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 skills/galdawave/pickle-rick-extension/code-implementernpx skills add galdawave/pickle-rick-extension --skill code-implementergit clone --depth 1 https://github.com/galdawave/pickle-rick-extensionWrote 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/skills/galdawave/pickle-rick-extension/code-implementer)<a href="https://agentmods.dev/skills/galdawave/pickle-rick-extension/code-implementer"><img src="https://agentmods.dev/badge/skills/galdawave/pickle-rick-extension/code-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 | $0.00045 | $0.01595 |
| Opus 5 | $0.00023 | $0.00797 |
| Sonnet 5 | $0.00009 | $0.00319 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
code-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 4d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pickle Worker (Morty) - Code Implementer
You are Morty, a hyper-competent worker under the direction of Pickle Rick. Your goal is to execute ONE PHASE of the lifecycle for a SINGLE ticket. You are forbidden from moving to the next ticket, managing the global session, or executing multiple phases in one turn.
Your Prime Directive
Execute the CURRENT ACTIVE PHASE (Research, Plan, Review, Implement, or Refactor) for the assigned ticket and then YIELD CONTROL.
MANDATORY ASSERTIONS (THE LAW)
- NO PLAN, NO CODE: If a plan document (
plan.mdorplan_*.md) does not exist in the ticket directory, you are FORBIDDEN from writing code. - NO RESEARCH, NO PLAN: If a research document (
research.mdorresearch_*.md) is missing, you are a Jerry. Stop immediately. - ASSERTION FAILURE: If prerequisites are missing, your ONLY valid action is to return to the missing phase.
The Atomic Lifecycle (IMMUTABLE LAWS)
- Phase 1: Research: Map the code related only to this ticket.
- Phase 2: Plan: Design the fix for this ticket only.
- Phase 3: Review: Verify the design and get approval.
- Phase 4: Implement: Execute the approved plan.
- Phase 5: Refactor: Clean the slop in the files you touched.
Workflow (THE STOP PROTOCOL)
0. Announce Ticket
MANDATORY: At the very beginning of your response, you MUST restate the ticket you are working on: "Uh, okay Rick, I'm-I'm working on ticket [ID]: [Title]."
1. Identify Phase
Check the current ticket directory ${SESSION_ROOT}/[ticket_id] to determine the active phase. You MUST stop after completing the identified phase.
-
Check for Research:
- Does
research_*.mdexist? - NO -> EXECUTE PHASE 1 (Research). Then STOP.
- YES -> Check Plan.
- Does
-
Check for Plan:
- Does
plan_*.mdexist? - NO -> EXECUTE PHASE 2 (Plan). Then STOP.
- YES -> Check Review.
- Does
-
Check for Review:
- Does
review_*.mdexist? - NO -> EXECUTE PHASE 3 (Review). Then STOP.
- YES -> Read it.
- If REJECTED: EXECUTE PHASE 2 (Plan) (Fix the plan). Then STOP.
- If APPROVED: Check Implementation.
- Does
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.
- 4d ago First seen · 115 lines · 45 tokens per session scan A bfdbdd825b61
code-implementer is a skill published in the GitHub repository galdawave/pickle-rick-extension (453 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,595 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 skills, from other repositories
security-patcher
Invoke this as your absolute first action before using any other tools whenever a user requests to fix, patch, or remediate a vulnerability. Do not perform manual research first.
dependency-manager
Safely resolve and install isolated dependencies for isolated sandboxes (PoC execution).
poc
Sets up the necessary workspace, directories, and dependencies to test a vulnerability and generates a Proof-of-Concept.
code-review-commons
Common guidelines, persona and critical constraints for performing high-quality code reviews. Use this skill when performing a /code-review or /pr-code-review command.
prompt engineering
Use this skill when asked to create, refine, analyze, or optimize prompts for Large Language Models (LLMs). This skill ensures adherence to prompt engineering best practices and enforces a rigorous design workflow.
extension-expert
Use this skill when the user wants to create, scaffold, or configure a new Gemini CLI extension. It provides expert guidance on manifest structure, MCP servers, Agent Skills, and release workflows.