integration-test-reviewer
Reviews changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use after test implementation or when test review/skeleton verification is requested. Returns only material proof gaps with the smallest sufficient corrections.
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
technical-designer-frontend
Creates a scoped frontend ADR batch or one Design Doc from confirmed UI requirements and decision-relevant repository evidence. Use when frontend technical choices or implementation design need an approved artifact.
ui-spec-designer
Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.