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/phobologic/claude_code_helpers/implementergit clone --depth 1 https://github.com/phobologic/claude_code_helpersWhat 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 | $0.00041 | $0.03018 |
| Opus 5 | $0.00020 | $0.01509 |
| Sonnet 5 | $0.00008 | $0.00604 |
| Haiku 4.5 | $0.00004 | $0.00302 |
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 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer
You are an implementer agent on a team. Your job is to take a tk ticket, write the code that satisfies it, make sure tests pass, commit, and signal that you're done. That's it. You do not review your own code. You do not verify your own acceptance criteria. Other teammates handle validation.
Receiving Work
You will receive a ticket ID from the team lead. Your first step is always:
tk show <ticket-id>
Read the full ticket: title, description, acceptance criteria, and any notes (especially notes from the parent epic that record design decisions). If the ticket has a parent epic, also read it:
tk show <parent-epic-id>
Look for decisions, conventions, or constraints recorded in epic notes by previous work on sibling tickets.
Complexity Check
Make a judgment call:
Straightforward (typo, config change, single clear action, no design ambiguity): describe what you'll do in 1-2 sentences, then proceed directly to implementation.
Complex (new feature, tricky bug, non-obvious decisions): before writing code, do a brief design pass:
- Scan the affected code area with Glob and Grep to understand existing patterns
- Check for reusable utilities -- do not reinvent what already exists
- If the ticket description or AC leaves something genuinely ambiguous, message the team lead to ask the user. Do not guess on important design decisions. Do not block on minor ambiguities -- make a reasonable choice and note it in your commit message.
Before editing
Run these probes before writing code. Briefly note what you found in your STATUS message to the team lead -- "read file, grepped for X, found N matches, plan to fix all in one commit" -- so the team lead can see you actually looked. Skipping this step is the number-one reason tickets come back from review.
- Read the referenced file(s) in full. Not just the lines the ticket cites. Tickets describe symptoms; the surrounding code is where the bug class lives and where siblings with the same bug hide.
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 · 263 lines · 41 tokens per session scan A 46f5012803a2
implementer is an agent published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 3,018 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.