live-memory

A set of instructions for using Live Memory, a long-running read-only companion that stores knowledge about a codebase. It answers repository questions through ask_live_memory instead of requiring the agent to reread files.

In plain words
What is it for?
Use it for questions about where code lives, how components work, what calls what, what a change could affect, and which conventions the repository uses.
Why use it?
It helps the agent find and understand code with less repeated file loading, while making clear that it cannot edit the project.

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/shofer-dev/claude-code-live-memory/live-memory
Any agent
npx skills add shofer-dev/claude-code-live-memory --skill live-memory
Clone the repo
git clone --depth 1 https://github.com/shofer-dev/claude-code-live-memory

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 568 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 $0.00059 $0.00568
Opus 5 $0.00030 $0.00284
Sonnet 5 $0.00012 $0.00114
Haiku 4.5 $0.00006 $0.00057

Measured 2d ago against content hash a99106ee0c2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

live-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 2d 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/live-memory/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Live Memory

The Live Memory is a long-running companion that holds an ever-growing, read-only understanding of this codebase. Use it to answer "where / how / what calls what" questions cheaply, without loading large files into your own context.

When to use ask_live_memory

Prefer it for codebase-knowledge questions:

  • "Where is X implemented / configured / registered?"
  • "How does component Y work, and what does it depend on?"
  • "What calls Z / what would break if I change it?"
  • "What's the convention for doing W in this repo?"

It can read files, ripgrep, and glob on its own to answer — you do not need to pre-load context for it.

When NOT to use it

  • For writing or editing code (it is read-only — it answers, it never changes files).
  • For facts unrelated to this repository.
  • When you already have the answer in your own context.

How to call it

Call the ask_live_memory MCP tool with:

  • question (required) — a specific, self-contained question.
  • cwd (required) — the absolute path of the current project/repository root (your session's working directory). Must be absolute — a relative path is rejected, since the server cannot resolve it against your session. The memory is keyed per repository, so always pass the repo root, not a subdirectory.
  • max_answer_tokens (optional) — a hard cap on the answer length, in output tokens (~4 characters each). The Live Memory is told this budget and keeps its answer within it; beyond the cap the answer is truncated. Omit it (or pass 0) for the default, which suits normal lookups. Raise it when you deliberately want a long, detailed answer (e.g. "walk me through the whole request flow"); lower it to force a terse one.

The call blocks until the answer arrives, bounded by a server-configured time budget (default_timeout_s, typically 1–2 minutes) — there is no timeout argument. At the budget the Live Memory returns its best-effort answer so far.

Ask one focused question per call. The answer string is what you get back — the Live Memory's own working context is private and does not enter yours.

Read the full file on GitHub · 52 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. 2d ago First seen · 52 lines · 59 tokens per session scan A a99106ee0c2b

Subscribe to this mod's changes

live-memory is a skill published in the GitHub repository shofer-dev/claude-code-live-memory (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 568 once invoked, about $0.0003 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 2026-08-30.

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