Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. 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/Smart-AI-Memory/attune-ai/main/.agents/skills/cross-review/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/smart-ai-memory/attune-ai/cross-review)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/cross-review"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/cross-review/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/smart-ai-memory/attune-ai/cross-review"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/cross-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.01716 |
| Opus 5.5 | $0.00024 | $0.00686 |
| Sonnet 5.5 | $0.00012 | $0.00343 |
| Haiku 4.5 | $0.00006 | $0.00172 |
Grade A, and why
cross-review 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross Review
IMPORTANT: Start your response by telling the user:
Cross review — one non-authoring seat reviews the real diff. Advisory only: findings inform you; they never gate anything.
Binding posture (spec requirement, not style)
Board-only ADVISORY. Never wire this skill's output into a merge
gate, CI check, exit code, or blocking path — that violates
docs/specs/cross-review/requirements.md (Binding posture). Only a
chair ruling backed by the spec's dogfood ledger can upgrade it.
What it does
Phase T2 of docs/specs/cross-review/: the moderator (this
session) resolves the current branch's diff vs its merge base
(default) or the staged diff, briefs ONE non-authoring seat with
the ACTUAL diff under an honest truncation manifest, posts the
reply to the board, renders findings as advisory items, and
appends a dogfood-ledger row. All mechanics live in
attune.roundtable.review — do not reimplement them inline.
Steps
- Spend gate: state seat + target (one line) and get a go
(session-durable, same rule as
/roundtable). An existing explicit review request is the go for that seat/target. For an explicitly requested Claude subscription review, useseat="claude", claude_auth="subscription". The launcher checks saved Pro/Max authentication in a child with API credentials removed, disables tools/custom integrations, and refuses ambiguous/API authentication. It does not raise or disable the API spend cap or modify interactive authentication. Subscription entitlement is not an invoice/overage receipt. - Run (module does target resolution, brief, invocation, lint, board post):
MODE="branch" python -c "import os, sys, json, structlog; structlog.configure(logger_factory=structlog.PrintLoggerFactory(file=sys.stderr))
from attune.roundtable import Board; from attune.roundtable.review import run_review; b=None
try:
b=Board(); b.ensure_functions()
except Exception as e: print(f'board unavailable: {e}', file=sys.stderr)
print(json.dumps(run_review('.', mode=os.environ['MODE'], board=b), ensure_ascii=False))"
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 Changed · +20 lines a678830388cd
- 1mo ago Changed · +29 lines 692ae0d36cbe
- 1mo ago Changed · +18 lines · +2 tokens per session c8244f44eb61
- 1mo ago First seen · 78 lines · 58 tokens per session scan A 6b9e29957b53
cross-review is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 1,716 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 2026-08-31.
Other skills, from other repositories
attest
Verifying spec compliance: extracts ACs from specs, adversarially checks conformance, generates BDD scenarios and traceability matrices. Use when impl must be proven to match a PRD/SRS/AC.
guardian
Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy; the ship recipe also executes PR delivery (create, CI watch, merge, cleanup) with Ask First on merge. Use when PR preparation, commit strategy, or gated PR delivery is needed.
atlas
Analyzing dependencies, circular references, and God Classes; authoring ADRs/RFCs. Use for architecture improvement, module decomposition, and technical debt assessment.
judge
Reviewing code via multi-engine orchestration (Claude + Codex) on three axes — secure, correct, and lean — shipping only findings worth fixing. Use for PR review or pre-commit. Complements Zen.
quill
Adding JSDoc/TSDoc, updating READMEs, replacing any types with proper definitions, and adding high-value comments to complex logic. Use for documentation gaps or type safety.
zen
Refactoring code: variable naming, function extraction, magic number constants, dead code removal. Does not change behavior. Not for bugs (Judge), security (Sentinel), tests (Radar), or features (Builder).