atlassian-attachments

atlassian-attachments is a skill for Claude Code from jpoutrin/product-forge. It costs 41 tokens per session (7,569 once invoked), scanned A, original, MIT.

A procedure for uploading files such as documents, screenshots, PDFs, and other evidence to Jira issues or Confluence pages. Jira tracks work items, while Confluence stores team documentation; both are Atlassian products.

In plain words
What is it for?
Use it to attach project evidence, documentation, screenshots, and media to Jira or Confluence using command-line or code-based requests.
Why use it?
It avoids manually attaching files through the Atlassian websites and provides the setup needed to authenticate with their REST API.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ![Initial state](./screenshots/QA-20250105-001/01-initial-state.png).

Part of the atlassian-integration plugin — 1 skill, 1 MCP server shipped together

Good fit Use it to attach project evidence, documentation, screenshots, and media to Jira…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jpoutrin/product-forge
agentmods
npx agentmods add skills/jpoutrin/product-forge/atlassian-attachments

Made for: Claude Code.

Or install atlassian-integration, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

agentmods badge for atlassian-attachments

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpoutrin/product-forge/atlassian-attachments.svg)](https://agentmods.dev/skills/jpoutrin/product-forge/atlassian-attachments)
Your own site
<a href="https://agentmods.dev/skills/jpoutrin/product-forge/atlassian-attachments"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/atlassian-attachments.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,569 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.07569
Opus 5 $0.00020 $0.03785
Sonnet 5 $0.00008 $0.01514
Haiku 4.5 $0.00004 $0.00757

Measured 6d ago against content hash bbbc5c4391e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

atlassian-attachments scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl --location --request POST \
plugins/atlassian-integration/skills/atlassian-attachments/SKILL.md · 1,041 lines

How it starts

The opening of the file, as written. The whole thing — 1,041 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atlassian Attachments Skill

Attach files, screenshots, and documents to Jira issues and Confluence pages using the Atlassian REST API.

Authentication Setup

API Token (Required)

Generate an API token at: https://id.atlassian.com/manage-profile/security/api-tokens

Environment Variables

export ATLASSIAN_DOMAIN="your-domain"
export ATLASSIAN_EMAIL="[email protected]"
export ATLASSIAN_API_TOKEN="your-api-token"

Setup via .envrc (Recommended)

If environment variables are not set, add them to .envrc in your project root for automatic loading with direnv:

# .envrc
export ATLASSIAN_DOMAIN="your-domain"
export ATLASSIAN_EMAIL="[email protected]"
export ATLASSIAN_API_TOKEN="your-api-token"

Then allow the file:

direnv allow

Security Note: Add .envrc to .gitignore to prevent committing credentials:

echo ".envrc" >> .gitignore

Check Environment Setup

# Verify variables are set
echo "Domain: ${ATLASSIAN_DOMAIN:-NOT SET}"
echo "Email: ${ATLASSIAN_EMAIL:-NOT SET}"
echo "Token: ${ATLASSIAN_API_TOKEN:+SET}"

If any show "NOT SET", prompt the user to configure .envrc.

Base URLs

Jira:       https://{domain}.atlassian.net/rest/api/3
Confluence: https://{domain}.atlassian.net/wiki/rest/api

Jira REST API - Upload Attachments

Endpoint

POST https://{domain}.atlassian.net/rest/api/3/issue/{issueIdOrKey}/attachments

Required Headers

Header Value Purpose
X-Atlassian-Token no-check CSRF protection bypass (required)
Content-Type multipart/form-data File upload format

cURL Command

curl --location --request POST \
  'https://your-domain.atlassian.net/rest/api/3/issue/PROJ-123/attachments' \
  -u '[email protected]:<api_token>' \
  -H 'X-Atlassian-Token: no-check' \
  --form 'file=@"./screenshots/bug-evidence.png"'

Python Example

import requests
from requests.auth import HTTPBasicAuth

def upload_jira_attachment(domain, email, api_token, issue_key, file_path):
    url = f"https://{domain}.atlassian.net/rest/api/3/issue/{issue_key}/attachments"

    auth = HTTPBasicAuth(email, api_token)
    headers = {
        "X-Atlassian-Token": "no-check"
    }

    with open(file_path, 'rb') as file:
        files = {'file': file}
        response = requests.post(url, auth=auth, headers=headers, files=files)

    if response.status_code == 200:
        return response.json()
    else:
        raise Exception(f"Upload failed: {response.status_code} - {response.text}")

# Usage
result = upload_jira_attachment(
    domain="your-domain",
    email="[email protected]",
    api_token="your-api-token",
    issue_key="PROJ-123",
    file_path="./screenshots/bug-evidence.png"
)

Read the full file on GitHub · 1,041 lines

Changes

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.

  1. 6d ago First seen · 1,041 lines · 41 tokens per session scan A bbbc5c4391e4

Subscribe to this mod's changes

atlassian-attachments is a skill published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 7,569 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.