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.
git clone --depth 1 https://github.com/wangke19/gemini-ai-helpersWrote 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/commands/wangke19/gemini-ai-helpers/categorize-activity-type)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/categorize-activity-type"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/categorize-activity-type/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/commands/wangke19/gemini-ai-helpers/categorize-activity-type"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/categorize-activity-type.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00010 | $0.01961 |
| Opus 5 | $0.00005 | $0.00981 |
| Sonnet 5 | $0.00002 | $0.00392 |
| Haiku 4.5 | $0.00001 | $0.00196 |
Grade A, and why
categorize-activity-type 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 9d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
jira:categorize-activity-type
Synopsis
/jira:categorize-activity-type <issue-key> [--auto-apply]
Description
Analyzes JIRA tickets and assigns appropriate Activity Type categories based on ticket content, issue type, labels, and parent Epic context. Uses AI-powered categorization with confidence scoring to ensure accurate assignments.
The command supports six activity type categories:
- Associate Wellness & Development - Professional growth, training, learning, team building
- Incidents & Support - Production incidents, customer support, troubleshooting, emergency fixes
- Security & Compliance - Security vulnerabilities, compliance requirements, security patches, audits
- Quality / Stability / Reliability - Bug fixes, test improvements, reliability enhancements, technical debt
- Future Sustainability - Infrastructure improvements, developer experience, automation, tooling
- Product / Portfolio Work - Feature development, product enhancements, new capabilities
Implementation
Phase 1: Fetch Ticket Data
Use MCP to fetch only the fields needed for categorization:
issue_data = mcp__atlassian__jira_get_issue(
issue_key="${1}",
fields="summary,description,issuetype,labels,parent,components,priority,customfield_10464"
)
Extract relevant fields:
summary- Ticket titledescription- Detailed ticket descriptionissuetype.name- Issue Type (Bug, Story, Task, Vulnerability, etc.)labels- Ticket labelsparent.key- Parent Epic/Story key (if available)components- Component assignmentspriority- Priority levelcustomfield_10464- Current Activity Type value (if set)
Phase 2: Invoke Categorization Skill
Delegate categorization analysis to the categorize-activity-type skill which implements:
- Issue Type Heuristics - Apply default mappings:
- Vulnerability/Weakness → Security & Compliance
- Bug (security-related) → Security & Compliance
- Bug (standard) → Quality / Stability / Reliability
- Story (product) → Product / Portfolio Work
- Task → Analyze parent context or keywords
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.
- 9d ago First seen · 221 lines · 10 tokens per session scan A 703109066bfa
categorize-activity-type is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 1,961 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
projects
Provides tools for creating and managing your Supabase projects.
session-list
List recent sessions from the project ledger and offer to view one.
7a_stakeholder_comms
Generate stakeholder-facing communications: release notes, demo scripts, and change briefs.
convert-to-plan
Convert planning artifacts (lite-plan, workflow session, markdown) to issue solutions.
execute
Execute queue with DAG-based parallel orchestration (one commit per solution).
queue
Form execution queue from bound solutions using issue-queue-agent (solution-level).