remembering-conversations

remembering-conversations is a skill for Claude Code, Codex from BongSuCHOI/memex. It costs 48 tokens per session (413 once invoked), scanned A, original, MIT.

A skill that searches Memex for relevant details from earlier Codex conversations, such as decisions, failed approaches, preferences, and unfamiliar workflows. Memex is a local system for storing and retrieving this history.

In plain words
What is it for?
Use it when a task depends on earlier discussions, durable project facts, related solutions from other projects, or the reasons behind past decisions.
Why use it?
It helps recover past context before repeating work or making up a rationale, while keeping current code inspection as the primary source for present code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

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/bongsuchoi/memex/remembering-conversations
Any agent
npx skills add BongSuCHOI/memex --skill remembering-conversations
Clone the repo
git clone --depth 1 https://github.com/BongSuCHOI/memex

Made for: Claude Code, Codex.

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 remembering-conversations

README.md
[![agentmods](https://agentmods.dev/badge/skills/bongsuchoi/memex/remembering-conversations.svg)](https://agentmods.dev/skills/bongsuchoi/memex/remembering-conversations)
Your own site
<a href="https://agentmods.dev/skills/bongsuchoi/memex/remembering-conversations"><img src="https://agentmods.dev/badge/skills/bongsuchoi/memex/remembering-conversations.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 413 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 5.1 $0.00048 $0.00413
Opus 5 $0.00024 $0.00206
Sonnet 5 $0.00010 $0.00083
Haiku 4.5 $0.00005 $0.00041

Measured yesterday against content hash 9d2c0c6bab3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

remembering-conversations 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.

skills/remembering-conversations/SKILL.md · 41 lines

What it actually says

Remembering Conversations

Recover relevant evidence from Memex before repeating past work or inventing a new rationale. These MCP calls are read-only. Their results are marked memex_recall: they remain searchable context but are not eligible evidence for new fact extraction merely because the agent repeated them.

Route the question

  • Past implementation, discussion, or exact wording: call search, then read only the best 2–5 archive ranges.
  • Durable decision, preference, pattern, knowledge, or constraint: call search_facts.
  • Why a fact exists: call trace_fact; treat source exchanges as authoritative provenance and the separately labeled interpretive context as non-authoritative.
  • How decisions connect: call explore_graph; use search_ontology for domain/category browsing.
  • How another project solved a similar problem: call cross_project_insights.
  • A synthesis in the user's established style: call ask_avatar, then retain its cited evidence and confidence boundary.

For project-sensitive tools, pass the current Codex thread's canonical absolute cwd as project/current_project, or use an explicit global/all scope. Never let the MCP server's installed-plugin cwd stand in for the user's project.

Handoff

Synthesize the evidence into an answer for the current task. Keep conversation archive paths and line ranges, or fact provenance, next to the claims they support. Distinguish historical evidence from current repository state and verify current code before making a change.

Do not load whole archives when a focused range is enough. Read references/mcp-tools.md when exact tool parameters or scope behavior matter.

Files

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.

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. yesterday Changed · +1 lines 9d2c0c6bab3b
  2. 5d ago First seen · 40 lines · 48 tokens per session scan A 738539badb20

Subscribe to this mod's changes

remembering-conversations is a skill published in the GitHub repository BongSuCHOI/memex (0 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 413 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 2026-08-31.