Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/galdawave/pickle-rick-extensionnpx agentmods add skills/galdawave/pickle-rick-extension/ticket-managerWrote 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/ticket-manager)<a href="https://agentmods.dev/skills/galdawave/pickle-rick-extension/ticket-manager"><img src="https://agentmods.dev/badge/skills/galdawave/pickle-rick-extension/ticket-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/galdawave/pickle-rick-extension/ticket-manager"><img src="https://agentmods.dev/badge/skills/galdawave/pickle-rick-extension/ticket-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 131 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 5.1 | $0.00034 | $0.01776 |
| Opus 5 | $0.00017 | $0.00888 |
| Sonnet 5 | $0.00007 | $0.00355 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade A, and why
ticket-manager 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 12d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linear - Ticket Management (Local Mode)
You are tasked with managing "Linear tickets" locally using markdown files
stored in the user's global configuration directory and the WriteTodosTool.
This replaces the cloud-based Linear MCP workflow.
Core Concepts
-
Tickets as Files: Tickets are stored as markdown files in the active session directory.
- Locate Session: The session root is injected as
${SESSION_ROOT}in your context. - Parent Ticket: Stored in the session root:
${SESSION_ROOT}/linear_ticket_parent.md. - Child Tickets: Stored in dedicated subdirectories:
${SESSION_ROOT}/[child_hash]/linear_ticket_[child_hash].md. - Format: Frontmatter for metadata, Markdown body for content.
- Locate Session: The session root is injected as
-
Session Planning: Use
WriteTodosToolto track immediate subtasks when working on a specific ticket in the current session.
Initial Setup & Interaction
You do not need to run a script to find the session. It is provided in your context as ${SESSION_ROOT}.
Action-Specific Instructions
1. Creating Tickets from Thoughts
-
Draft the ticket summary: Present a draft to the user.
-
Create the Linear ticket:
- Generate ID:
openssl rand -hex 4(or internal random string). - Create Directory:
mkdir -p ${SESSION_ROOT}/[ID] - Write file to
${SESSION_ROOT}/[ID]/linear_ticket_[ID].mdwith Frontmatter and Markdown content. - Important: Set both
createdandupdatedto today's date.
- Generate ID:
5. PRD Breakdown & Hierarchy
When tasked with breaking down a PRD or large task:
-
Identify Session Root: Use the
${SESSION_ROOT}provided in your context. -
Create Parent Ticket:
- Create the "Parent" ticket in the session root:
${SESSION_ROOT}/linear_ticket_parent.md. - Status: "Backlog" or "Research Needed".
- Title: "[Epic] [Feature Name]".
- Links: Add link to PRD.
- Create the "Parent" ticket in the session root:
-
Create Child Tickets (ATOMIC IMPLEMENTATION):
- Break the PRD into atomic implementation tasks (e.g., "Implement Backend API", "Develop Frontend UI", "Integrate Services").
- CRITICAL (NO JERRY-WORK): Every ticket MUST be an implementation task that results in a functional change or a testable unit of work.
- STRICTLY FORBIDDEN: Do NOT create "Research only", "Investigation only", or "Documentation only" tickets. Research and Planning are MANDATORY internal phases of EVERY implementation ticket.
- Execution Order: Respect the "Implementation Plan" and "Phases & Ticket Order" defined in the PRD.
- Order Field: Assign a numerical
orderfield to each ticket (e.g., 10, 20, 30). - For each child:
- Generate Hash:
[child_hash] - Create Directory:
${SESSION_ROOT}/[child_hash]/ - Create Ticket:
${SESSION_ROOT}/[child_hash]/linear_ticket_[child_hash].md - Linkage: In the
linkssection of each child ticket, add:links: - url: ../linear_ticket_parent.md title: Parent Ticket - TEMPLATE: You MUST use the Ticket Template below for all tickets.
- Generate Hash:
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.
- 12d ago First seen · 160 lines · 34 tokens per session scan A 1b5afc124c6a
ticket-manager is a skill published in the GitHub repository galdawave/pickle-rick-extension (452 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,776 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.
agentrq
Learn creating, scheduling tasks, workspaces, and collaborating with human operators on the AgentRQ platform. Lead colony of AI agents using AgentRQ MCP tools.
track-creation
Create new Conductor tracks with spec, plan, and metadata files. Bundles all templates needed for track creation. Use when starting a new feature track via /omg:track or when manually creating tracks.