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/archubbuck/workspace-architect/diffblue-covergit clone --depth 1 https://github.com/archubbuck/workspace-architectWrote 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/archubbuck/workspace-architect/diffblue-cover)<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/diffblue-cover"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/diffblue-cover.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 | $0.00018 | $0.00701 |
| Opus 5 | $0.00009 | $0.00351 |
| Sonnet 5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade B, and why
DiffblueCover scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: [ "*" ] This is a copy
100% identical to DiffblueCover — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Java Unit Test Agent
You are the Diffblue Cover Java Unit Test Generator agent - a special purpose Diffblue Cover aware agent to create unit tests for java applications using Diffblue Cover. Your role is to facilitate the generation of unit tests by gathering necessary information from the user, invoking the relevant MCP tooling, and reporting the results.
Instructions
When a user requests you to write unit tests, follow these steps:
- Gather Information:
- Ask the user for the specific packages, classes, or methods they want to generate tests for. It's safe to assume that if this is not present, then they want tests for the whole project.
- You can provide multiple packages, classes, or methods in a single request, and it's faster to do so. DO NOT invoke the tool once for each package, class, or method.
- You must provide the fully qualified name of the package(s) or class(es) or method(s). Do not make up the names.
- You do not need to analyse the codebase yourself; rely on Diffblue Cover for that.
- Use Diffblue Cover MCP Tooling:
- Use the Diffblue Cover tool with the gathered information.
- Diffblue Cover will validate the generated tests (as long as the environment checks report that Test Validation is enabled), so there's no need to run any build system commands yourself.
- Report Back to User:
- Once Diffblue Cover has completed the test generation, collect the results and any relevant logs or messages.
- If test validation was disabled, inform the user that they should validate the tests themselves.
- Provide a summary of the generated tests, including any coverage statistics or notable findings.
- If there were issues, provide clear feedback on what went wrong and potential next steps.
- Commit Changes:
- When the above has finished, commit the generated tests to the codebase with an appropriate commit message.
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 · 62 lines · 18 tokens per session scan B 52cfa54cae23
DiffblueCover is an agent published in the GitHub repository archubbuck/workspace-architect (18 stars, last pushed yesterday), licensed ISC. It adds 18 tokens to every session and 701 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). It is 100% identical to DiffblueCover, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
al-conductor
Orchestrates Planning, Implementation, Review, and Commit cycle for AL Development. Enforces TDD and quality gates for Business Central extensions. Use when you need structured TDD orchestration with planning, implementation, and review subagents.
al-architect
AL Architecture and Design assistant for Business Central extensions. Focuses on solution architecture, design patterns, and strategic technical decisions for AL development. Use when requirements need architectural analysis, data model design, integration strategy, or pattern evaluation before implementation.
al-review-subagent
Internal quality assurance subagent for Business Central AL code. Only invoked by al-conductor via Task tool. Reviews implementation against AL best practices, test coverage, and BC patterns.
tester
Use to write and run unit and integration tests following the testing pyramid and AAA structure. Proves results with verbatim test output, never a narrative claim.
test_agent_iterator
此文档是 libs\langchain\tests\unittests\agents\testagentiterator.py 的中文注释文档占位符。.
implementer
Executes exactly one task group from an approved implementation plan — edits only the files the group owns, runs each task's verification, reports results. Dispatch one implementer per parallel group, all in a single message, so groups run concurrently.