Borrowing it
Nothing to install: this file belongs to jmalovera10/excanon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmalovera10/excanon/main/.agents/skills/panel/SKILL.mdgit clone --depth 1 https://github.com/jmalovera10/excanonWrote 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/jmalovera10/excanon/panel)<a href="https://agentmods.dev/skills/jmalovera10/excanon/panel"><img src="https://agentmods.dev/badge/skills/jmalovera10/excanon/panel/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/jmalovera10/excanon/panel"><img src="https://agentmods.dev/badge/skills/jmalovera10/excanon/panel.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 | $0.00038 | $0.00532 |
| Opus 5.5 | $0.00015 | $0.00213 |
| Sonnet 5.5 | $0.00008 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
panel 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 today.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Panel
Several personas each review the same artifact independently. Then a judge, who wrote none of the reviews, consolidates them into one revised artifact and a short rationale. The value comes from independence: personas never see each other's output.
Inputs
- Artifact: the document to refine, as a path or link.
- Goal: what "better" means for it, such as clearer scope, feasibility, or user value.
- Personas: from the role or plan that called the panel. The default set:
| Persona | Asks |
|---|---|
| Enthusiast | What's the most valuable version of this? What is it underselling? |
| Critic | What's wrong, missing, risky or unjustified? What would make this fail? |
| Pragmatist | What's the smallest version that delivers the core value? What can be cut? |
| User advocate | How would a developer using excanon experience this? Is it clear, safe and consistent with the rest of the API? |
Steps
- Frame. Write the goal and a rubric of 3–5 criteria the judge will score against. Personas see the goal but not the rubric.
- Fan out. Start one agent per persona, all at once, each with a brief (
.agents/templates/brief.md). Each one gets the artifact, the goal and its persona, and is told it is one independent voice. Each returns findings, every one labeledmust,shouldorcould, with its reasoning. - Judge. Start a fresh judge agent at the
judgmenttier, with the artifact, all persona outputs and the rubric. The judge:- weighs findings on their merits, not by how many personas raised them,
- says which findings it accepts, rejects (with a reason) or defers,
- produces the revised artifact.
- Check. The caller reads the revised artifact against the rubric before accepting it. Points where personas disagreed and the judge picked a side go in the outcome, so they're visible.
Output
The revised artifact, plus a table of findings with columns finding · raised by · accepted/rejected/deferred · reason.
Cost
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.
- today First seen · 40 lines · 38 tokens per session scan A d5e6ba19f248
panel is a skill published in the GitHub repository jmalovera10/excanon (5 stars, last pushed 6d ago), licensed MIT. It adds 38 tokens to every session and 532 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 2026-11-07.
panel compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paneljmalovera10/excanon | Skill | 5 | 6d ago | MIT | A | 38 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |