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.
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitnpx agentmods add skills/ulises-jeremias/agent-toolkit/confluence-attachmentWrote 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/ulises-jeremias/agent-toolkit/confluence-attachment)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/confluence-attachment"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/confluence-attachment/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/confluence-attachment"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/confluence-attachment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 135 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 143 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00031 | $0.01160 |
| Opus 5.5 | $0.00012 | $0.00464 |
| Sonnet 5.5 | $0.00006 | $0.00232 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
confluence-attachment 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confluence Attachment Skill
Manage file attachments on Confluence pages.
⚠️ PRIMARY USE CASE
This skill manages files attached to Confluence pages. Use for:
- Uploading files to pages
- Downloading attachments
- Listing files on a page
- Deleting attachments
When to Use / When NOT to Use
| Use This Skill | Use Instead |
|---|---|
| Upload/download files | - |
| List page attachments | - |
| Delete attachments | - |
| Create/edit pages | confluence-page |
| Search for content | confluence-search |
Risk Levels
| Operation | Risk | Notes |
|---|---|---|
| List/download | - | Read-only |
| Upload | - | Can be deleted |
| Update | ⚠️ | Replaces existing file |
| Delete | ⚠️ | Moves to trash (recoverable) |
Delete --purge |
⚠️⚠️ | Permanent - only works on an already-trashed attachment |
CLI Commands
confluence-as attachment upload
Upload a file to a page.
Usage:
confluence-as attachment upload PAGE_ID FILE_PATH
confluence-as attachment upload 12345 report.pdf
confluence-as attachment upload 12345 image.png --comment "Screenshot"
confluence-as attachment upload 12345 data.csv --output json
Options:
--comment- Comment describing the attachment--output, -o- Output format:text(default) orjson
confluence-as attachment download
Download an attachment.
Usage:
confluence-as attachment download ATTACHMENT_ID --output ./downloads/
confluence-as attachment download att123456 --output myfile.pdf
confluence-as attachment download 12345 --all --output ./downloads/ # Download all from page
Options:
--output, -o- Output file or directory (default: current directory)--all, -a- Download all attachments from a page (the ID argument is a page ID)
confluence-as attachment list
List attachments on a page.
Usage:
confluence-as attachment list 12345
confluence-as attachment list 12345 --output json
confluence-as attachment list 12345 --output table
confluence-as attachment list 12345 --media-type application/pdf
confluence-as attachment list 12345 --limit 50
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 Changed a969f4581dcd
- 1mo ago First seen · 160 lines · 31 tokens per session scan A 0e6d416c2b6f
confluence-attachment is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (19 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 1,160 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
read
Read PDF page by page with structured output — key arguments, terms glossary, thesis connections. Use when reading academic papers, books, or articles.
release-governance
Use when preparing, auditing, releasing, PDF-hardening, or rebuttal-hardening academic manuscripts, datasets, artifacts, reviewer packets, or claim registers involving multiple refs, local assets, human labels, agent-assisted drafts, wide tables, figure provenance, submission PDFs, or evidence-boundary checks.
export
Convert thesis chapters and reading notes from Markdown to Word (.docx) and package for submission. Use when preparing materials for supervisors or examiners.
human-eval-handoff-repair
Use when validating, repairing, or mapping human-evaluation handoff packages, filled annotation CSVs, rebuttal annotation UIs, or reviewer annotation returns across package versions. Applies to checking row alignment, detecting cross-snapshot contamination, converting old labels to current schemas, generating…
local-mcp-pdf-to-sheet
Use when the user wants to pull data out of one or more PDFs (invoices, bank/credit-card statements, receipts, reports, tables) and put it into a spreadsheet. pdfread is one of the most-used tools; this codifies the read-PDF → structure → write-Excel workflow. Powered by LMCP on macOS and Windows.
google-drive
Read, export, upload, rename, move and delete Google Drive files explicitly selected or shared with the app via the Drive v3 REST API. Use when the user provides a Drive file ID/link or has selected files for the Google Drive connector.