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 skills add thamaraiselvam/mcp-jira-confluence --skill jira-confluence-cligit clone --depth 1 https://github.com/thamaraiselvam/mcp-jira-confluenceWrote 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/thamaraiselvam/mcp-jira-confluence/jira-confluence-cli)<a href="https://agentmods.dev/skills/thamaraiselvam/mcp-jira-confluence/jira-confluence-cli"><img src="https://agentmods.dev/badge/skills/thamaraiselvam/mcp-jira-confluence/jira-confluence-cli.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 | $0.00217 | $0.04949 |
| Opus 5 | $0.00109 | $0.02475 |
| Sonnet 5 | $0.00043 | $0.00990 |
| Haiku 4.5 | $0.00022 | $0.00495 |
Grade A, and why
jira-confluence-cli 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 8d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jira & Confluence CLI Skill
Drive Jira and Confluence from the terminal using the published mcp-jira-confluence npm package. Its bundled CLI — reached through the package's single entry point (npx -y mcp-jira-confluence@latest <group> <command>) — wraps the same Jira/Confluence API layer as the MCP server, so every capability is available without starting a server.
The CLI is read-heavy with controlled writes — there are deliberately no delete operations. If the user asks to delete a page, issue, or comment, refuse and explain the CLI does not support destructive actions; suggest doing it manually in the Atlassian UI.
Quick reference: which command for which action
Match the user's intent to a command here first, then jump to the detailed table for exact args. Commands are written in shorthand (jira … / confluence …); run each through the CLI runner — prepend npx -y mcp-jira-confluence@latest (see Run below). Set up Credentials before the first command.
Jira
| The user wants to… | Command | Notes |
|---|---|---|
| Find / list / count issues | jira search --jql '<JQL>' |
Use --json to parse keys for follow-ups. |
| Read one issue (summary, status, assignee, description, labels…) | jira get-issue --issueIdOrKey KEY |
Returns core fields + description as text; does not return comments. |
| Create a story / bug / task / epic | jira create-issue … |
--description is a file path. |
| Edit summary / priority / labels / any field | jira update-issue --fields '{…}' |
JSON object of fields. |
| Edit or replace the description | jira update-issue --descriptionFile body.md |
Markdown file → ADF. |
| Assign / reassign / unassign an issue | jira update-issue --fields '{"assignee":"<accountId>"}' |
No assign command. "assignee":null unassigns. Needs an account ID (see caveats). |
| Change status / move through workflow | jira get-transitions … then jira transition-issue … |
Always list transitions first — valid ones depend on current status. |
| See what statuses an issue can move to | jira get-transitions --issueIdOrKey KEY |
|
| Comment on an issue | jira add-comment --markdownBody note.md |
Body is a file path. |
| Edit an existing comment | jira update-comment --commentId ID --markdownBody note.md |
Comment ID comes from the add-comment --json response (or the Atlassian UI) — there is no list-comments command. |
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.
- 8d ago First seen · 270 lines · 0 tokens per session scan A 7854b5817c9f
jira-confluence-cli is a skill published in the GitHub repository thamaraiselvam/mcp-jira-confluence (2 stars, last pushed 3mo ago), licensed MIT. It adds 217 tokens to every session and 4,949 once invoked, about $0.0011 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 skills, from other repositories
hmem-new-project
Create a new P-entry (project) in hmem via createproject — handles schema, section setup, and O-entry linking. Use when the user asks to add/register/track a new project ('neues Projekt', 'P-Entry erstellen'), or before any writememory with prefix='P'.
hmem-activate
Switch active project mid-session via loadproject, then fix any misrouted O-entry exchanges. Use when the user says 'aktiviere/lade Projekt X', 'switch to project Y', or whenever you'd otherwise call loadproject mid-session.
orchestrations
Pick and run a multi-phase workflow that chains foundational task skills (git-wrapup, release-and-publish, maintenance, field-test, setup, etc.) end-to-end. Routes user intent to a workflow file under workflows/ — greenfield builds, maintenance + release, field-test + fix, or known-work + release. Single source for…
openclaw-task-queue
Persistent task queue MCP server with 5 tools for AI agents. Use when: (1) 'create a task for later' or 'add to queue', (2) 'what tasks are pending' or 'show task list', (3) 'assign this task to agent X', (4) 'mark task as complete' or 'finish this task', (5) 'how many tasks are done' or 'queue statistics'. TaskFlow…
rentalot
Comprehensive reference for the Rentalot platform — AI-powered rental agent with 37 MCP tools across 14 domains. Use when working with Rentalot API, MCP server, property management, contacts, showings, messaging, workflows, or any Rentalot integration.
report-issue-local
File a bug or feature request against this MCP server's own repo. Use for server-specific issues — tool logic, service integrations, config problems, or domain bugs that aren't caused by the framework.