AgentStack
SKILL verified MIT Self-run

Review Deep

skill-juliusz-cwiakalski-agentic-delivery-os-review-deep · by juliusz-cwiakalski

Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.

No reviews yet
0 installs
19 views
0.0% view→install

Install

$ agentstack add skill-juliusz-cwiakalski-agentic-delivery-os-review-deep

✓ 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.

Are you the author of Review Deep? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Invoke the unified reviewer in local mode with a stronger reasoning model for deeper analysis. Same comprehensive review framework as /review — validates against specification, implementation plan, code quality heuristics, and repository rules.

User invocation: /review-deep [directives...] Examples: /review-deep PDEV-123 /review-deep GH-456 dry run /review-deep PDEV-123 base=staging /review-deep GH-456 head=feat/GH-456/new-endpoint base=production preview only /review-deep PDEV-123 no commit

workItemRef='$1' — Tracker reference (e.g., PDEV-123, GH-456). REQUIRED. directives: remainder free-text. OPTIONAL. Derived flags: baseBranch, headRef, commit (default true), dryRun (default false).

Locate change folder: search doc/changes/**/*----*/ If not found, search: doc/changes/**/chg--spec.md Spec file: chg--spec.md; derive slug & change.type from frontmatter. Plan file: chg--plan.md Folder pattern: doc/changes/YYYY-MM/YYYY-MM-DD----/ Abort with clear error if spec OR plan missing.

changeBranch = // headRef: directives override, else try changeBranch, fallback: current HEAD. baseBranch: directives override, else main, fallback: master. Compute merge-base and gather symmetric diff baseBranch...headRef.

Directives (case-insensitive):

  • Base branch: base= | base branch | compare vs
  • Head ref: head= | head ref | branch
  • Disable commit: commit=false | no commit
  • Dry run: dry run | preview only

Unrecognized tokens ignored.

  1. Validate workItemRef format (uppercase prefix + hyphen + digits).
  2. Resolve spec; extract change.type & slug.
  3. Resolve plan; parse phases & existing remediation.
  4. Load repository rules (AGENTS.md, .ai/rules/**).
  5. Resolve branches & compute diff metadata.
  6. If dryRun: prepare preview but do NOT write.

The reviewer agent applies its full review framework:

Spec/plan compliance (local mode):

  • Scope compliance: changed files align with spec capabilities
  • Plan alignment: all tasks done, acceptance criteria have evidence
  • Plan task audit: OPENTASKS, DONEBUTUNCHECKED, CHECKEDBUT_MISSING
  • Out-of-scope detection: changes to files not in plan

Code quality heuristics (both modes):

  • Full built-in heuristic framework: correctness, security, performance, reliability, API compat, testing gaps, documentation, dependencies
  • Repository-local rules from .ai/agent/code-review-instructions.md and .ai/rules/

Ticket context (when available):

  • Acceptance criteria verification against implementation
  • Linked issue traversal for additional constraints and decisions

The reviewer loads all available context — spec, plan, ticket, repo rules, heuristics — and applies them holistically. Do not duplicate heuristic definitions here; they live in the reviewer agent prompt.

[severity: major|minor|nit] [:line] — ; fix:

If findings exist, append new phase to plan:

### Phase X: Code Review Remediation

- Goal: Address code review findings.
- Tasks:
  - [ ] 
- Acceptance criteria:
  - Must: All fixes implemented and validated.
  - Must: Updated tests pass.
- Files and modules: 
- Completion signal: docs(plan): remediate review findings for 

Rules:

  • X = max existing phase + 1.
  • Do NOT modify earlier phases.
  • Append revision log entry.
  • If commit=true and not dryRun: stage plan file, create Conventional Commit via /commit.
  • If commit=false: write only.
  • Dry run: no write; include preview in output.
  1. Review Summary: pass/fail; changed files count; key themes.
  2. Findings: one line per item.
  3. Plan Update: "Added Phase X" OR "No plan changes required." OR dry-run preview.
  4. Branch info: base, head, changeBranch.
  5. Next action: suggest /run-plan if remediation added.
  • Only modify plan file; never touch spec or code.
  • Never include doc/changes/current in paths.
  • Idempotent: re-running yields no duplicate tasks.
  • No external network calls.
  • Missing spec or plan: abort with message.
  • Unable to derive slug or change.type: abort.
  • Branch resolution failure: fallback to HEAD; note in summary.
  • Empty diff: advisory; no remediation unless plan gaps found.

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.

Versions

  • v0.1.0 Imported from the upstream source.