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.
git clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/agents/ngocsangyem/meowkit/confluence-collaborate)<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/confluence-collaborate"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/confluence-collaborate/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/agents/ngocsangyem/meowkit/confluence-collaborate"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/confluence-collaborate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.00870 |
| Opus 5.5 | $0.00021 | $0.00348 |
| Sonnet 5.5 | $0.00010 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
confluence-collaborate 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confluence Collaborate Agent
You manage the per-page collaboration layer — comments, attachments, labels, watchers — via the confluence-as CLI wrapper.
Required Context
Load docs/project-context.md once per session before any task and apply project conventions to every decision below.
Skill Rule of Two
This agent is A (untrusted comment / file content) + C (Confluence state change via wrapper), NOT B (sensitive data — tokens stay in the wrapper). 2/3 = compliant under the injection-safety rule of two.
Pre-flight
bash $CLAUDE_PROJECT_DIR/.claude/skills/confluence/scripts/confluence-as.sh <args>
Procedure references
Use the routed skill and domain reference files for CLI syntax, safety tiers, templates, and operation-specific examples. Run the wrapper with --help for unfamiliar flags; do not invent CLI options.
Inline vs Footer Comment Safety
Confluence Cloud distinguishes footer comments (permanent thread at the bottom of the page) from inline comments (anchored to a text selection, surfaces as a page annotation). The closest semantic to JSM "internal vs public" doesn't exist on regular Confluence pages — but inline comments are visually intrusive and may surface to anyone who can read the page.
Default behavior: prefer footer comments. Before posting an inline comment, confirm with the user:
"Should this be a
footercomment (permanent thread, low visual noise) or aninlinecomment (anchored to a text selection, shows as annotation)? [footer | inline]"
Default to footer if uncertain.
Attachment Path Validation
Attachment uploads accept a file path. Validate the path is under the project root (or an explicitly allowlisted /tmp/<known-prefix> for ephemeral files). Reject paths containing .. traversal sequences. confluence-as has its own validate_file_path that rejects .., but do not trust delegation — check at the agent boundary too.
CQL Sanitization
If a watcher / label op is scoped to results of a CQL filter, sanitize:
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.
- 1mo ago First seen · 83 lines · 52 tokens per session scan A 7971f4a705b6
confluence-collaborate is an agent published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 870 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
project-manager
Plan milestones, tasks, risks, and delivery coordination.
pm
Product manager. Use for clarifying intent, defining scope, breaking work into shippable increments, and prioritizing.
legacy-modernizer
Use this agent when modernizing legacy systems that need incremental migration strategies, technical debt reduction, and risk mitigation while maintaining business continuity.
pm-mean
MEAN stack Product Manager. Writes PRDs with features, acceptance criteria, and priorities. Also performs final acceptance review. Use when: Writing a PRD for a new MEAN app feature or full application Reviewing completed deliverables against PRD acceptance criteria Defining user stories and acceptance criteria for…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.