cocosearch-review-pr

cocosearch-review-pr is a skill for Claude Code from VioletCranberry/coco-search. It costs 68 tokens per session (9,356 once invoked), scanned A, original, MIT.

A workflow for reviewing a GitHub pull request or GitLab merge request with codebase-wide analysis. It examines how changed files affect other code, dependencies, coding patterns, and tests.

In plain words
What is it for?
Use it to assess a PR or MR's broader impact, find affected code, compare implementation patterns, check tests, identify missing changes, and optionally prepare inline review comments.
Why use it?
It reveals problems that may not be visible in the changed lines alone, such as missing related edits or missing test coverage. Reviews are read-only unless you approve posting comments.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cocosearch plugin — 12 skills shipped together

Good fit Use it to assess a PR or MR's broader impact, find affected code, compare implementation patterns, check tests, identify missing changes, and optionally prepare inline review comments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/violetcranberry/coco-search/cocosearch-review-pr
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 VioletCranberry/coco-search --skill cocosearch-review-pr
Clone the repo
git clone --depth 1 https://github.com/VioletCranberry/coco-search

Made for: Claude Code.

Or install cocosearch, the plugin that ships this one along with the rest of its 12 skills.

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 cocosearch-review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-review-pr/github.svg)](https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-review-pr)
Your own site
<a href="https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-review-pr"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-review-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.

agentmods 80×15 button for cocosearch-review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-review-pr"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,356 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 8 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 58
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
  • medium Excessive Agency · line 19
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Data Exfiltration · line 90
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 121
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 131
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 167
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 717
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Excessive Agency · line 337
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00068 $0.09356
Opus 5 $0.00034 $0.04678
Sonnet 5 $0.00014 $0.01871
Haiku 4.5 $0.00007 $0.00936

Measured 11d ago against content hash aba87699c65b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cocosearch-review-pr 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 11d 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.

> **Important:** Use the Python `urllib` / `curl` snippets provided below for all API calls. Do NOT use `gh`, `glab`, or other CLI wrappers -- they may not be installed and add an unnecessary dependency.
skills/cocosearch-review-pr/SKILL.md · 870 lines

How it starts

The opening of the file, as written. The whole thing — 870 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR/MR Review with CocoSearch

A structured workflow for reviewing pull requests (GitHub) or merge requests (GitLab) using CocoSearch's semantic search and dependency analysis. Goes beyond line-by-line diff reading to assess blast radius, dependency impact, pattern consistency, and test coverage.

Read-only by default. The review itself only reads the PR/MR and the codebase. The final step (Step 6) is an optional, confirmation-gated write-back that posts findings as inline comments on the lines that need changes plus an overall summary — nothing is posted without an explicit dry-run preview and your approval.

What this skill adds over manual review:

  • Blast radius: For each changed file, see what else in the codebase depends on it
  • Dependency context: Understand what the changed code relies on
  • Pattern consistency: Find similar patterns elsewhere to check if changes are consistent
  • Test coverage: Verify that tests exist for the changed code
  • Missing changes: Identify files that should have changed but didn't
  • Push back (optional): After review, post findings as inline GitHub/GitLab comments on the exact lines — interactive, comment-only, never auto-approves

Pre-flight Check

  1. Resolve index name (use the resolved name for all operations):

    • Try cocosearch.yaml for indexName field -- if found, use it
    • If no config file, call list_indexes() and match the current project's directory name against available indexes. The MCP tools auto-derive index names from directory paths (e.g., my-project/ -> my_project), so a match is likely if the repo was indexed without a config file.
    • If no match found, the project is genuinely not indexed -- offer to index it. Do NOT abandon CocoSearch tools just because cocosearch.yaml is missing.
  2. Inventory API tokens. Check which tokens are available before anything else:

    python3 -c "
    import os
    tokens = {
        'GITHUB_TOKEN': bool(os.environ.get('GITHUB_TOKEN')),
        'GH_TOKEN': bool(os.environ.get('GH_TOKEN')),
        'GITLAB_TOKEN': bool(os.environ.get('GITLAB_TOKEN')),
        'GITLAB_PAT': bool(os.environ.get('GITLAB_PAT')),
    }
    found = [k for k, v in tokens.items() if v]
    print(f'Available tokens: {found if found else \"none\"}')"
    

Read the full file on GitHub · 870 lines

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. 11d ago First seen · 870 lines · 68 tokens per session scan A aba87699c65b

Subscribe to this mod's changes

cocosearch-review-pr is a skill published in the GitHub repository VioletCranberry/coco-search (37 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 9,356 once invoked, about $0.0003 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 2026-08-30.