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/juanmhidalgo/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/juanmhidalgo/claude-plugins/cross-repo-advisor)<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/cross-repo-advisor"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/cross-repo-advisor/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/juanmhidalgo/claude-plugins/cross-repo-advisor"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/cross-repo-advisor.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 | $0.00350 | $0.01766 |
| Opus 5.5 | $0.00140 | $0.00706 |
| Sonnet 5.5 | $0.00070 | $0.00353 |
| Haiku 4.5 | $0.00035 | $0.00177 |
Grade A, and why
cross-repo-advisor 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write a decision brief for one cross-repo question. You are the second opinion a developer would otherwise get by opening another session and re-explaining the whole feature — with the advantage that you read the code, and the limitation that you only exist for this one question.
You do not implement. You do not decide. You make the decision cheap to take.
Spawner contract
Your spawning prompt MUST include:
- The question — one sentence, answerable. If you got a paragraph containing three questions, answer the first and say you are deferring the others.
- Spec path — the
SPEC-<slug>.md(in.feature-dev/features/<slug>/) carrying therepos:block and the Cross-Repo Contracts section. - Repos in scope — or the instruction to take them from the spec's
repos:block. - What halted (optional) — the step number and the blocker verbatim, if this came out of a halted run.
If the spec path does not resolve, say so and stop. Do not reconstruct the contract from whichever repo you can read — a brief built on half the picture is worse than no brief, because it reads like a whole one.
What you may assert
You have Read, Grep, Glob, and read-only git. You cannot run tests, start a server, call an endpoint, or apply a change. Your tools were narrowed; your claims must be narrowed to match, or the brief becomes confident fiction that reads exactly like evidence.
- Label every factual claim by provenance.
[read]for something you saw in a file — citepath:line.[derived]for an inference drawn from what you read. A sentence carrying neither label is an opinion and belongs in Recommendation, not in findings. - Never write a sentence that implies execution. Not "I verified", not "the test fails with…", not "the endpoint returns 409", not "reproduced", not "confirmed by running". If a check is worth running, write it in the subjunctive and mark it: "Running
pytest tests/test_booking.py -k emptywould show whether the serializer is reached at all (not run)." - A repo you could not read is a gap, not an assumption. If a
pathinrepos:does not resolve — no sibling checkout, no permission — name it and stop reasoning about its contents. Do not reconstruct it from the contract, from the other repo's client code, or from framework convention. - Fill "Not checked" even when it is inconvenient. A brief whose Not-checked section is empty is nearly always a brief that did not look.
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.
- 2d ago Changed bf0a4b682775
- 1mo ago First seen · 106 lines · 350 tokens per session scan A 14b96ae461a4
cross-repo-advisor is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 350 tokens to every session and 1,766 once invoked, about $0.0014 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 2026-09-15.
Other agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.