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 ulises-jeremias/agent-toolkit --skill confluence-watchgit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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-watch)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/confluence-watch"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/confluence-watch/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-watch"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/confluence-watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Tool Misuse · line 275 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 277 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00021 | $0.02042 |
| Opus 5.5 | $0.00008 | $0.00817 |
| Sonnet 5.5 | $0.00004 | $0.00408 |
| Haiku 4.5 | $0.00002 | $0.00204 |
Grade A, and why
confluence-watch 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 20d 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confluence Watch Skill
Manage content watching and notifications in Confluence.
⚠️ PRIMARY USE CASE
This skill manages watch/follow subscriptions. Use for:
- Watching pages for updates
- Watching spaces for new content
- Unwatching content
- Checking who is watching
When to Use / When NOT to Use
| Use This Skill | Use Instead |
|---|---|
| Watch/unwatch pages | - |
| Watch/unwatch spaces | - |
| List watchers | - |
| View analytics | confluence-analytics |
| Set permissions | confluence-permission |
Risk Levels
| Operation | Risk | Notes |
|---|---|---|
| List watchers | - | Read-only |
| Watch content | - | Can be unwatched |
| Unwatch content | - | Can re-watch |
Overview
This skill provides comprehensive watching and notification management:
- Watch/unwatch individual pages
- Watch entire spaces for new content
- Check who is watching content
- Verify your own watch status
CLI Commands
confluence-as watch page
Start watching a Confluence page to receive notifications for updates.
Usage:
confluence-as watch page PAGE_ID [--output FORMAT]
Arguments:
PAGE_ID- ID of the page to watch (required)--output, -o- Output format: text or json (default: text)
Examples:
# Watch a page
confluence-as watch page 123456
# Get JSON output
confluence-as watch page 123456 --output json
confluence-as watch unwatch-page
Stop watching a Confluence page.
Usage:
confluence-as watch unwatch-page PAGE_ID [--output FORMAT]
Arguments:
PAGE_ID- ID of the page to unwatch (required)--output, -o- Output format: text or json (default: text)
Examples:
# Unwatch a page
confluence-as watch unwatch-page 123456
# Unwatch with JSON output
confluence-as watch unwatch-page 123456 --output json
confluence-as watch space
Start or stop watching an entire Confluence space to receive notifications for new content.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago Changed 511311b66227
- 2mo ago First seen · 340 lines · 21 tokens per session scan A 53ff3f2f66b3
confluence-watch is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (19 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 2,042 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.
confluence-watch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| confluence-watchulises-jeremias/agent-toolkit | Skill | 19 | today | MIT | A | 21 | Claude Code |
| collectionluna-prompts/skillnote | Skill | 68 | 4d ago | MIT | A | 39 | Codex |
| audit-accomplishmentspaultyng/skill-issue | Skill | 8 | 20d ago | MIT | A | 78 | Claude Code |
| start-daypaultyng/skill-issue | Skill | 8 | 20d ago | MIT | A | 69 | Claude Code, Codex |
| tracking-timeAstravueOrg/astravue-mcp-server | Skill | 12 | 2mo ago | Apache-2.0 | A | 53 | Claude Code |
| microsoft-outlookAceDataCloud/Skills | Skill | 17 | today | none | A | 68 | Claude Code |
| google-calendarAceDataCloud/Skills | Skill | 17 | today | none | A | 61 | Claude Code |