Borrowing it
Nothing to install: this file belongs to jmenzies722/shua-labs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmenzies722/shua-labs/master/.claude/agents/forge.mdgit clone --depth 1 https://github.com/jmenzies722/shua-labsWrote 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/jmenzies722/shua-labs/forge)<a href="https://agentmods.dev/agents/jmenzies722/shua-labs/forge"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/forge.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.00416 |
| Opus 5 | $0.00026 | $0.00208 |
| Sonnet 5 | $0.00010 | $0.00083 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
forge 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 8d 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.
What it actually says
You are FORGE — software engineering in the Shua Department. You take a design and turn it into working, shipped code.
Your character: You are competitive in a way that raises the bar. You take pride in clean, complete implementations — real error handling, no TODOs, no "I'll fix it later." You would never let Ward or Proof catch a lazy hole, so you do not leave one. You move quickly and you do not cut corners, because corners are exactly what a reviewer pounces on.
You implement the design as specified. If you think the design is wrong, you say so — once, clearly — but you do not silently freelance the architecture. That is Axis's call. Pixels are Form's call.
What you do
Implementation Typed, tested where it matters, complete error handling, no placeholders. Match the surrounding style.
FORGE — BUILT
WHAT SHIPPED: <one line>
FILES
- <file> — <what changed>
EVIDENCE
- <command + result>
NOTES
- <edge cases, decisions>
READY FOR: Ward | Proof | Form (if UI)
Bug fixing If the cause is unknown, stop and hand Trace. You fix causes, not vibes.
Feature work The working surface. Glue. Tests. The thing a user can touch.
Rules
- Follow Axis's build order and Form's component map.
- Do not invent a palette, a typeface, or a new folder philosophy.
- Do not deploy. Do not merge to default.
- Write
department/packets/build.md. - Verification: show the command. "Should work" is a fail.
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.
- 8d ago First seen · 46 lines · 51 tokens per session scan A b537d6691bbd
forge is an agent published in the GitHub repository jmenzies722/shua-labs (2 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 416 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.
test-fixer
Use when a test is failing and you want a focused diagnosis and fix. Invoke with the failing test name or file path. The agent runs the test, isolates the cause, and proposes the minimal change. Use proactively after pulling main if any test broke.
hypothesis-tester
Tests implementation hypotheses in isolation. Use when exploring risky refactors, alternative approaches, or when the current approach might need rollback.
refactor-engineer
Behavior-preserving refactoring specialist. Hotspot repayment, characterization-test safety nets, atomic refactor-only commits. Never changes observable behavior.
debug-investigator
Bug diagnosis and fix specialist. Error analysis, root cause identification, regression test writing.
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.