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 commands/wangke19/gemini-ai-helpers/backloggit 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/backlog)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/backlog"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/backlog.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 5.1 | $0.00016 | $0.06201 |
| Opus 5 | $0.00008 | $0.03100 |
| Sonnet 5 | $0.00003 | $0.01240 |
| Haiku 4.5 | $0.00002 | $0.00620 |
Grade C, and why
backlog scanned grade C with 2 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 2d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
# Extract credentials from your mcp.json file Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Solution:** This command uses `curl` to fetch data directly from JIRA and save to disk, then processes it with Python. It reads JIRA credentials from `~/.config/claude-code/mcp.json` - the same file used by the MCP ser This is a copy
89% identical to backlog — 169 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
jira:backlog
Synopsis
/jira:backlog [project-key] [--assignee username] [--days-inactive N]
Description
The jira:backlog command helps identify suitable tickets from the JIRA backlog to work on by intelligently analyzing unassigned tickets and bot-assigned tickets. Unlike simple filtering, this command reads ticket descriptions, comments, and activity patterns to recommend the best candidates for work.
Key Feature: The command selects 2 tickets from each priority level (Critical, High, Normal, Low) that are actually available to pick up (unassigned or assigned to bots only), giving you a balanced view across all priorities so you can choose based on your expertise and preference.
Important: This command only recommends tickets that are unassigned or assigned to bots (like "OCP DocsBot"). Tickets assigned to real people are excluded, even if they have no recent activity, because they may already be claimed by someone.
This command is particularly useful for:
- Finding tickets to work on when you have available capacity
- Identifying unassigned or abandoned tickets that need attention
- Getting a mix of priorities to choose from (not just critical)
- Understanding ticket context before starting work
How it works:
- Searches for unassigned tickets or tickets with no activity for 28+ days (configurable)
- Filters for availability - keeps only unassigned or bot-assigned tickets
- Analyzes ticket content - reads descriptions, comments, and activity patterns
- Evaluates suitability - identifies tickets that are ready vs. need verification vs. may be abandoned
- Selects intelligently - chooses the most suitable 2 tickets from each priority level
- Provides comprehensive summaries with recommendations for each ticket
Prerequisites
This command requires JIRA credentials to be configured via the JIRA MCP server setup, even though it uses direct API calls instead of MCP commands.
1. Install the Jira Plugin
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.
- 2d ago First seen · 597 lines · 16 tokens per session scan C 7c92fb0764ff
backlog is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 6,201 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, makes network calls). It is 89% identical to backlog, differing in 169 lines, and is treated as a copy.
Other commands, from other repositories
spec-design
Create comprehensive technical design for a specification.
spec-kitty.implement
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
release-prod
Guide you through promoting stage → production.
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.
modernize-extract-rules
Mine business logic from legacy code into testable, human-readable rule specifications.
mem-search
Full-text search in the memory vault (archives, contexts, histories, index).