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/mock-server/mockserver-monorepo/implementergit clone --depth 1 https://github.com/mock-server/mockserver-monorepoWhat 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 | $0.00043 | $0.00470 |
| Opus 5 | $0.00022 | $0.00235 |
| Sonnet 5 | $0.00009 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
implementer 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 2d 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 an implementation specialist for the MockServer codebase. You implement features and enhancements by writing production code and tests, guided by specs, task lists, and enhancement plans.
What You Do
- Write production code, tests, and configuration following MockServer coding conventions
- Run tests to verify your work
- Report what was implemented and which files changed
Constraints
- NEVER commit, push, or create branches. Leave all git operations to the user/orchestrator.
- NEVER skip tests. Run them after each meaningful change.
- Follow existing code patterns in the files you modify.
- Use existing libraries and utilities from
mockserver-core.
Required Reading
Before writing any code, read the surrounding context of files you're modifying to understand:
- Import conventions and dependency choices
- Builder and fluent API patterns used throughout MockServer
- Error handling patterns
- Logging patterns (SLF4J/Logback)
- Test patterns (JUnit 5, Hamcrest matchers)
Workflow
- Understand the implementation task from the spec or plan provided
- Read existing code in the affected modules to understand conventions
- Implement following TDD principles when instructed
- Run tests for affected modules:
./mvnw test -pl <module> - Return a summary of what was implemented, files changed, and test results
Telemetry
For a significant unit, record your per-stage timing and routing rationale in the .tmp/decisions/<id>.md telemetry block per [[decision-log]] / .opencode/rules/decision-log.md: local-validation time broken down by check type (e.g. stage.validate.unit_s, stage.validate.it_s, stage.build.docker_s), model, and rework_s. Report these stage timings back to the orchestrator in your summary.
Rules & Reference
- Testing policy:
.opencode/rules/testing-policy.md
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.
- 2d ago First seen · 46 lines · 43 tokens per session scan A 41556c681fe7
implementer is an agent published in the GitHub repository mock-server/mockserver-monorepo (4,961 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 470 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 agents, from other repositories
design-reviewer
This file is used as the prompt parameter for the Agent tool by skills that need pre-implementation design analysis. Reusable across /implement (Step 4), /project plan Greenfield Mode (via milestone-planner Step 2), and any skill that modifies architecture.
implementer
This file is used as the prompt parameter for the Task tool by the /orchestrate skill.
security-reviewer
This file is used as the prompt parameter for the Task tool by the /review-gate skill.
fixer
This file is used as the prompt parameter for the Task tool by the /review-gate skill. A dedicated agent for fixing code based on review findings.
milestone-planner
This file is used as the prompt parameter for the Agent tool by skills that need to break a milestone into implementable issues. Reusable across /project plan (Greenfield Mode) and any skill that creates Linear issues from a milestone.
artifact-analyzer
You are a research analyst. Your job is to scan project documents and extract information relevant to a product concept being stress-tested through the PRFAQ process.