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.
npx agentmods add skills/lanterncx/agent/using-memorynpx skills add LanternCX/Agent --skill using-memorygit clone --depth 1 https://github.com/LanternCX/AgentWhat 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 | $0.00025 | $0.00585 |
| Opus 5 | $0.00013 | $0.00293 |
| Sonnet 5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
using-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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Memory
Overview
Use project memory only when history can materially improve the current decision.
This skill is retrieval-only. It helps find the smallest amount of relevant history, then stop.
When to Use
Memory is worth consulting when one or more of these are true:
- current work depends on why something was designed, fixed, or reorganized before
- the task may already have a precedent worth reusing
- the task needs to stay consistent with earlier project decisions or boundaries
- several reasonable directions exist and project history may narrow the choice
Do not use memory when the current request, code, spec, and plan already make the path clear. Do not keep reading once extra history would add background but not change the decision.
Retrieval Order
- Start by scanning
docs/superpowers/memory/*/MEMORY.md. - Use
grepto find only the## Use Whenand## Avoid Whenfield titles first. - Use the reported line numbers to
readonly small windows around those sections. - Expand the read window only if the section boundary is still unclear.
- Choose the smallest useful set of candidate memory types.
- Only after choosing candidate types, inspect their
INDEX.mdfiles. - From those candidates, inspect only the specific entries that look relevant.
- Stop as soon as the current task has enough history to move forward.
MEMORY.md files define when a type is worth consulting. INDEX.md helps find likely entries inside a chosen type. Specific entries provide evidence only after the type has already been chosen.
If docs/superpowers/memory/ is missing, or scanning finds no usable MEMORY.md files, stop and report that no project memory is available. This skill does not create or repair memory structure.
Stop Conditions
Stop reading when any of these are true:
- you can tell whether relevant precedent exists
- you have the 1-3 history constraints that matter for the task
- you know the needed background well enough to continue safely
- reading more would add detail but not change the decision
- continuing would require whole-file or whole-index reading instead of targeted lookup
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.
- yesterday First seen · 67 lines · 25 tokens per session scan A 2054b54e6aa9
using-memory is a skill published in the GitHub repository LanternCX/Agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 585 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…