AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Dag Review

skill-abysscn-oh-my-dag-dag-review · by AbyssCN

Adversarial multi-dimension diff review as a DAG: correctness/security/boundary/contract lenses review the diff concurrently, then a verify/refute layer converges findings (kills plausible-but-wrong ones). Trigger: review this diff / PR review / 审查这组改动 / 提交前对抗审查 / find P0s before merge / dag-review. Skip: root-cause debugging of a known bug (investigate directly) / building code (/dag-build embed…

↗ Repository
— No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-abysscn-oh-my-dag-dag-review

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-abysscn-oh-my-dag-dag-review)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 16d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Dag Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

/dag-review — adversarial diff review

Reviews a git diff through independent dimension lenses concurrently, then runs an adversarial verify layer over the findings — each finding must survive an attempted refutation before it reaches the report. Gate levels size the dimension set.

Usage

bun run dag-review \
  [--gate G2|G3]      # G1=[contract,boundary] G2=[correctness,security,boundary] G3=G2+contract
  [--base main]       # diff base (default main)
  [--staged]          # review staged changes instead
  [--dims correctness,security,boundary,contract]   # explicit dimension override
  [--extra ""] # extra reviewer focus, free text
  [--model M] [--brief] [--no-verify] [--paths "src,sql"] [--out path]

Exit 2 on empty diff. Artifact default: /tmp/pi-dag-review--.md.

Discipline

  • Findings that fail refutation are dropped, not softened — the verify layer exists

to kill plausible-but-wrong reviews, the classic weak spot of single-pass LLM review.

  • --no-verify only for quick brainstorm passes; never for a merge gate.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML