proactive-memory

proactive-memory is a skill for Claude Code, Codex from ryantlee25-droid/tages. It costs 91 tokens per session (981 once invoked), scanned A, original, MIT.

A coding workflow for saving useful project knowledge, such as conventions, design decisions, problems discovered, and user corrections, for later sessions.

In plain words
What is it for?
Recording naming rules, code patterns, architecture choices, workarounds, and other facts worth remembering during development.
Why use it?
It reduces the need to rediscover project-specific details after the agent starts a new session.

Skill for Claude CodeCodex

Part of the tages plugin — 2 skills, 1 MCP server shipped together

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/ryantlee25-droid/tages/proactive-memory
Any agent
npx skills add ryantlee25-droid/tages --skill proactive-memory
Clone the repo
git clone --depth 1 https://github.com/ryantlee25-droid/tages

Made for: Claude Code, Codex.

Or install tages, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote 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.

agentmods badge for proactive-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/ryantlee25-droid/tages/proactive-memory.svg)](https://agentmods.dev/skills/ryantlee25-droid/tages/proactive-memory)
Your own site
<a href="https://agentmods.dev/skills/ryantlee25-droid/tages/proactive-memory"><img src="https://agentmods.dev/badge/skills/ryantlee25-droid/tages/proactive-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 981 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 $0.00091 $0.00981
Opus 5 $0.00046 $0.00491
Sonnet 5 $0.00018 $0.00196
Haiku 4.5 $0.00009 $0.00098

Measured 4d ago against content hash e483a8577afe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proactive-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 4d 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/proactive-memory/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proactive Memory — Remember as You Work

Keywords

remember this, save convention, note this pattern, don't forget, save this decision, remember for next time, keep this in mind, convention, architecture decision, gotcha, correction

Overview

During normal coding work, capture valuable project knowledge into Tages so it persists across sessions. This skill guides when and what to remember — the goal is that the next session starts with full context instead of amnesia.

Use this skill when: You discover something worth remembering during coding, or the user explicitly asks you to remember something.


What to Remember

Conventions

Naming patterns, code style, file organization, import conventions, test patterns.

Examples:

  • "Components in this project use PascalCase with a .component.tsx suffix"
  • "All API routes validate input with Zod schemas before processing"
  • "Tests use factories from tests/factories/ instead of inline fixtures"

Architecture Decisions

Why something is built a certain way, trade-offs that were made, structural choices.

Examples:

  • "Auth uses Supabase PKCE flow with a /auth/cli-token workaround for CLI OAuth"
  • "SQLite is the primary store for sub-10ms reads; Supabase syncs in background"
  • "Dashboard deploys manually via vercel --prod, not auto-deploy from GitHub"

Gotchas

Non-obvious behavior, common mistakes, workarounds, things that look wrong but are intentional.

Examples:

  • "Supabase .from().insert() returns PromiseLike not Promise — wrap with Promise.resolve() for .catch()"
  • "The ESM/CJS boundary between CLI and server requires createRequire + directory walk"
  • "Migration params need explicit ::uuid cast for uuid columns"

Corrections

When the user corrects your approach — remember it so you don't repeat the mistake.

Examples:

  • User: "No, we don't mock the database in these tests" → Remember: integration tests use real DB
  • User: "Use the existing Button component, don't create a new one" → Remember: reuse shared components from src/components/ui/

Read the full file on GitHub · 109 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. 4d ago First seen · 109 lines · 91 tokens per session scan A e483a8577afe

Subscribe to this mod's changes

proactive-memory is a skill published in the GitHub repository ryantlee25-droid/tages (4 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 981 once invoked, about $0.0005 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.