Get Feedback Markdown Plan
DEPRECATED — use the pair-* skill series (e.g. pair-consult / pair-optimize) instead. Evaluates inline feedback annotations on a markdown plan by verifying each critique against the codebase and context using subagents.
Install
$ agentstack add skill-ccomkhj-skills-get-feedback-markdown-plan ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-ccomkhj-skills-get-feedback-markdown-plan) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Get Feedback on Markdown Plan
> ⚠️ Deprecated. Use the pair-* skill series (e.g. pair-consult, pair-optimize) instead. This skill is no longer installed and is kept only for reference.
You have a markdown plan with inline feedback annotations (e.g., [CODEX], [Claude], or similar tags). Your job is to verify whether each annotation is correct by checking it against the codebase and project context.
Workflow
- Parse — Extract all inline annotations from the plan. For each one, capture the annotation text and the plan section it refers to.
- Group — Cluster related annotations that share context (e.g., multiple comments about the same service, same migration step, or same data flow). Each group becomes one subagent task.
- Verify — Launch one subagent per group in parallel. Each subagent receives:
- The plan section(s) under review
- The annotation(s) to verify
- Instruction: explore the codebase to determine if the critique is factually correct. Return one of:
- Correct — the critique identifies a real problem. Briefly explain why.
- Wrong — the critique is incorrect or based on a false assumption. Explain what it got wrong.
- Inconclusive — cannot verify from available context. State what's missing.
- Report — Present a summary table:
| # | Annotation | Verdict | Reason | |---|-----------|---------|--------| | 1 | ... | Correct / Wrong / Inconclusive | One-line explanation |
Then list the annotations that were Wrong with full reasoning, so the user knows which feedback to ignore.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ccomkhj
- Source: ccomkhj/skills
- License: MIT
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.