receive

receive is a command for coding agents from juanmhidalgo/claude-plugins. It costs 38 tokens per session (861 once invoked), scanned A, original, MIT.

A command for processing code-review findings pasted from another session. It treats the review as advice that must be checked against the current code before any fix is made.

In plain words
What is it for?
Use it to extract findings, check their files and line numbers, assess their severity and category, and decide which verified issues should be fixed.
Why use it?
Review reports can refer to changed files, misunderstand the project, or identify issues that are not technically real.

Command

Part of the code-review plugin — 5 skills, 14 commands, 13 agents shipped together

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/juanmhidalgo/claude-plugins/receive
Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Or install code-review, the plugin that ships this one along with the rest of its 5 skills, 14 commands, 13 agents.

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 receive

README.md
[![agentmods](https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/receive.svg)](https://agentmods.dev/commands/juanmhidalgo/claude-plugins/receive)
Your own site
<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/receive"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/receive.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 861 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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00861
Opus 5 $0.00019 $0.00430
Sonnet 5 $0.00008 $0.00172
Haiku 4.5 $0.00004 $0.00086

Measured 5d ago against content hash b84377e66fa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

receive 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 5d 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.

code-review/commands/receive.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Receive Code Review

Process code review feedback from another session. The review is external analysis, not a source of truth — findings may reference stale code, misunderstand context, or flag non-issues.

Review Content

$ARGUMENTS


Protocol

Follow these phases in order. Do NOT skip to implementation.

Phase 1: Parse Findings

Extract each finding from the review report:

  • File path and line numbers
  • Severity (CRITICAL / HIGH / MEDIUM / LOW)
  • Category (security, performance, bug, code quality, etc.)
  • Description of the issue
  • Suggested fix (if provided)

If the review format is unclear or unstructured, do your best to identify individual findings.

Phase 2: Verify Against Actual Code

For each finding, read the referenced file and check:

Check How
File and line still match Read the file, compare to what the review references
Issue still exists Code may have changed since the review ran
Finding is technically correct The reviewer (even AI) can be wrong
Context was understood Check surrounding code the reviewer may not have seen
Aligns with project conventions Check CLAUDE.md and existing patterns

Classify each finding:

  • CONFIRMED — issue exists and finding is correct
  • STALE — code has changed, finding no longer applies
  • INCORRECT — finding misunderstands the code or is technically wrong
  • DISPUTED — finding is debatable, needs user input

Phase 3: Present Verified Results

Enter plan mode using the EnterPlanMode tool.

Present findings grouped by status:

## Verified Review Findings

### Confirmed (X findings)
For each: severity, file:line, issue summary, suggested action

### Disputed (X findings)
For each: what the review says vs what the code actually does, your assessment

### Rejected (X findings)
For each: brief reason (stale / incorrect / non-issue)

Read the full file on GitHub · 123 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. 5d ago First seen · 123 lines · 38 tokens per session scan A b84377e66fa6

Subscribe to this mod's changes

receive is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 10d ago), licensed MIT. It adds 38 tokens to every session and 861 once invoked, about $0.0002 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.