pr-review-subscribe

pr-review-subscribe is a skill for Claude Code, Codex from scottlz0310/mcp-resource-subscriber. It costs 118 tokens per session (7,676 once invoked), scanned A, original, MIT.

A workflow for collecting and handling review comments on GitHub pull requests, which are proposed code changes. It supports comments from automated reviewers, Codex, people, or existing review threads.

In plain words
What is it for?
Running a pull-request review cycle from comment collection through fixes, replies, and resolution.
Why use it?
It gives different review sources one consistent process for finding comments, fixing code, replying, and resolving threads.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md; mentions Codex.

Good fit Running a pull-request review cycle from comment collection through fixes, replies, and resolution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/scottlz0310/mcp-resource-subscriber/pr-review-subscribe
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.

Any agent
npx skills add scottlz0310/mcp-resource-subscriber --skill pr-review-subscribe
Clone the repo
git clone --depth 1 https://github.com/scottlz0310/mcp-resource-subscriber

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pr-review-subscribe

README.md
[![agentmods](https://agentmods.dev/badge/skills/scottlz0310/mcp-resource-subscriber/pr-review-subscribe/github.svg)](https://agentmods.dev/skills/scottlz0310/mcp-resource-subscriber/pr-review-subscribe)
Your own site
<a href="https://agentmods.dev/skills/scottlz0310/mcp-resource-subscriber/pr-review-subscribe"><img src="https://agentmods.dev/badge/skills/scottlz0310/mcp-resource-subscriber/pr-review-subscribe/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.

agentmods 80×15 button for pr-review-subscribe

Your own site · 80×15
<a href="https://agentmods.dev/skills/scottlz0310/mcp-resource-subscriber/pr-review-subscribe"><img src="https://agentmods.dev/badge/skills/scottlz0310/mcp-resource-subscriber/pr-review-subscribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,676 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.07676
Opus 5 $0.00059 $0.03838
Sonnet 5 $0.00024 $0.01535
Haiku 4.5 $0.00012 $0.00768

Measured 10d ago against content hash 12dc14881e3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-review-subscribe scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`mcp-gateway` must be running. Verify with `curl -s http://127.0.0.1:8080/health` or
docs/skills/pr-review-subscribe/SKILL.md · 790 lines

How it starts

The opening of the file, as written. The whole thing — 790 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pr-review-subscribe

PR review cycle with provider abstraction: review acquisition and thread processing are separate concerns.

provider = auto | copilot-review | codex | external | existing

Review acquisition (provider-specific):
  copilot-review → Phase 1S (watch/subscribe/complete)
  codex          → Phase W  (post @codex review comment, wait)
  external/human → Phase W  (wait for user signal)
  existing       → skip directly to Phase U1

Unified Review Thread Handling (all providers):
  Phase U1 → Phase U2 → Phase 3 → Phase 4 → Phase U5 → Phase U6

If server/tool names differ, load references/tool-template.md and map placeholders before starting.

Required Surfaces

Placeholder Purpose When used
{CRM} Copilot review MCP tools: review status, request, watch start/cancel copilot-review acquisition only
{GH} GitHub issue/PR comment tools All providers
{RSRC} MCP resource operations: subscribe/read/unsubscribe or SDK wrapper copilot-review acquisition only

copilot-review acquisition minimum operations:

  • {CRM}:get_copilot_review_status
  • {CRM}:request_copilot_review
  • {CRM}:start_copilot_review_watch
  • {CRM}:cancel_copilot_review_watch
  • {CRM}:get_copilot_review_watch_status (fallback polling only)
  • {RSRC}:resources/subscribe equivalent for the watch resource
  • {RSRC}:resources/read equivalent for the watch resource
  • {RSRC}:resources/unsubscribe equivalent for the watch resource

Unified thread handling minimum operations (all providers):

  • gh CLI (for gh api GraphQL and REST calls)
  • {GH}:add_reply_to_pull_request_comment (map actual name via references/tool-template.md)
  • {GH}:add_issue_comment (for PR summary comment and re-review requests)
  • {GH}:create_issue (for follow-up issue tracking)

Flow

Phase 0: provider selection
  |
  +--> existing threads detected --------> Phase U1
  |
  +--> copilot-review --> Phase 1S -------> Phase U1
  |
  +--> codex/external --> Phase W ---------> Phase U1 (on user signal)

Phase U1 -> Phase U2 -> Phase 3 -> Phase 4 -> Phase U5 -> Phase U6
                                                             |
                        READY_TO_MERGE <-------- unresolved=0
                             |
                   Phase 6.5 -> Phase 6.6 -> Phase 7 -> Phase 8

Phase U6 re-review policy:
  copilot-review  → structured: Phase 1S loop (max cycles)
  codex/external  → message-based: post comment → WAITING_FOR_REVIEW → stop
  (on ESCALATE or max cycles exceeded → Phase 6.5)

Phase 1S detail (copilot-review acquisition):
  1S-A: Start Watch
  1S-B: Native resources/subscribe  --> success: wait for notification
         |
         | unavailable or failed
         v
  1S-B2: SDK Wrapper subscription   --> success: run wrapper, wait for output
         |
         | not found or failed
         v
  1S-C: Fallback Polling            (last resort only)

Read the full file on GitHub · 790 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 10d ago First seen · 790 lines · 118 tokens per session scan A 12dc14881e3d

Subscribe to this mod's changes

pr-review-subscribe is a skill published in the GitHub repository scottlz0310/mcp-resource-subscriber (0 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 7,676 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.