@olegkoval/agent-skills 1.20.0 → 1.21.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-agent-skills",
   "description": "Agent-agnostic skill catalog for Codex, Claude, Cursor, Grok, Copilot, Windsurf, Kiro, and other skill-aware tools.",
-  "version": "1.19.1",
+  "version": "1.20.0",
   "author": {
     "name": "Oleg Koval"
   },
@@ -33,6 +33,7 @@
     "./packages/software-development/skill-budget-audit",
     "./packages/software-development/crash-course",
     "./packages/software-development/qodoloop",
-    "./packages/wearables/garmin-watchface"
+    "./packages/wearables/garmin-watchface",
+    "./packages/software-development/coderabbitloop"
   ]
 }

package/.cursor-plugin/index.json

@@ -115,6 +115,11 @@
       "name": "olko:garmin-watchface",
       "source": "./packages/wearables/garmin-watchface/adapters/cursor",
       "description": "Build, test, screenshot and publish Garmin Connect IQ watch faces in Monkey C."
+    },
+    {
+      "name": "olko:coderabbitloop",
+      "source": "./packages/software-development/coderabbitloop/adapters/cursor",
+      "description": "Iteratively drives a GitHub PR to zero unresolved CodeRabbit findings — reads each inline comment's own Prompt for AI Agents block, applies the fix, replies to the thread, resolves it, pushes, and re-triggers CodeRabbit."
     }
   ]
 }

package/.grok-plugin/index.json

@@ -125,6 +125,11 @@
       "name": "olko:garmin-watchface",
       "source": "./packages/wearables/garmin-watchface/adapters/grok",
       "description": "Build, test, screenshot and publish Garmin Connect IQ watch faces in Monkey C."
+    },
+    {
+      "name": "olko:coderabbitloop",
+      "source": "./packages/software-development/coderabbitloop/adapters/grok",
+      "description": "Iteratively drives a GitHub PR to zero unresolved CodeRabbit findings — reads each inline comment's own Prompt for AI Agents block, applies the fix, replies to the thread, resolves it, pushes, and re-triggers CodeRabbit."
     }
   ]
 }

package/.kiro/steering/coderabbitloop.md

@@ -0,0 +1,109 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+inclusion: manual
+description: "Iteratively drives a GitHub PR to zero unresolved CodeRabbit findings — reads each inline comment's own Prompt for AI Agents block, applies the fix, replies to the thread, resolves it, pushes, and re-triggers CodeRabbit."
+---
+
+# Coderabbitloop
+
+Fix every actionable CodeRabbit finding on a PR, answer each thread, resolve it, and keep going until CodeRabbit has nothing left to say (or a finding needs a human call).
+
+## Inputs
+
+- **PR number** (optional): detect from the current branch if not given.
+
+## How CodeRabbit actually posts (verified against docs.coderabbit.ai and a live install — don't assume otherwise)
+
+CodeRabbit runs as `coderabbitai[bot]` and posts **two independent things**, not one:
+
+1. An auto-generated **walkthrough/summary issue comment** — body starts with the HTML marker `<!-- This is an auto-generated comment: summarize by coderabbit.ai -->`. This is a description, not a review — use it for context only, never as a source of fixable findings.
+2. A **formal PR review** carrying one **inline review comment per finding**, each a real, resolvable GitHub review thread at the finding's file/line. Each one contains a `<details><summary>🤖 Prompt for AI Agents</summary>` block: a ready-made fix spec, CodeRabbit's own words, meant to be handed straight to an agent.
+
+**Use the inline threads as the source of truth**, exactly like Greptile/Qodo — fetch via GraphQL `reviewThreads`, which carries native `isResolved` state (see `references/graphql-queries.md`, shared with `qodoloop`; only the bot login and the prompt-heading text differ).
+
+CodeRabbit has slash commands (official, `docs.coderabbit.ai/reference/review-commands`) — the ones this loop actually uses:
+- `@coderabbitai review` — incremental review of new changes (use this to re-trigger after a push, if automatic review-on-push is off for this repo).
+- `@coderabbitai resolve` — marks **all** CodeRabbit threads resolved in one shot. This is a bulk escape hatch, not the default path: this loop resolves threads one at a time, right after replying to each, so the reply-then-resolve record stays intact per finding.
+- CodeRabbit also has its own built-in `@coderabbitai autofix`, which commits fixes directly without a model in the loop. Mention it to the user as an alternative if they'd rather skip the loop entirely, but this skill's whole point is the Claude-orchestrated version — don't default to autofix instead of doing the work.
+
+**Rate limit is a real terminal state, not a bug.** A comment reading "you've reached your PR review limit" (confirmed live wording) means CodeRabbit will not review again this cycle — stop and report it, don't loop waiting for something that isn't coming.
+
+## Instructions
+
+### 1. Identify the PR
+
+```bash
+gh pr view --json number,headRefName,headRefOid -q '{number, branch: .headRefName, sha: .headRefOid}'
+```
+
+Check out the branch if not already on it.
+
+### 2. Loop (max 5 iterations)
+
+#### A. Push and wait
+
+```bash
+git push
+```
+
+If this repo doesn't auto-review on push, nudge it:
+
+```bash
+gh pr comment <PR_NUMBER> --body "@coderabbitai review"
+```
+
+Poll (every ~10s, timeout ~5min) for CodeRabbit's next formal review to land — a new entry in `gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/reviews` from `coderabbitai[bot]` created after this push. If you instead see a rate-limit comment ("review limit"), **stop the loop now** and go to Report with `blocked: rate-limited`.
+
+#### B. Fetch unresolved findings
+
+Run the `unresolvedQodoThreads`-shaped query in `references/graphql-queries.md` (filter `author.login == "coderabbitai[bot]"` instead of Qodo's login). For each unresolved thread, parse the finding text and the **Prompt for AI Agents** block (heading text is `🤖 Prompt for AI Agents`, not `Agent Prompt` — match case/emoji-insensitively).
+
+#### C. Check exit conditions
+
+Stop if there are zero unresolved CodeRabbit threads, or max iterations reached.
+
+#### D. Fix each finding
+
+For each thread, in order: read the Prompt for AI Agents block in full — it names the issue and the fix. Apply it, staying inside its stated scope. If the suggestion is wrong, unsafe, or needs a product decision, don't force it — note that in step E instead.
+
+#### E. Answer and resolve
+
+**Reply to the thread first, then resolve it** — the "answer to the comments" half of the job:
+
+```bash
+gh api graphql -f query='mutation { addPullRequestReviewThreadReply(input: {pullRequestReviewThreadId: "<THREAD_ID>", body: "<REPLY>"}) { comment { id } } }'
+```
+
+Reply body: one or two sentences — what you changed and why, or exactly why you didn't fix it. Then resolve (`resolveReviewThread`). A finding you deliberately skip still gets a reply and gets resolved.
+
+#### F. Commit and push
+
+```bash
+git add -A
+git commit -m "address CodeRabbit review feedback (coderabbitloop iteration N)"
+git push
+```
+
+Go back to step A.
+
+### 3. Report
+
+| Field              | Value |
+|--------------------|-------|
+| Iterations         | N     |
+| Findings resolved  | N     |
+| Findings skipped   | N (with reasons) |
+| Remaining          | N (if any) |
+| Blocked            | rate-limited / max-iterations / none |
+
+```
+Coderabbitloop complete.
+  Iterations:  2
+  Resolved:    4 (3 fixed, 1 false-positive, replied + resolved)
+  Remaining:   0
+```
+
+## References
+
+- `references/graphql-queries.md` — shared with `qodoloop`: the exact `reviewThreads` query and the `resolveReviewThread` / `addPullRequestReviewThreadReply` mutations. Swap the author-login filter to `coderabbitai[bot]` and the prompt-heading match to `Prompt for AI Agents`.

package/.windsurf/rules/coderabbitloop.md

@@ -0,0 +1,108 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+description: "Iteratively drives a GitHub PR to zero unresolved CodeRabbit findings — reads each inline comment's own Prompt for AI Agents block, applies the fix, replies to the thread, resolves it, pushes, and re-triggers CodeRabbit."
+---
+
+# Coderabbitloop
+
+Fix every actionable CodeRabbit finding on a PR, answer each thread, resolve it, and keep going until CodeRabbit has nothing left to say (or a finding needs a human call).
+
+## Inputs
+
+- **PR number** (optional): detect from the current branch if not given.
+
+## How CodeRabbit actually posts (verified against docs.coderabbit.ai and a live install — don't assume otherwise)
+
+CodeRabbit runs as `coderabbitai[bot]` and posts **two independent things**, not one:
+
+1. An auto-generated **walkthrough/summary issue comment** — body starts with the HTML marker `<!-- This is an auto-generated comment: summarize by coderabbit.ai -->`. This is a description, not a review — use it for context only, never as a source of fixable findings.
+2. A **formal PR review** carrying one **inline review comment per finding**, each a real, resolvable GitHub review thread at the finding's file/line. Each one contains a `<details><summary>🤖 Prompt for AI Agents</summary>` block: a ready-made fix spec, CodeRabbit's own words, meant to be handed straight to an agent.
+
+**Use the inline threads as the source of truth**, exactly like Greptile/Qodo — fetch via GraphQL `reviewThreads`, which carries native `isResolved` state (see `references/graphql-queries.md`, shared with `qodoloop`; only the bot login and the prompt-heading text differ).
+
+CodeRabbit has slash commands (official, `docs.coderabbit.ai/reference/review-commands`) — the ones this loop actually uses:
+- `@coderabbitai review` — incremental review of new changes (use this to re-trigger after a push, if automatic review-on-push is off for this repo).
+- `@coderabbitai resolve` — marks **all** CodeRabbit threads resolved in one shot. This is a bulk escape hatch, not the default path: this loop resolves threads one at a time, right after replying to each, so the reply-then-resolve record stays intact per finding.
+- CodeRabbit also has its own built-in `@coderabbitai autofix`, which commits fixes directly without a model in the loop. Mention it to the user as an alternative if they'd rather skip the loop entirely, but this skill's whole point is the Claude-orchestrated version — don't default to autofix instead of doing the work.
+
+**Rate limit is a real terminal state, not a bug.** A comment reading "you've reached your PR review limit" (confirmed live wording) means CodeRabbit will not review again this cycle — stop and report it, don't loop waiting for something that isn't coming.
+
+## Instructions
+
+### 1. Identify the PR
+
+```bash
+gh pr view --json number,headRefName,headRefOid -q '{number, branch: .headRefName, sha: .headRefOid}'
+```
+
+Check out the branch if not already on it.
+
+### 2. Loop (max 5 iterations)
+
+#### A. Push and wait
+
+```bash
+git push
+```
+
+If this repo doesn't auto-review on push, nudge it:
+
+```bash
+gh pr comment <PR_NUMBER> --body "@coderabbitai review"
+```
+
+Poll (every ~10s, timeout ~5min) for CodeRabbit's next formal review to land — a new entry in `gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/reviews` from `coderabbitai[bot]` created after this push. If you instead see a rate-limit comment ("review limit"), **stop the loop now** and go to Report with `blocked: rate-limited`.
+
+#### B. Fetch unresolved findings
+
+Run the `unresolvedQodoThreads`-shaped query in `references/graphql-queries.md` (filter `author.login == "coderabbitai[bot]"` instead of Qodo's login). For each unresolved thread, parse the finding text and the **Prompt for AI Agents** block (heading text is `🤖 Prompt for AI Agents`, not `Agent Prompt` — match case/emoji-insensitively).
+
+#### C. Check exit conditions
+
+Stop if there are zero unresolved CodeRabbit threads, or max iterations reached.
+
+#### D. Fix each finding
+
+For each thread, in order: read the Prompt for AI Agents block in full — it names the issue and the fix. Apply it, staying inside its stated scope. If the suggestion is wrong, unsafe, or needs a product decision, don't force it — note that in step E instead.
+
+#### E. Answer and resolve
+
+**Reply to the thread first, then resolve it** — the "answer to the comments" half of the job:
+
+```bash
+gh api graphql -f query='mutation { addPullRequestReviewThreadReply(input: {pullRequestReviewThreadId: "<THREAD_ID>", body: "<REPLY>"}) { comment { id } } }'
+```
+
+Reply body: one or two sentences — what you changed and why, or exactly why you didn't fix it. Then resolve (`resolveReviewThread`). A finding you deliberately skip still gets a reply and gets resolved.
+
+#### F. Commit and push
+
+```bash
+git add -A
+git commit -m "address CodeRabbit review feedback (coderabbitloop iteration N)"
+git push
+```
+
+Go back to step A.
+
+### 3. Report
+
+| Field              | Value |
+|--------------------|-------|
+| Iterations         | N     |
+| Findings resolved  | N     |
+| Findings skipped   | N (with reasons) |
+| Remaining          | N (if any) |
+| Blocked            | rate-limited / max-iterations / none |
+
+```
+Coderabbitloop complete.
+  Iterations:  2
+  Resolved:    4 (3 fixed, 1 false-positive, replied + resolved)
+  Remaining:   0
+```
+
+## References
+
+- `references/graphql-queries.md` — shared with `qodoloop`: the exact `reviewThreads` query and the `resolveReviewThread` / `addPullRequestReviewThreadReply` mutations. Swap the author-login filter to `coderabbitai[bot]` and the prompt-heading match to `Prompt for AI Agents`.

package/README.md

@@ -136,7 +136,7 @@ packages/{category}/{skill}/SKILL.md
 
 </details>
 
-## All 25 Skills
+## All 26 Skills
 
 Each entry links to its `SKILL.md`. Reference any skill by its `olko:*` lookup name in a new agent session.
 
@@ -149,6 +149,7 @@ Each entry links to its `SKILL.md`. Reference any skill by its `olko:*` lookup n
 | [apple-store-submit](packages/software-development/apple-store-submit/SKILL.md) | Handles App Store rejection emails end-to-end — parses rejection reasons, creates a fix plan, implements code changes, and prepares resubmission | Responding to App Store rejections for privacy strings, entitlements, or guideline violations |
 | [changelog-generator](packages/software-development/changelog-generator/SKILL.md) | Transforms git commits into polished user-facing changelogs by categorising changes and rewriting technical commit messages | Preparing release notes, app store update descriptions, or a public changelog |
 | [cloudflare-block-countries](packages/software-development/cloudflare-block-countries/SKILL.md) | Blocks specific countries via Cloudflare WAF Custom Rules using the API | Geo-blocking traffic or setting up WAF country rules across single or multiple zones |
+| [coderabbitloop](packages/software-development/coderabbitloop/SKILL.md) | Iteratively drives a GitHub PR to zero unresolved CodeRabbit findings, reading each inline comment's own Prompt for AI Agents block, replying to the thread, and resolving it | Fully addressing a PR against CodeRabbit's review before merging |
 | [crash-course](packages/software-development/crash-course/SKILL.md) | Expert tutor for rapid, source-grounded learning of any topic: a timed 4-hour sprint plus cheat-sheet, learning-ladder, quiz-me, Feynman, and resource-curation modes | Ramping up on an unfamiliar codebase, project, or concept under time pressure |
 | [docs-index-keeper](packages/software-development/docs-index-keeper/SKILL.md) | Keeps a Markdown docs index in sync through pre-commit, CI, or one-off maintenance flows | A repo has `docs/` and needs `docs/README.md` updated automatically |
 | [gh-cli](packages/software-development/gh-cli/SKILL.md) | Guides GitHub CLI usage for repos, PRs, Actions, releases, issues, and all related GitHub operations | Working with GitHub from the command line and needing reliable `gh` commands |

package/catalog/skills.json

@@ -580,6 +580,30 @@
         "kiro",
         "grok"
       ]
+    },
+    {
+      "name": "coderabbitloop",
+      "lookupName": "olko:coderabbitloop",
+      "category": "software-development",
+      "path": "packages/software-development/coderabbitloop",
+      "description": "Iteratively drives a GitHub PR to zero unresolved CodeRabbit findings \u2014 reads each inline comment's own Prompt for AI Agents block, applies the fix, replies to the thread, resolves it, pushes, and re-triggers CodeRabbit.",
+      "tags": [
+        "code-review",
+        "coderabbit",
+        "github",
+        "pull-requests",
+        "automation",
+        "agents"
+      ],
+      "adapters": [
+        "claude",
+        "codex",
+        "cursor",
+        "copilot",
+        "grok",
+        "windsurf",
+        "kiro"
+      ]
     }
   ]
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@olegkoval/agent-skills",
-  "version": "1.20.0",
+  "version": "1.21.0",
   "private": false,
   "publishConfig": {
     "access": "public"

package/packages/software-development/coderabbitloop/SKILL.md

@@ -0,0 +1,117 @@
+---
+name: coderabbitloop
+description: >
+  Iteratively drives a GitHub PR to zero unresolved CodeRabbit (coderabbitai[bot]) findings. Reads
+  each inline comment's own "Prompt for AI Agents" block (CodeRabbit's ready-made fix spec per
+  issue), applies the fix, replies to the thread explaining what was done, resolves it, pushes, and
+  re-triggers CodeRabbit. Repeats until clean or a real blocker needs a human. Use when the user
+  wants a PR fully addressed against CodeRabbit's review, or says "run coderabbitloop" / "satisfy
+  CodeRabbit" / "resolve CodeRabbit comments".
+compatibility: Requires git and gh (GitHub CLI) authenticated, with the CodeRabbit GitHub App installed on the repo.
+metadata:
+  version: "1.0"
+allowed-tools: Bash(gh:*) Bash(git:*)
+---
+
+# Coderabbitloop
+
+Fix every actionable CodeRabbit finding on a PR, answer each thread, resolve it, and keep going until CodeRabbit has nothing left to say (or a finding needs a human call).
+
+## Inputs
+
+- **PR number** (optional): detect from the current branch if not given.
+
+## How CodeRabbit actually posts (verified against docs.coderabbit.ai and a live install — don't assume otherwise)
+
+CodeRabbit runs as `coderabbitai[bot]` and posts **two independent things**, not one:
+
+1. An auto-generated **walkthrough/summary issue comment** — body starts with the HTML marker `<!-- This is an auto-generated comment: summarize by coderabbit.ai -->`. This is a description, not a review — use it for context only, never as a source of fixable findings.
+2. A **formal PR review** carrying one **inline review comment per finding**, each a real, resolvable GitHub review thread at the finding's file/line. Each one contains a `<details><summary>🤖 Prompt for AI Agents</summary>` block: a ready-made fix spec, CodeRabbit's own words, meant to be handed straight to an agent.
+
+**Use the inline threads as the source of truth**, exactly like Greptile/Qodo — fetch via GraphQL `reviewThreads`, which carries native `isResolved` state (see `references/graphql-queries.md`, shared with `qodoloop`; only the bot login and the prompt-heading text differ).
+
+CodeRabbit has slash commands (official, `docs.coderabbit.ai/reference/review-commands`) — the ones this loop actually uses:
+- `@coderabbitai review` — incremental review of new changes (use this to re-trigger after a push, if automatic review-on-push is off for this repo).
+- `@coderabbitai resolve` — marks **all** CodeRabbit threads resolved in one shot. This is a bulk escape hatch, not the default path: this loop resolves threads one at a time, right after replying to each, so the reply-then-resolve record stays intact per finding.
+- CodeRabbit also has its own built-in `@coderabbitai autofix`, which commits fixes directly without a model in the loop. Mention it to the user as an alternative if they'd rather skip the loop entirely, but this skill's whole point is the Claude-orchestrated version — don't default to autofix instead of doing the work.
+
+**Rate limit is a real terminal state, not a bug.** A comment reading "you've reached your PR review limit" (confirmed live wording) means CodeRabbit will not review again this cycle — stop and report it, don't loop waiting for something that isn't coming.
+
+## Instructions
+
+### 1. Identify the PR
+
+```bash
+gh pr view --json number,headRefName,headRefOid -q '{number, branch: .headRefName, sha: .headRefOid}'
+```
+
+Check out the branch if not already on it.
+
+### 2. Loop (max 5 iterations)
+
+#### A. Push and wait
+
+```bash
+git push
+```
+
+If this repo doesn't auto-review on push, nudge it:
+
+```bash
+gh pr comment <PR_NUMBER> --body "@coderabbitai review"
+```
+
+Poll (every ~10s, timeout ~5min) for CodeRabbit's next formal review to land — a new entry in `gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/reviews` from `coderabbitai[bot]` created after this push. If you instead see a rate-limit comment ("review limit"), **stop the loop now** and go to Report with `blocked: rate-limited`.
+
+#### B. Fetch unresolved findings
+
+Run the `unresolvedQodoThreads`-shaped query in `references/graphql-queries.md` (filter `author.login == "coderabbitai[bot]"` instead of Qodo's login). For each unresolved thread, parse the finding text and the **Prompt for AI Agents** block (heading text is `🤖 Prompt for AI Agents`, not `Agent Prompt` — match case/emoji-insensitively).
+
+#### C. Check exit conditions
+
+Stop if there are zero unresolved CodeRabbit threads, or max iterations reached.
+
+#### D. Fix each finding
+
+For each thread, in order: read the Prompt for AI Agents block in full — it names the issue and the fix. Apply it, staying inside its stated scope. If the suggestion is wrong, unsafe, or needs a product decision, don't force it — note that in step E instead.
+
+#### E. Answer and resolve
+
+**Reply to the thread first, then resolve it** — the "answer to the comments" half of the job:
+
+```bash
+gh api graphql -f query='mutation { addPullRequestReviewThreadReply(input: {pullRequestReviewThreadId: "<THREAD_ID>", body: "<REPLY>"}) { comment { id } } }'
+```
+
+Reply body: one or two sentences — what you changed and why, or exactly why you didn't fix it. Then resolve (`resolveReviewThread`). A finding you deliberately skip still gets a reply and gets resolved.
+
+#### F. Commit and push
+
+```bash
+git add -A
+git commit -m "address CodeRabbit review feedback (coderabbitloop iteration N)"
+git push
+```
+
+Go back to step A.
+
+### 3. Report
+
+| Field              | Value |
+|--------------------|-------|
+| Iterations         | N     |
+| Findings resolved  | N     |
+| Findings skipped   | N (with reasons) |
+| Remaining          | N (if any) |
+| Blocked            | rate-limited / max-iterations / none |
+
+```
+Coderabbitloop complete.
+  Iterations:  2
+  Resolved:    4 (3 fixed, 1 false-positive, replied + resolved)
+  Remaining:   0
+```
+
+## References
+
+- `references/graphql-queries.md` — shared with `qodoloop`: the exact `reviewThreads` query and the `resolveReviewThread` / `addPullRequestReviewThreadReply` mutations. Swap the author-login filter to `coderabbitai[bot]` and the prompt-heading match to `Prompt for AI Agents`.

package/packages/software-development/coderabbitloop/adapters/claude/plugin.json

@@ -0,0 +1,5 @@
+{
+  "name": "olko-coderabbitloop",
+  "description": "Iteratively drives a GitHub PR to zero unresolved CodeRabbit findings — reads each inline comment's own Prompt for AI Agents block, applies the fix, replies to the thread, resolves it, pushes, and re-triggers CodeRabbit.",
+  "skills": "./skills"
+}

package/packages/software-development/coderabbitloop/adapters/claude/skills/coderabbitloop/SKILL.md

@@ -0,0 +1,118 @@
+---
+name: coderabbitloop
+description: >
+  Iteratively drives a GitHub PR to zero unresolved CodeRabbit (coderabbitai[bot]) findings. Reads
+  each inline comment's own "Prompt for AI Agents" block (CodeRabbit's ready-made fix spec per
+  issue), applies the fix, replies to the thread explaining what was done, resolves it, pushes, and
+  re-triggers CodeRabbit. Repeats until clean or a real blocker needs a human. Use when the user
+  wants a PR fully addressed against CodeRabbit's review, or says "run coderabbitloop" / "satisfy
+  CodeRabbit" / "resolve CodeRabbit comments".
+compatibility: Requires git and gh (GitHub CLI) authenticated, with the CodeRabbit GitHub App installed on the repo.
+metadata:
+  version: "1.0"
+allowed-tools: Bash(gh:*) Bash(git:*)
+---
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+# Coderabbitloop
+
+Fix every actionable CodeRabbit finding on a PR, answer each thread, resolve it, and keep going until CodeRabbit has nothing left to say (or a finding needs a human call).
+
+## Inputs
+
+- **PR number** (optional): detect from the current branch if not given.
+
+## How CodeRabbit actually posts (verified against docs.coderabbit.ai and a live install — don't assume otherwise)
+
+CodeRabbit runs as `coderabbitai[bot]` and posts **two independent things**, not one:
+
+1. An auto-generated **walkthrough/summary issue comment** — body starts with the HTML marker `<!-- This is an auto-generated comment: summarize by coderabbit.ai -->`. This is a description, not a review — use it for context only, never as a source of fixable findings.
+2. A **formal PR review** carrying one **inline review comment per finding**, each a real, resolvable GitHub review thread at the finding's file/line. Each one contains a `<details><summary>🤖 Prompt for AI Agents</summary>` block: a ready-made fix spec, CodeRabbit's own words, meant to be handed straight to an agent.
+
+**Use the inline threads as the source of truth**, exactly like Greptile/Qodo — fetch via GraphQL `reviewThreads`, which carries native `isResolved` state (see `references/graphql-queries.md`, shared with `qodoloop`; only the bot login and the prompt-heading text differ).
+
+CodeRabbit has slash commands (official, `docs.coderabbit.ai/reference/review-commands`) — the ones this loop actually uses:
+- `@coderabbitai review` — incremental review of new changes (use this to re-trigger after a push, if automatic review-on-push is off for this repo).
+- `@coderabbitai resolve` — marks **all** CodeRabbit threads resolved in one shot. This is a bulk escape hatch, not the default path: this loop resolves threads one at a time, right after replying to each, so the reply-then-resolve record stays intact per finding.
+- CodeRabbit also has its own built-in `@coderabbitai autofix`, which commits fixes directly without a model in the loop. Mention it to the user as an alternative if they'd rather skip the loop entirely, but this skill's whole point is the Claude-orchestrated version — don't default to autofix instead of doing the work.
+
+**Rate limit is a real terminal state, not a bug.** A comment reading "you've reached your PR review limit" (confirmed live wording) means CodeRabbit will not review again this cycle — stop and report it, don't loop waiting for something that isn't coming.
+
+## Instructions
+
+### 1. Identify the PR
+
+```bash
+gh pr view --json number,headRefName,headRefOid -q '{number, branch: .headRefName, sha: .headRefOid}'
+```
+
+Check out the branch if not already on it.
+
+### 2. Loop (max 5 iterations)
+
+#### A. Push and wait
+
+```bash
+git push
+```
+
+If this repo doesn't auto-review on push, nudge it:
+
+```bash
+gh pr comment <PR_NUMBER> --body "@coderabbitai review"
+```
+
+Poll (every ~10s, timeout ~5min) for CodeRabbit's next formal review to land — a new entry in `gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/reviews` from `coderabbitai[bot]` created after this push. If you instead see a rate-limit comment ("review limit"), **stop the loop now** and go to Report with `blocked: rate-limited`.
+
+#### B. Fetch unresolved findings
+
+Run the `unresolvedQodoThreads`-shaped query in `references/graphql-queries.md` (filter `author.login == "coderabbitai[bot]"` instead of Qodo's login). For each unresolved thread, parse the finding text and the **Prompt for AI Agents** block (heading text is `🤖 Prompt for AI Agents`, not `Agent Prompt` — match case/emoji-insensitively).
+
+#### C. Check exit conditions
+
+Stop if there are zero unresolved CodeRabbit threads, or max iterations reached.
+
+#### D. Fix each finding
+
+For each thread, in order: read the Prompt for AI Agents block in full — it names the issue and the fix. Apply it, staying inside its stated scope. If the suggestion is wrong, unsafe, or needs a product decision, don't force it — note that in step E instead.
+
+#### E. Answer and resolve
+
+**Reply to the thread first, then resolve it** — the "answer to the comments" half of the job:
+
+```bash
+gh api graphql -f query='mutation { addPullRequestReviewThreadReply(input: {pullRequestReviewThreadId: "<THREAD_ID>", body: "<REPLY>"}) { comment { id } } }'
+```
+
+Reply body: one or two sentences — what you changed and why, or exactly why you didn't fix it. Then resolve (`resolveReviewThread`). A finding you deliberately skip still gets a reply and gets resolved.
+
+#### F. Commit and push
+
+```bash
+git add -A
+git commit -m "address CodeRabbit review feedback (coderabbitloop iteration N)"
+git push
+```
+
+Go back to step A.
+
+### 3. Report
+
+| Field              | Value |
+|--------------------|-------|
+| Iterations         | N     |
+| Findings resolved  | N     |
+| Findings skipped   | N (with reasons) |
+| Remaining          | N (if any) |
+| Blocked            | rate-limited / max-iterations / none |
+
+```
+Coderabbitloop complete.
+  Iterations:  2
+  Resolved:    4 (3 fixed, 1 false-positive, replied + resolved)
+  Remaining:   0
+```
+
+## References
+
+- `references/graphql-queries.md` — shared with `qodoloop`: the exact `reviewThreads` query and the `resolveReviewThread` / `addPullRequestReviewThreadReply` mutations. Swap the author-login filter to `coderabbitai[bot]` and the prompt-heading match to `Prompt for AI Agents`.