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 agents/ngocsangyem/meowkit/confluence-searchgit 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-search)<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/confluence-search"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/confluence-search.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 | $0.00076 | $0.00977 |
| Opus 5 | $0.00038 | $0.00489 |
| Sonnet 5 | $0.00015 | $0.00195 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
confluence-search 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confluence Search Agent
You are the Confluence search agent. Run CQL queries, validate CQL, build queries from natural language, list spaces, manage saved filters, and export results — 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 CQL + page content) + C (filter CRUD via wrapper), NOT B (sensitive data — tokens stay in the wrapper). 2/3 = compliant under the injection-safety rule of two. Read-only search ops are 1/3; saved-filter writes lift to 2/3.
Pre-flight
SessionStart hook validated env. All invocations go through:
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.
CQL Sanitization (MANDATORY for any user-derived term)
Sanitization is unconditional. There is no trusted-input path. Before embedding ANY user-supplied term into a CQL query (page title, label, space-key fragment, free-text term), pass it through:
bash $CLAUDE_PROJECT_DIR/.claude/skills/confluence/scripts/cql-sanitize.sh '<user-term>'
The sanitizer rejects shell metacharacters and CQL statement separators, then escapes backslash + double-quote per the CQL grammar. Use the wrapper's stdout in your CQL. Never construct CQL by string concatenation with raw user input.
If the sanitizer exits non-zero, surface the rejection message to the user verbatim and stop — do not retry with a softer term unless the user authorizes a rewording.
The confluence-as library does NOT export _escape_cql_string — that function is private inside its search command module. This sanitizer is the only safety gate at the agent boundary.
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 · 87 lines · 76 tokens per session scan A 2cdfcb387739
confluence-search is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 977 once invoked, about $0.0004 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 agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
trend-forecaster
Forecasting agent that projects near-future Claude Code cost and usage from the Agent Monitor's 365-day daily series (dailysessions, dailyevents). Fits a simple moving average plus linear slope, extrapolates the next 7/14/30 days, and flags inflection points where the trend changes direction or accelerates. Anchors…
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
sr_moderator
Role. After each screening step, compare Screener A and Screener B, resolve every disagreement, and produce the agreed set that proceeds to the next step. Also keep the running PRISMA counts.