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 skills/iblai/enterprise-agents/confluencenpx skills add iblai/enterprise-agents --skill confluencegit clone --depth 1 https://github.com/iblai/enterprise-agentsWrote 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/iblai/enterprise-agents/confluence)<a href="https://agentmods.dev/skills/iblai/enterprise-agents/confluence"><img src="https://agentmods.dev/badge/skills/iblai/enterprise-agents/confluence.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 | $0.00036 | $0.00608 |
| Opus 5 | $0.00018 | $0.00304 |
| Sonnet 5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
confluence 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 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.
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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confluence
What it is
Confluence by Atlassian is the most common enterprise wiki and documentation platform, used by engineering, IT, HR, and operations teams to maintain runbooks, technical design docs, architecture decision records (ADRs), and policy documentation. In this segment, the knowledge agent and engineering agent rely on Confluence to retrieve institutional knowledge and draft or update documentation pages.
When to use this skill
- Searching for an existing runbook, policy, or technical document by keyword
- Retrieving the full content of a specific Confluence page for summarization
- Checking the last-modified date and author of a page to assess content freshness
- Creating or updating a page with meeting notes, a post-incident review, or onboarding documentation
- Listing pages within a specific space to inventory available documentation
Credentials
This skill authenticates using variables from ~/.openclaw/.env (template: .env.example at the config root). Required variables:
CONFLUENCE_BASE_URL- base URL (e.g.https://mycompany.atlassian.net/wiki)CONFLUENCE_USER_EMAIL- email of the service accountCONFLUENCE_API_TOKEN- API token from the Atlassian account portal
Key operations
GET /rest/api/content/{id}?expand=body.storage- retrieve page contentGET /rest/api/content/search?cql=...- search pages using CQL (Confluence Query Language)POST /rest/api/content- create a new pagePUT /rest/api/content/{id}- update an existing page (requires current version number)GET /rest/api/space- list available spacesGET /rest/api/content?spaceKey=...&type=page- list pages within a space
Notes
- Authentication uses HTTP Basic with email + API token (same mechanism as Jira cloud).
- Page body format options:
storage(XML/HTML) for reading,wikifor simplified markup on write. - CQL (Confluence Query Language) supports
text ~ "keyword",space = "KEY", andancestor = {page_id}filters. - Rate limits mirror Jira cloud: ~1,000 requests/minute per token; reduce frequency for large space crawls.
- Confluence Server/Data Center has a different API base path (
/confluence/rest/api) and uses PATs instead of API tokens.
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.
- 6d ago First seen · 39 lines · 36 tokens per session scan A 98bd77b9c195
confluence is a skill published in the GitHub repository iblai/enterprise-agents (11 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 608 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
chatbot
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is building-agents), NOT a human answering one ticket…
vf-performance
Use when reviewing code for performance issues, profiling hot paths, benchmarking before/after changes, or optimizing runtime, build, request latency, or bundle size.
flywheel
Development flywheel - autonomous cycle of run, observe, fix, verify. Use for continuous development with browser automation.
veryfront
Build Veryfront apps. Use for real-time errors, route preview, HMR control, and scaffolding pages/APIs/components/AI tools.
vf-error-handling
Use when creating new errors, migrating error classes to registry, catching/handling errors, or working with the VeryfrontError system.
vf-security-checklist
Use when touching auth, user input validation, file paths, redirects, WebSocket, uploads, rate limiting, CORS, or any security-sensitive code in veryfront.