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 skills add usernameisthebestofthebest/claude-recap --skill remembergit clone --depth 1 https://github.com/usernameisthebestofthebest/claude-recapWrote 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.
[](https://agentmods.dev/skills/usernameisthebestofthebest/claude-recap/remember)<a href="https://agentmods.dev/skills/usernameisthebestofthebest/claude-recap/remember"><img src="https://agentmods.dev/badge/skills/usernameisthebestofthebest/claude-recap/remember/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/usernameisthebestofthebest/claude-recap/remember"><img src="https://agentmods.dev/badge/skills/usernameisthebestofthebest/claude-recap/remember.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00515 |
| Opus 5 | $0.00025 | $0.00258 |
| Sonnet 5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
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 12d 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.
This is a copy
100% identical to remember — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
remember
Overview
Saves a user preference, constraint, or fact to REMEMBER.md so it persists across sessions. The user chooses scope (global or project).
When to Use
- User explicitly says "remember...", "always...", "never...", "don't forget..."
- User states a clear preference or constraint worth persisting (e.g., "I use bun not npm")
- User provides identity or context info they'd want every session to know
Instructions
-
Distill what the user wants to remember into one concise line (imperative form, no filler).
- Good: "Use bun instead of npm for all package management"
- Bad: "The user mentioned they prefer bun over npm and would like us to always use it"
-
Ask the user which scope using AskUserQuestion:
Which scope should this apply to?
- Global: applies to all projects
- Project: applies only to this project
-
Get the plugin scripts path from the SessionStart injection in your context:
Plugin scripts path: /path/to/scripts -
Run the remember script:
bash "<plugin_scripts_path>/remember.sh" "<scope>" "<content>"
Where:
plugin_scripts_path: the path from SessionStart injectionscope:globalorprojectcontent: the distilled one-liner (quote it properly for shell)
Rules
- One entry per invocation — don't batch multiple items
- Distill to a clear imperative statement, not a description of what happened
- If the user's intent is ambiguous, ask for clarification before writing
- Do NOT remember session-specific or temporary information (e.g., "I'm debugging auth today")
Examples
| User says | Distilled entry |
|---|---|
| "Remember I always use bun" | Use bun instead of npm for package management |
| "Never auto-commit without asking" | Never auto-commit; always ask before committing |
| "My name is Alex" | User's name is Alex |
| "For this project, always run tests with --verbose" | Run tests with --verbose flag (project scope) |
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.
- 12d ago First seen · 61 lines · 50 tokens per session scan A b3455b36bb33
remember is a skill published in the GitHub repository usernameisthebestofthebest/claude-recap (2 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 515 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to remember, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
save-topic
Use when the user wants to save or checkpoint topic progress, persist current discussion state, or save all topics before ending a session.
ignore-topic
Use when the user wants to ignore, skip, or exclude specific topics from being archived. Triggers on "ignore topic", "don't archive", "skip topic", "stop remembering", "list ignored topics", "remove ignore rule".
remember
Use when the user wants to persistently remember something across sessions (e.g., "always use bun", "never auto-commit", "my name is Alex"). Also use when you detect a clear user preference or constraint worth persisting.
list-topics
Use when the user asks about topics discussed in the current session, wants to see a topic list, or asks what has been talked about.
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.