A command for checking open pull requests for human review feedback before starting new work. A pull request is a proposed code change awaiting review.

Use it to find actionable comments, requested changes, and relevant labels, then implement, test, commit, push, and report the fixes.

It helps surface requested changes early and prevents new work from taking priority over unresolved feedback on existing changes.

review-prs — Command by nkhdiscovery

Install

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.

agentmods

npx agentmods add commands/nkhdiscovery/headless-agentic-codebase/review-prs

Clone the repo

git clone --depth 1 https://github.com/nkhdiscovery/headless-agentic-codebase

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 449 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00011	$0.00449
Opus 5	$0.00005	$0.00225
Sonnet 5	$0.00002	$0.00090
Haiku 4.5	$0.00001	$0.00045

Measured yesterday against content hash 4e63651361c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-prs 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 yesterday.

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.

.claude/commands/review-prs.md · 32 lines

What it actually says

Check for actionable feedback on your open PRs and address it before any new work.

List your open PRs: gh pr list --author @me --state open --json number,title,labels,reviewDecision
Filter to PRs that are agent-produced (not merged/closed).

Actionable feedback means any of:

A comment whose body starts with @agent (case-insensitive)
A review with state CHANGES_REQUESTED
Labels: needs-revision, agent-please-fix

For each PR with feedback:

Check out the branch: git fetch && git checkout <branch> && git pull
Read full PR conversation — every comment and review thread.
If feedback is ambiguous or contradicts CLAUDE.md/ADRs/unattended-rules, leave a clarifying comment, label blocked, move on.
Otherwise: implement requested changes. Tests first. Run make ci locally and capture to plans/ci-<N>.log + .exit (see docs/unattended-rules.md → "Running tests locally").
Commit: fix: address PR #<N> review feedback — <summary>
Push to same branch.
Post local make ci output as a PR comment (see docs/unattended-rules.md → "Posting local test output to the PR").
If plans/ci-<N>.log.exit is 0 and PR is mergeable, self-merge: gh pr merge <N> --squash --delete-branch. GitHub Actions checks (if a human opted in) are informational only — local result is the gate.
Reply to PR with summary of what changed.
Remove agent-please-fix label.

If a PR has human-takeover label, skip it permanently.

Record activity in logs/daily/YYYY-MM-DD.md under "PR feedback".

Only after all open PRs are handled, move to /next-issue.

Changes

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.

yesterday First seen · 32 lines · 11 tokens per session scan A 4e63651361c5

Subscribe to this mod's changes

review-prs is a command published in the GitHub repository nkhdiscovery/headless-agentic-codebase (10 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 449 once invoked, about $0.0001 per session on Opus 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.

Code review Git and workflow Testing agentic-ai agentic-coding ai-agent ai-engineering autonomous-agent boilerplate

review-prs

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

implement

workflow-claude-commands

workflow-claude-subagents

weather-orchestrator

agent-farm

oss-docs