Borrowing it
Nothing to install: this file belongs to drabaioli/cdd. 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/drabaioli/cdd/main/.claude/commands/cdd-process-pr.mdgit clone --depth 1 https://github.com/drabaioli/cddWrote 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/commands/drabaioli/cdd/cdd-process-pr)<a href="https://agentmods.dev/commands/drabaioli/cdd/cdd-process-pr"><img src="https://agentmods.dev/badge/commands/drabaioli/cdd/cdd-process-pr/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/commands/drabaioli/cdd/cdd-process-pr"><img src="https://agentmods.dev/badge/commands/drabaioli/cdd/cdd-process-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.02535 |
| Opus 5.5 | $0.00000 | $0.01014 |
| Sonnet 5.5 | $0.00000 | $0.00507 |
| Haiku 4.5 | $0.00000 | $0.00253 |
Grade A, and why
cdd-process-pr 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 28d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address the open PR's review feedback: read the review comments for the current branch, triage them, implement the change-requests (pushing back where warranted), then auto-post in-thread replies and auto-commit + push the result.
Run this command on the feature branch (not on main), after a PR has been opened and someone has reviewed it. It is a post-review side-loop, analogous in position to /cdd-merge-base.
Note on automation: this command has a single checkpoint, placed up front: the triage plan in step 4. Once the user approves that plan, the rest of the run — edits, in-thread replies, commit, push — executes without further confirmation gates. Do not add per-action gates after the plan is approved — the one exception is where step 5 routes a workflow gap (folded into this PR, a roadmap item, or an issue on another repo), which the triage plan does not settle and which is asked once, with a recommendation. Review threads are never resolved by this command; the user resolves them.
1. Discover the open PR
Confirm the current branch is not main:
git rev-parse --abbrev-ref HEAD
Resolve the code host down the ladder — project, then machine; the first file present wins:
for c in .cdd/code-host ~/.cdd/adapters/code-host; do [ -e "$c" ] && { CODE_HOST="$c"; break; }; done
If $CODE_HOST is set, check it before using it: the file is executable, and "$CODE_HOST" describe exits 0, parses as JSON, and reports capability code-host and contract 1. If any of that fails, the adapter is installed but broken — say so in one line naming its path, and stop; do not route around it, because an installed adapter declares which code host this project uses. If it is usable, say in one line which adapter serves and its backend. With nothing resolved, print No code-host adapter is installed; run /cdd-retrofit in this project to install one. and stop.
Resolve the open PR for the current branch.
"$CODE_HOST" pr-for-branch "$(git rev-parse --abbrev-ref HEAD)" # JSON array, newest first
Keep only the entries whose state is open. If pr-for-branch is not in the adapter's describe.verbs (or it exits 3), say so in one line and ask the user for the PR reference instead. Any other failure → say so in one line, quoting the adapter's error line, and stop.
- If there is no open PR, stop and report clearly: "No open PR for this branch; nothing to process."
- If there is more than one open candidate PR, stop and ask the user which PR number to process.
Hold the PR number — the open entry's .ref; the steps below refer to it as NUMBER.
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.
- 28d ago Changed · -57 lines 6380ff6f1026
- 1mo ago Changed · +42 lines b93c6df1f3d4
- 2mo ago First seen · 173 lines · 0 tokens per session scan A d2501ed2283c
cdd-process-pr is a command published in the GitHub repository drabaioli/cdd (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,535 tokens. 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 commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
review
Review the current diff against project memory.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.
code-review-give
Give mode for code-review: Review someone else's code with multi-pass analysis and structured recommendations.
review-design-verify
Phases 4-5 of reviewing-design-docs: Interface Verification + Implementation Simulation.
lucius
Segunda opinión técnica externa vía Codex CLI — diagnóstico y prescripción por ítem.