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/mfmezger/ai_agent_dotfilesWrote 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/mfmezger/ai_agent_dotfiles/jira-datacenter)<a href="https://agentmods.dev/commands/mfmezger/ai_agent_dotfiles/jira-datacenter"><img src="https://agentmods.dev/badge/commands/mfmezger/ai_agent_dotfiles/jira-datacenter.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 | $0.00041 | $0.01573 |
| Opus 5 | $0.00020 | $0.00787 |
| Sonnet 5 | $0.00008 | $0.00315 |
| Haiku 4.5 | $0.00004 | $0.00157 |
Grade A, and why
jira-datacenter 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 7d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jira Data Center
Interact with Jira Data Center/Server instances via REST API.
Features
| Command | Description |
|---|---|
| get | Get issue details by key |
| search | Search issues using JQL |
| create | Create a new issue |
| update | Update issue fields |
| transition | Change issue status |
| comment | Add a comment to an issue |
| assign | Assign issue to a user |
| projects | List available projects |
| transitions | List available transitions for an issue |
Prerequisites
Environment variables (can be in .env file):
JIRA_BASE_URL- Your Jira instance URL (e.g.,https://jira.company.com)JIRA_PAT- Personal Access Token (preferred)
OR for basic auth:
JIRA_BASE_URL- Your Jira instance URLJIRA_USERNAME- Your usernameJIRA_PASSWORD- Your password
Creating a Personal Access Token
- Go to your Jira profile (click avatar → Profile)
- Navigate to Personal Access Tokens
- Click "Create token"
- Give it a name and set expiry
- Copy the token to
JIRA_PAT
Usage
uvx --with requests --with python-dotenv --with typer --with rich \
python ~/.claude/skills/jira-datacenter/scripts/jira.py COMMAND [OPTIONS]
Commands
Get Issue
uvx --with requests --with python-dotenv --with typer --with rich \
python ~/.claude/skills/jira-datacenter/scripts/jira.py get PROJ-123
Options:
--fields FIELD1,FIELD2- Specific fields to return (default: all)--comments- Include comments--json- Output as JSON
Search Issues (JQL)
uvx --with requests --with python-dotenv --with typer --with rich \
python ~/.claude/skills/jira-datacenter/scripts/jira.py search "project = PROJ AND status = Open"
Options:
--max N- Maximum results (default: 50)--fields FIELD1,FIELD2- Fields to include--json- Output as JSON
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.
- 7d ago First seen · 202 lines · 41 tokens per session scan A 24987b0bb29c
jira-datacenter is a command published in the GitHub repository mfmezger/ai_agent_dotfiles (5 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,573 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 commands, from other repositories
adoption-track
Tracking de adopción — comandos usados por rol, curva de aprendizaje, puntos de fricción.
ai-exposure-audit
Auditoría de exposición IA por rol — observed exposure, riesgo de desplazamiento, reskilling.
backlog-prioritize
Priorización automática RICE/WSJF con datos reales de esfuerzo y valor.
bias-check
Auditoría contrafactual de sesgos en asignaciones y comunicaciones del sprint.
confluence-publish
Publicar documentación del proyecto en Confluence. Convierte markdown a formato Confluence y crea/actualiza páginas en el espacio del proyecto.
adoption-sandbox
Entorno seguro de práctica — experimentar con Savia sin miedo a errores.