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/parkerm2/create-claude-workflow/connect-atlassiangit clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWrote 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/parkerm2/create-claude-workflow/connect-atlassian)<a href="https://agentmods.dev/commands/parkerm2/create-claude-workflow/connect-atlassian"><img src="https://agentmods.dev/badge/commands/parkerm2/create-claude-workflow/connect-atlassian.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 | $0.00042 | $0.01834 |
| Opus 5 | $0.00021 | $0.00917 |
| Sonnet 5 | $0.00008 | $0.00367 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade D, and why
connect-atlassian scanned grade D with 3 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Read `~/.claude/settings.json`. Check if `mcpServers.mcp-atlassian` already exists. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/connect-atlassian — Jira + Confluence Integration
Connects your Atlassian Cloud (or Server/Data Center) account to Claude Code using the sooperset/mcp-atlassian MCP server. Gives Claude access to 72 tools across Jira and Confluence.
Prerequisites
- Atlassian Cloud account (Jira and/or Confluence)
- Python 3.10+ (for
uvx)
Step 1: Check Existing Configuration
Read ~/.claude/settings.json. Check if mcpServers.mcp-atlassian already exists.
- Already configured: Display current config. Ask: "Atlassian is already connected. Update / Keep / Remove?"
- Not configured: Proceed to Step 2.
Step 2: Generate API Token
Guide the user through API token creation:
To connect Jira and Confluence, you need an Atlassian API token.
This takes about 2 minutes and the token lasts up to 365 days.
1. Open: https://id.atlassian.com/manage-profile/security/api-tokens
2. Click "Create API token"
3. Name it "Claude Workflow" (or anything descriptive)
4. Set expiration to 365 days (maximum)
5. Click Create → Copy the token immediately (you can't see it again)
Use AskUserQuestion to collect the API token (user pastes via "Other" text input).
Step 3: Collect Connection Details
Use AskUserQuestion:
- Atlassian site URL: "What is your Atlassian site URL? (e.g., yourcompany.atlassian.net)"
- Email: "What email do you use to log into Atlassian?"
- Products: "Which Atlassian products do you use?"
- Jira + Confluence (both)
- Jira only
- Confluence only
Step 4: Install Prerequisites
# Check if uvx is available
uvx --version 2>/dev/null
If missing, offer to install:
curl -LsSf https://astral.sh/uv/install.sh | sh
Step 5: Configure Environment Variables
Instruct the user to add credentials to their shell profile (~/.bashrc, ~/.zshrc, or ~/.profile):
# Add to your shell profile:
export JIRA_API_TOKEN="<your-api-token>"
export CONFLUENCE_API_TOKEN="<your-api-token>" # Same token works for both
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 · 231 lines · 42 tokens per session scan D 22a2d17d2961
connect-atlassian is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 1,834 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
create-plan
Create a PLANS.md execution plan document for project management.
pm-export
Export desensitized governance summary markdown for sharing or machine switch.
confluence-publish
Publicar documentación del proyecto en Confluence. Convierte markdown a formato Confluence y crea/actualiza páginas en el espacio del proyecto.
requirements
Manage project requirements registry (status, sync, add, update).
brd-package
BRD customer-package workflow (PM phase, fifth command of the BRD-to-PRD route). Gates on the BRD's decisions being merged and on every interview question carrying a terminal disposition or the held-for-the-customer holding state, then runs an adversarial self-review through brd-package-reviewer and refuses to build a…
presentation
Generate MARP presentation slides from existing project artifacts for governance boards and stakeholder briefings.