A project-memory command that reviews the 100 most recently merged pull requests, which are proposed code changes accepted into the repository, and extracts lasting decisions and conventions.

Use it to capture architectural facts, coding conventions, recurring problems, and other useful lessons in project memory.

It reduces the need to rediscover important context from old discussions, code reviews, and change descriptions.

enrich — Command for Claude Code by RashadAnsari

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.

Clone the repo

git clone --depth 1 https://github.com/RashadAnsari/myagents

Made for: Claude Code.

Or install albino, the plugin that ships this one along with the rest of its 8 skills, 10 commands, 14 agents, 3 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/rashadansari/myagents/enrich.svg)](https://agentmods.dev/commands/rashadansari/myagents/enrich)

Your own site

<a href="https://agentmods.dev/commands/rashadansari/myagents/enrich"><img src="https://agentmods.dev/badge/commands/rashadansari/myagents/enrich.svg" alt="Measured on agentmods" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,739 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.01739
Opus 5	$0.00017	$0.00870
Sonnet 5	$0.00007	$0.00348
Haiku 4.5	$0.00003	$0.00174

Measured 8d ago against content hash 10c7af565506, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

enrich 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 8d 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.

plugins/albino/commands/enrich.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Enrichment

Mine the 100 most recently merged PRs in the current repository. Extract durable learnings from PR bodies, review discussions, and comments. Write what is genuinely non-obvious and useful to project memory.

Step 1: Validate Environment

Run all three in parallel:

gh auth status

git rev-parse --show-toplevel

gh repo view --json nameWithOwner --jq '.nameWithOwner'

Store PROJECT_ROOT (from git rev-parse) and REPO (e.g. owner/repo). If gh is not authenticated, tell the user to run gh auth login and stop.

Step 2: Load Existing Memory

Call project_search with these two queries in parallel to understand what is already captured:

"architecture decision convention pattern"
"gotcha bug workflow dependency"

Combine results into EXISTING_MEMORY_SUMMARY: a compact list of summaries already stored. Extractor agents will use this to avoid rediscovering what is already known.

Step 3: Fetch Merged PR List

gh pr list --repo {REPO} --state merged --limit 100 \
  --json number,title,mergedAt,comments,reviews \
  --jq 'sort_by((.comments | length) + (.reviews | length)) | reverse | [.[] | {number: .number, title: .title}]'

Store as PR_LIST. Sort puts high-discussion PRs first to maximize signal in the analysis. If the repo has fewer than 100 merged PRs, proceed with however many exist. If there are no merged PRs, tell the user and stop.

Extract just the number field from each element so you have a flat array PR_NUMBERS like [101, 99, 88, ...].

Step 4: Split Into Batches and Spawn Extractor Agents

Divide PR_NUMBERS into batches of 10 (up to 10 batches total). Spawn all batches simultaneously. Do not wait for one to finish before starting the next.

Each extractor agent receives:

REPO: the owner/repo string
BATCH: a list of 10 PR numbers
EXISTING_MEMORY_SUMMARY: the summary from Step 2

Use this prompt for every extractor agent (substituting values):

Read the full file on GitHub · 184 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.

8d ago First seen · 184 lines · 34 tokens per session scan A 10c7af565506

Subscribe to this mod's changes

enrich is a command published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,739 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.

Claude Code Memory and context agents claude-desktop codex cursor plugins

context-restore

Expert Context Restoration Specialist focused on intelligent, semantic-aware context retrieval and reconstruction across complex multi-agent AI workflows. Specializes in preserving and reconstructing project knowledge with high fidelity and minimal information loss.

wshobson/agents · 0 tokens

context-save

An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation across AI workflows. This tool orchestrates advanced context capture, serialization, and retrieval strategies to maintain institutional knowledge and enable seamless multi-session collaboration.