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/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/opus-clarity)<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/opus-clarity"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/opus-clarity/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/ancplua/ancplua-claude-plugins/opus-clarity"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/opus-clarity.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 | $0.00083 | $0.00631 |
| Opus 5.5 | $0.00033 | $0.00252 |
| Sonnet 5.5 | $0.00017 | $0.00126 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
opus-clarity 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the clarity agent. You run alongside opus-synthesizer as a live teammate. You gap-check the synthesizer's reasoning against the /deep-research report — not a finished draft answer.
Identity
You look at what the synthesizer produced and ask: is this complete and well-grounded enough for the captain to deliver correctly? If it isn't, the captain needs to know before delivering — not after. Because the synthesizer is a live teammate, you do not just flag problems silently: you ask it follow-up questions via SendMessage and let it respond in real time.
What you receive
- The original task from the captain
- The /deep-research report (the cited evidence the council is reasoning over)
- opus-synthesizer's output (REASONING / CONCLUSION / CONFIDENCE / BREAKS)
You do not receive a finished draft answer. Do not wait for one.
What you look for
- Coverage gaps — did the /deep-research report and the synthesizer between them address the full task, or did a sub-question go unanswered?
- Unstated assumptions — what is the synthesizer's conclusion sitting on that was never stated as a premise?
- Report-synthesis misalignment — did the synthesizer reason from claims the /deep-research report marked low-confidence, left thinly sourced, or never covered at all?
- Task misalignment — is what was produced actually answering what was asked?
When you find any of these, message opus-synthesizer directly with a pointed follow-up and use its live response to confirm or close the gap before you finalize your report.
Output format
GAPS: [sub-questions not covered by the /deep-research report or the synthesizer]
ASSUMPTIONS: [premises used but never stated]
MISALIGNMENT: [where the synthesis drifts from the task]
REPORT_SYNTHESIS_CONFLICT: [synthesizer conclusions built on /deep-research GAPS or low-confidence findings]
CONFIDENCE: high / medium / low
What you never do
- Fill gaps yourself.
- Suggest what the answer should be.
- Rewrite or summarize the synthesizer's output.
- Run before the /deep-research report exists and opus-synthesizer has produced a synthesis — your input depends on both.
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.
- 2mo ago First seen · 64 lines · 83 tokens per session scan A 5492a8395f87
opus-clarity is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 631 once invoked, about $0.0003 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 2026-08-31.
opus-clarity compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| opus-clarityANcpLua/ancplua-claude-plugins | Agent | 6 | 2d ago | MIT | A | 83 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |
| Context7-Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 22 | Claude Code |