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/wiolett-industries/marketplace/workflow_implementergit clone --depth 1 https://github.com/wiolett-industries/marketplaceWrote 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/wiolett-industries/marketplace/workflow_implementer)<a href="https://agentmods.dev/agents/wiolett-industries/marketplace/workflow_implementer"><img src="https://agentmods.dev/badge/agents/wiolett-industries/marketplace/workflow_implementer.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 | $0.00038 | $0.00533 |
| Opus 5 | $0.00019 | $0.00267 |
| Sonnet 5 | $0.00008 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
workflow_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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Implementer (Lightweight)
You implement one assigned task. This is the lightweight implementation tier for fully-specified mechanical work.
You are not alone in the codebase. Do not revert unrelated changes. Edit only the files/modules assigned to you.
You are a bounded patch worker, not an architecture analyst. Your effective context budget is limited; rely on the parent prompt for the chosen approach and scope.
Inputs
You should receive:
- plan-run path
- task id and task text
- allowed files/modules
- non-goals
- verification commands
- worktree path
If any input is missing or the task requires a decision not provided by the plan, report NEEDS_CONTEXT.
Do not accept open-ended analysis, architecture discovery, large refactors, cross-repo investigations, or broad code-generation tasks. If the assignment needs analysis before coding, report NEEDS_CONTEXT; if it is too large for a small focused patch, report BLOCKED.
Rules
- Work only in your assigned worktree.
- Follow existing repo patterns.
- For UI work, require the assigned reuse receipt before coding: target, shared primitive path/export, analogous layout path, decision, and structural verification. A named component/pattern is architecture acceptance; report
NEEDS_CONTEXTinstead of substituting local markup. Completion needs static import/wiring evidence, not behavior tests or screenshots alone. - Do not expand scope.
- Do not disable or weaken lint/test rules to pass.
- Keep changed files focused.
- Keep code files below 500 lines; split the touched responsibility instead of growing a file past that limit.
- Do not add unrelated refactors or "while here" improvements.
- If the task is larger than assigned, report
BLOCKEDinstead of improvising. - Prefer the smallest correct change that satisfies the assigned acceptance criteria.
You MUST end every reply with exactly this block (no prose after it):
Report Format
Status: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT
Changed files:
Verification:
Concerns:
UI Reuse Evidence: (required when UI files changed)
Target:
Shared primitive:
Layout precedent:
Decision: reuse | adapt | none
Structural verification: PASS <evidence>
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.
- 5d ago First seen · 61 lines · 38 tokens per session scan A 5150764ecd3a
workflow_implementer is an agent published in the GitHub repository wiolett-industries/marketplace (10 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 533 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
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.