remember

Search past coding-agent work across all projects. Use when the user invokes $remember or /remember with keywords, or asks about past sessions, recaps, or finding past work.

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/laiso/cman/remember
Any agent
npx skills add laiso/cman --skill remember
Clone the repo
git clone --depth 1 https://github.com/laiso/cman

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00038 $0.01023
Opus 5 $0.00019 $0.00511
Sonnet 5 $0.00008 $0.00205
Haiku 4.5 $0.00004 $0.00102

Measured today against content hash 72f7139723d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 today.

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/remember/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.

Remember

Primary command: $remember in Codex or /remember in Claude Code (optional keywords as $ARGUMENTS).

Search and summarize past Claude Code, Pi Coding Agent, and Codex sessions, plans, and memory across all projects.

Arguments

If $ARGUMENTS is non-empty (e.g. /remember FOO BAR), join the tokens into the search keyword and follow the Search flow. Do not ask the user to repeat the query.

Instructions

First, gather data by calling these tools in parallel:

  1. mcp__plugin_cman_cman__list_sessions with limit=200
  2. mcp__plugin_cman_cman__list_plans
  3. mcp__plugin_cman_cman__list_memory
  4. mcp__plugin_cman_cman__list_pi_sessions with limit=200
  5. mcp__plugin_cman_cman__list_codex_sessions with limit=200

When running inside Pi, use the native cman tools with the same intent:

  1. cman_search_all for keyword search across all sources by default
  2. cman_claude_sessions and cman_pi_sessions together for recent/date recaps; use cman_search_all for Codex history
  3. A single source tool only when the user explicitly asks to limit the answer to that source

Then use the results to generate output. This skill searches across ALL projects by default. Determine what the user needs from context:

Recap (e.g., "what did I do yesterday?", "weekly standup")

  1. Filter sessions by time period (default: past 24 hours, "weekly" = past 7 days)
  2. Group by project, summarize what was done
  3. Show in-progress work with resume commands
  4. Include session count and project stats
  5. For date recaps such as "today" or "yesterday", use list_sessions(since="today") and list_pi_sessions(since="today") together, or in Pi use cman_claude_sessions(since="today") and cman_pi_sessions(since="today") together. Do not search for today's date as a keyword and do not inspect ~/.claude or ~/.pi with shell commands.
  6. If the user explicitly asks to limit the answer to one source, only then use that source.

Search (e.g., "where was that auth work?", "find migration sessions", or keyword arguments after /remember)

  1. Extract the keyword from the user's question, or from $ARGUMENTS when provided
  2. If the user did not explicitly name an agent/source, first call mcp__plugin_cman_cman__search_all (or mcp__cman__search_all) with the keyword
  3. Then search session titles, plans, and memory from the gathered data
  4. If the initial search has no useful results, retry conservative spelling or inflection variants (for example updates / update) before concluding there is no memory
  5. If the user explicitly asks to limit the answer to one source, call only the matching source search (search_sessions, search_pi_sessions, search_codex_sessions, or search_all with source=claude / source=pi / source=codex), or call those tools when search_all needs more detail
    • Use include_memory=true when the user may have stored relevant notes
    • Sub-agent logs are excluded by cman automatically
  6. Combine results from all matching agents and present with resume commands
  7. Alternate spellings: When searching for domain terms that may appear in different languages or spellings, run several search_all / source-specific search calls with alternate forms (e.g. English and Japanese: Scan / スキャン, or DynamoDB / dynamo) and merge the results

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. today First seen · 59 lines · 38 tokens per session scan A 72f7139723d3

Subscribe to this mod's changes

remember is a skill published in the GitHub repository laiso/cman (37 stars, last pushed 29d ago), licensed MIT. It adds 38 tokens to every session and 1,023 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 2026-09-01.

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