record-memory

A project-memory utility for recording completed, reviewable changes in a documentation folder. It chooses the appropriate memory category and follows that category's entry format.

In plain words
What is it for?
Creating a lasting record of one completed change unit in docs/superpowers/memory/ and updating its index.
Why use it?
It preserves important decisions after a change is finished, without mixing durable project knowledge with temporary work notes.

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/lanterncx/agent/record-memory
Any agent
npx skills add LanternCX/Agent --skill record-memory
Clone the repo
git clone --depth 1 https://github.com/LanternCX/Agent

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 529 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 $0.00023 $0.00529
Opus 5 $0.00012 $0.00264
Sonnet 5 $0.00005 $0.00106
Haiku 4.5 $0.00002 $0.00053

Measured yesterday against content hash a3622ba70411, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

record-memory 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 yesterday.

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.

skill/record-memory/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Record Memory

Overview

Record durable project memory for a completed change unit.

Entry Conditions

Create a memory entry only when all of the following are true:

  1. The work has one clear goal.
  2. The work forms one coherent, reviewable change unit.
  3. The work is complete enough to preserve as durable project memory.

Do not use memory entries as work logs for exploration, partial work, or scattered trivial changes.

Discovery Order

Every entry belongs to exactly one type.

If discovery cannot identify one unique type, stop and ask the user to clarify.

Discover the target type in this order:

  1. Scan docs/superpowers/memory/*/MEMORY.md.
  2. Read each candidate header's Type, Record When, Avoid Recording When, and Entry Template.
  3. Choose the best-matching type for the completed change unit.
  4. After selecting the type, read only that type's ENTRY.md before writing.
  5. Write the entry under docs/superpowers/memory/<type>/entries/<YYYY-MM>/.
  6. Update only that type's INDEX.md at docs/superpowers/memory/<type>/INDEX.md.

Do not hardcode type names or type meaning from this skill alone. Repository memory files are the source of truth. This skill only routes recording work. It never retrieves, summarizes, or pre-reads historical memory for the current task. If the task first needs project history to reduce uncertainty, hand off to using-memory; Use When / Avoid When are retrieval-facing fields and are not recording fallbacks.

Stop Conditions

Stop and ask the user to clarify when:

  • multiple discovered types fit and no clear choice exists
  • no discovered type fits and a new type may be needed
  • the completed work cannot be reduced to one reviewable change unit

Bootstrap Handoff

Read bootstrap.md, restore only the minimum missing structure, then restart discovery when:

  • docs/superpowers/memory/ is missing
  • scanning finds no usable docs/superpowers/memory/*/MEMORY.md
  • a scanned MEMORY.md is missing required record-facing fields, or cannot be parsed; treat that type as structurally damaged
  • the selected type is missing ENTRY.md
  • the selected type is missing INDEX.md
  • the selected type is missing its target month bucket under entries/<YYYY-MM>/

Read the full file on GitHub · 59 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. yesterday First seen · 59 lines · 23 tokens per session scan A a3622ba70411

Subscribe to this mod's changes

record-memory is a skill published in the GitHub repository LanternCX/Agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 529 once invoked, about $0.0001 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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

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