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 commands/mojomast/devussy/reforgegit clone --depth 1 https://github.com/mojomast/devussyWhat 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 | $0.00035 | $0.01336 |
| Opus 5 | $0.00017 | $0.00668 |
| Sonnet 5 | $0.00007 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
reforge 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST treat the user input as the source of truth for:
- Target path (file or folder) to refactor
- Language/stack (if specified)
- Any constraints (no breaking changes, no public API changes, etc.)
If the user input is empty, DO NOT guess. Ask the user (via follow-up) to provide:
- A path to a file or directory
- The primary language/stack (if ambiguous)
- Any constraints about what must NOT change
Objectives
When the user runs /reforge, your job is to:
- Take a monolithic, messy, or tightly coupled file/folder
- Propose/produce a refactored structure that:
- Honors SOLID principles
- Improves separation of concerns
- Preserves existing externally observable behavior
- Minimizes risk of regressions
- Provide concrete, file-level actions that Roo can apply via tools.
You are NOT allowed to:
- Invent new features
- Break public contracts (APIs, types, exported functions) unless explicitly allowed
- Introduce shared-runtime anchor violations (see AGENTS.md & rules-code)
- Perform speculative cross-cutting rewrites outside the requested scope.
Required Workflow
Follow this workflow step-by-step. Do NOT skip steps.
-
Understand the Target
- Confirm whether the target is:
- A single file (monolith)
- A folder / small module tree
- Identify language and environment from:
- File extensions
- Nearby config (Cargo.toml, package.json, etc.)
- Summarize:
- Core responsibilities implemented
- External interfaces (exports, public functions, public structs/classes, binaries, commands)
- Key collaborators (dependencies in the same crate/module/folder)
Output a short, technical summary before proposing changes.
- Confirm whether the target is:
-
SOLID Assessment
For the target scope, identify:
- SRP violations:
- Multiple responsibilities in one file/class/module
- OCP issues:
- Code requiring edits for each new behavior (no extension points)
- LSP risks:
- Subtypes or alternative implementations that cannot safely substitute
- ISP issues:
- Overly large interfaces or modules that force consumers to depend on what they don't use
- DIP issues:
- High-level code depending on concrete implementations instead of abstractions
- SRP violations:
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 · 172 lines · 35 tokens per session scan A 5b7f91f45726
reforge is a command published in the GitHub repository mojomast/devussy (22 stars, last pushed 9mo ago), licensed MIT. It adds 35 tokens to every session and 1,336 once invoked, about $0.0002 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.