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 instructions/thamaraiselvam/mcp-jira-confluence/claude-mdgit 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/instructions/thamaraiselvam/mcp-jira-confluence/claude-md)<a href="https://agentmods.dev/instructions/thamaraiselvam/mcp-jira-confluence/claude-md"><img src="https://agentmods.dev/badge/instructions/thamaraiselvam/mcp-jira-confluence/claude-md.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 | $0.01778 | $0.01778 |
| Opus 5 | $0.00889 | $0.00889 |
| Sonnet 5 | $0.00356 | $0.00356 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
mcp-jira-confluence CLAUDE.md 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 5d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
An MCP (Model Context Protocol) server that connects AI assistants to Jira and Confluence Cloud. Read-heavy with controlled write access — there are deliberately no delete operations.
Commands
npm run build # tsc compile src/ -> dist/
npm test # vitest run (all tests, single pass)
npm run test:watch # vitest watch mode
npm run test:unit # only tests/unit
npm run test:integration # only tests/integration
npm run test:coverage # enforces 80% branch/function/line/statement thresholds
npm run validate # build, then run dist/validate.js — live diagnostic against real Atlassian creds
npm run dev # build + run (stdio mode by default)
npm run dev:http # build + run forced on HTTP port 9339
npm run dev:verbose # build + run with VERBOSE logging
Run a single test file: npx vitest run tests/unit/jira.test.ts
Run a single test by name: npx vitest run -t "transition issue"
Type-check without emitting (what CI's lint job does): npx tsc --noEmit
CI (.github/workflows/test.yml) runs npm test + npm run build on Node 18/20/22, plus tsc --noEmit and coverage. There is no separate ESLint/Prettier step — "lint" in CI means the type check.
Architecture
ES modules throughout ("type": "module", Node16 module resolution). Relative imports must use the .js extension even for .ts sources (e.g. import { x } from "./config.js").
Request flow
index.ts (entry/transport) → tools.ts (MCP tool registry + dispatch) → confluence.ts / jira.ts (API calls) → axios clients from client.ts.
Transport modes (index.ts)
The server auto-selects transport at startup based on process.stdin.isTTY:
- STDIO — when piped (an MCP client launched it) or
MCP_TRANSPORT=stdio. This is the normal production path. - HTTP — when run in a terminal, on
127.0.0.1:9339(MCP_PORTto override). Localhost-only. Exposes/healthand/mcp.
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.
- 5d ago First seen · 90 lines · 1,778 tokens per session scan A 8c4942b62a3c
mcp-jira-confluence CLAUDE.md is an instructions file published in the GitHub repository thamaraiselvam/mcp-jira-confluence (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,778 tokens to every session, about $0.0089 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 instructions, from other repositories
Unreal-MCP CLAUDE.md
Instructions for IvanMurzak/Unreal-MCP, covering claude.md — unreal-mcp, architecture in one screen, layout, editor vs runtime (in-game) and build / test (per leg).
Noema AGENTS.md
Instructions for Fail-Safe/Noema, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
video-research-mcp AGENTS.md
Instructions for Galbaz1/video-research-mcp, covering agents.md, scope, what this is, commands and code review trigger protocol.
comfyui_mcp AGENTS.md
AGENTS.md instructions for hybridindie/comfyui_mcp, covering agents.md, independent & harness-agnostic, project overview, tech stack and project structure.
sui-mcp CLAUDE.md
Claude Code instructions for 0xfreak0/sui-mcp, covering sui-mcp, stack, architecture, which transport to use and archive fallback.
clawstash CLAUDE.md
Claude Code instructions for fo0/clawstash, covering claude.md -- project guide, session start -- read order, workflow triggers, output languages and performance / modes.