rem

rem is a skill for Claude Code from jameslowman/planning-with-james. It costs 39 tokens per session (11,721 once invoked), scanned A, original, MIT.

A maintenance routine for the planning plugin’s stored plans, notes, lessons, and code knowledge. It removes or combines old information and records patterns found in the repository.

In plain words
What is it for?
Use it to archive completed or abandoned plans, merge repeated notes, update stale code knowledge, and review exploratory files for useful patterns.
Why use it?
Planning records can become slow to load, difficult to search, and inaccurate as a project changes. This routine keeps accumulated information smaller and more current.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Part of the planning-with-james plugin — 7 skills, 2 hooks shipped together

Good fit Use it to archive completed or abandoned plans, merge repeated notes, update stale code knowledge, and review exploratory files for useful patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jameslowman/planning-with-james/rem
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 jameslowman/planning-with-james --skill rem
Clone the repo
git clone --depth 1 https://github.com/jameslowman/planning-with-james

Made for: Claude Code.

Or install planning-with-james, the plugin that ships this one along with the rest of its 7 skills, 2 hooks.

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 rem

README.md
[![agentmods](https://agentmods.dev/badge/skills/jameslowman/planning-with-james/rem.svg)](https://agentmods.dev/skills/jameslowman/planning-with-james/rem)
Your own site
<a href="https://agentmods.dev/skills/jameslowman/planning-with-james/rem"><img src="https://agentmods.dev/badge/skills/jameslowman/planning-with-james/rem.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,721 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.11721
Opus 5 $0.00019 $0.05861
Sonnet 5 $0.00008 $0.02344
Haiku 4.5 $0.00004 $0.01172

Measured 8d ago against content hash f8798856bbec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rem 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.

skills/rem/SKILL.md · 1,237 lines

How it starts

The opening of the file, as written. The whole thing — 1,237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

REM: Sleep-Cycle Maintenance

The planning plugin accumulates weight over time: completed plans linger in the registry, lessons pile up without curation, knowledge graph modules describe code that has since evolved, /dig explorations pile up, abandoned progress files hang around. Left alone, planning-with-james becomes slow to load, noisy to search, and quietly inaccurate.

/rem fixes this by running a sleep cycle: triage, prune, consolidate, dream. It mimics what a brain does overnight — archives the obvious dead weight, merges redundant memories, promotes things that got forgotten, and wanders the repo looking for patterns and weirdness the plugin didn't notice during working hours.

The main goal is consolidation — keep the plugin heavyweight in capability, light on its feet in operation. Dreams are a bonus: speculative notes and action items the user can act on during planning.


NON-NEGOTIABLES

1. ALL PATHS ARE RELATIVE TO THE REPO ROOT. All .claude/planning-with-james/ paths in this skill are relative to the current working directory, NOT ~/.claude/. Run pwd if unsure.

2. PROGRESS TRACKING. After each phase completes, update _rem_progress.json BEFORE starting the next. This enables resume after autocompact.

3. AGENT PERMISSIONS. Every Task agent spawn MUST include mode: "bypassPermissions". Background agents without this mode have Write/Edit calls silently denied, burning turns with no output.

4. NO BASH FOR FILE MODIFICATIONS. Use Read → Edit or Read → Write for all file changes. No sed, awk, echo redirection, heredocs, or for loops that write files. Bash is only for git, mv (archive operations), and project tools. This applies to orchestrator AND subagents — include this rule in every subagent prompt.

5. REM NEVER WRITES TO knowledge/modules/. The knowledge graph is owned by create-knowledge and update-knowledge. When rem detects stale or shallow knowledge, it creates an action item recommending /planning-with-james:update-knowledge guided with specific context. It does not edit the module docs.

Read the full file on GitHub · 1,237 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. 8d ago First seen · 1,237 lines · 39 tokens per session scan A f8798856bbec

Subscribe to this mod's changes

rem is a skill published in the GitHub repository jameslowman/planning-with-james (2 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 11,721 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens