craft-project-remember

craft-project-remember is a skill for Claude Code, Codex from derjochenmeyer/claude-code-craft. It costs 32 tokens per session (1,012 once invoked), scanned A, original, MIT.

A project-memory helper that saves useful facts, decisions, lessons, and context in structured files for later sessions.

In plain words
What is it for?
Use it to record a technical fact, a chosen approach and its reason, a reusable lesson, or other context the project should remember.
Why use it?
It prevents important information from being lost between sessions and keeps future work from repeating the same investigation.

Skill for Claude CodeCodex

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 skills/derjochenmeyer/claude-code-craft/craft-project-remember
Any agent
npx skills add derjochenmeyer/claude-code-craft --skill craft-project-remember
Clone the repo
git clone --depth 1 https://github.com/derjochenmeyer/claude-code-craft

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 craft-project-remember

README.md
[![agentmods](https://agentmods.dev/badge/skills/derjochenmeyer/claude-code-craft/craft-project-remember.svg)](https://agentmods.dev/skills/derjochenmeyer/claude-code-craft/craft-project-remember)
Your own site
<a href="https://agentmods.dev/skills/derjochenmeyer/claude-code-craft/craft-project-remember"><img src="https://agentmods.dev/badge/skills/derjochenmeyer/claude-code-craft/craft-project-remember.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,012 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 $0.00032 $0.01012
Opus 5 $0.00016 $0.00506
Sonnet 5 $0.00006 $0.00202
Haiku 4.5 $0.00003 $0.00101

Measured 3d ago against content hash 533903d2f322, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

craft-project-remember 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 3d 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/craft-project-remember/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

craft-project-remember

Save something to project memory so future sessions can use it.

Invocation

  • /craft-project-remember -- Claude picks the most valuable insight from the current context
  • /craft-project-remember [what] -- saves exactly what was specified

Memory structure

Target directory: .craft/memory/ in the current working directory.

.craft/memory/
  INDEX.md              index of all entries (one line per entry)
  learned-rules.md      lessons with L001 numbering (read by session-start hook)
  YYYYMMDD_slug.md      individual memory files

If .craft/memory/ does not exist: create it, create an empty MEMORY_INDEX.md, create an empty learned-rules.md.

Step 1: Determine what to save

If no argument was given: review the current conversation context and identify the most valuable non-obvious information. Prioritize: decisions > lessons > facts > context.

If an argument was given: use it as the content, enrich with context from the conversation if helpful.

Step 2: Classify

Type When to use
fact Technical or domain knowledge not in the code itself
decision A choice with rationale (why not the alternative?)
lesson Something learned from a mistake, correction, or unexpected behavior
context Background information future sessions might need
warning Something easy to get wrong, with explanation

Step 3: Check for duplicates

Read MEMORY_INDEX.md. If a similar entry already exists (same topic, overlapping keywords): update the existing file instead of creating a new one.

Step 4: Write the memory file

Filename: YYYYMMDD_slug.md -- today's date, slug derived from the title (lowercase, spaces to hyphens, max 40 characters).

Format:

---
title: [short title]
type: [fact | decision | lesson | context | warning]
date: YYYY-MM-DD
---

[Content -- precise, not verbose. 1-5 sentences.]

**Why:** [rationale or source, if applicable]

**How to apply:** [when/where this matters in future sessions]

Read the full file on GitHub · 133 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. 3d ago First seen · 133 lines · 32 tokens per session scan A 533903d2f322

Subscribe to this mod's changes

craft-project-remember is a skill published in the GitHub repository derjochenmeyer/claude-code-craft (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,012 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens