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/remember-md/remember/evolvenpx skills add remember-md/remember --skill evolvegit clone --depth 1 https://github.com/remember-md/rememberWhat 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 | $0.00028 | $0.02259 |
| Opus 5 | $0.00014 | $0.01130 |
| Sonnet 5 | $0.00006 | $0.00452 |
| Haiku 4.5 | $0.00003 | $0.00226 |
Grade A, and why
remember:evolve 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/remember:evolve — Evolve the Brain (periodic, weekly recommended)
The deeper LLM-driven evolution layer. The deterministic Phase 3 (promote) runs automatically after every capture — that keeps Persona.md ## Top Beliefs current in real time. This skill is what does the work that promote alone can't: re-synthesizing entity profiles, re-scoring belief confidence semantically, marking stale beliefs that should retire.
Without periodic evolution, the brain becomes append-only:
People/,Projects/,Areas/files accumulate log entries but never get a refreshed## Profileoverview- Beliefs keep their initial confidence forever, even after 15 supporting captures that should push them to 0.95
- 6-month-old beliefs with no new evidence stay marked
stableinstead ofstale
Three phases:
- Consolidate (LLM) — re-synthesize entity profiles from accumulated facts and beliefs
- Reflect (LLM) — re-evaluate beliefs against evidence, update confidence and freshness, mark contradictions
- Promote (deterministic, no LLM) — also runs here, usually a no-op because auto-promote already kept Top Beliefs current
Recommended cadence: /loop 7d /remember:evolve (weekly) or /loop 30d /remember:evolve (monthly). Idempotent — safe to run any time.
After each Phase that writes (Phase 1 entity re-synthesis, Phase 2 belief frontmatter updates, Phase 3 Persona.md update via promote.js), call node ${CLAUDE_PLUGIN_ROOT}/scripts/schema.js validate <filepath> on the touched files. Surface its warnings (e.g. "confidence defaulted to 0.5 — review") in your final report.
Flags (parsed from user input)
| Flag | Effect |
|---|---|
--consolidate-only |
Run Phase 1 only |
--reflect-only |
Run Phase 2 only |
--promote-only |
Run Phase 3 only (no LLM — pure script call) |
--dry-run |
Log intended changes; write nothing |
If no flag → run all three phases in order.
Step 1: Resolve brain path & load config
- Read
$REMEMBER_BRAIN_PATH(fallback~/remember). Call this{brain}. - If missing → tell user to run
/remember:initand stop. - Run:
node ${CLAUDE_PLUGIN_ROOT}/scripts/build-index.js --compactto get the brain index. Use throughout to resolve entities and prevent duplicates. - Load thresholds + auto_promote flag:
Defaults:node -e "const {loadEvolutionConfig} = require('${CLAUDE_PLUGIN_ROOT}/scripts/config'); console.log(JSON.stringify(loadEvolutionConfig()));"promotion_confidence=0.85,promotion_sources=5,stale_days=90,consolidate_touches=5,top_beliefs_n=10.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 208 lines · 28 tokens per session scan A 73754a40f6e4
remember:evolve is a skill published in the GitHub repository remember-md/remember (58 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 2,259 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 2026-08-30.
Other skills, from other repositories
designing-commands
Use when someone wants to add their own slash command to this vault — most often /query (ask the wiki a question), but also /lint, /gaps, /weekly, or anything else. Guides them through the design decisions that make it theirs, then writes the command file. Trigger on "help me write a command", "build my query…
pos-verify
Use this immediately after files are created, edited, moved, deleted, or materially rewritten inside PersonalOS. Verifies that new truth was routed to the correct owner, written in the correct file shape, and still follows POS conventions. Do NOT use for whole-vault deep audits; use system-health-check.
skillify
Use this when {{username}} asks to skillify a repeated workflow, determine whether it deserves a reusable PersonalOS skill, or harden an existing workflow into a tested resolver-reachable capability. Do NOT use for one-off notes, ordinary execution, or already-specified skill authoring; use write-skill.
write-skill
Use this when the user wants to create a new shared PersonalOS skill under skills/ or revise a specified PersonalOS skill and the scope is already clear. Do NOT use for raw workflow capture or deciding whether work should become a skill; use skillify first. Do NOT use for repo-local or agent-local skills unless…
priority-dashboard
Use this to rebuild, inspect, or temporarily steer {{username}}'s current PersonalOS priority dashboard from canonical Actions, Attention Triggers, and owner context. Do NOT use it to create, complete, or independently manage tasks; use task-manager for Action and Trigger lifecycle changes.
lint-brain
Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".