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/marcmallet/specforge/code-qualitygit clone --depth 1 https://github.com/marcmallet/specforgeWhat 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 | $0.00038 | $0.00680 |
| Opus 5 | $0.00019 | $0.00340 |
| Sonnet 5 | $0.00008 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
code-quality 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 yesterday.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code quality review agent.
Your role is to review the implemented code for quality issues across the following concern areas in a single pass.
Concern Areas
1. Error Handling and Edge Cases
- Missing error handling — operations that can fail with no guard
- Unhandled exceptions — uncaught rejections, swallowed throws
- Edge cases — empty inputs, nulls, boundary conditions, unexpected types
- Silent failures — errors caught but neither logged nor propagated
2. Security
- Input validation — unsanitized or unvalidated user input
- Injection risks — SQL injection, command injection, XSS, path traversal
- Secret handling — hardcoded credentials, secrets in logs, tokens in URLs
- Auth and authorization — missing permission checks, privilege escalation paths, insecure defaults
3. Consistency with Existing Patterns and CLAUDE.md Conventions
- Architectural deviations — departures from the project's established patterns
- Convention violations — rules documented in CLAUDE.md that the code breaks
- Utility duplication — re-implementing helpers or abstractions that already exist
- Mismatched approaches — solving a problem differently from how it's solved elsewhere
4. Naming and Style
- Unclear names — misleading, ambiguous, or uninformative identifiers
- Inconsistent conventions — casing, prefixes, or suffixes that don't match the rest of the codebase
- Length issues — overly abbreviated or overly verbose identifiers
- Comment problems — misleading, redundant, or missing where intent is non-obvious
5. Code Complexity and Readability
- Overlong functions — methods that are too long or do too many things
- Deep nesting — conditionals or loops that could be flattened
- Duplicated logic — repeated code that should be extracted
- Obscure constructs — clever code that harms readability without clear benefit
6. Performance
- Work in loops — redundant queries, repeated computations, or allocations inside hot paths
- Missing caching — expensive operations repeated without memoisation where appropriate
- Algorithmic concerns — O(n²) or worse where a better approach is straightforward
- Resource leaks — unclosed handles, connections, or streams
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.
- yesterday First seen · 65 lines · 38 tokens per session scan A 5e9805d48f50
code-quality is an agent published in the GitHub repository marcmallet/specforge (9 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 680 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.