agentmods.dev

memory-first

memory-first is a skill for Claude Code, Codex from yeisonrestrepo/code-conductor. It costs 32 tokens per session (303 once invoked), scanned A, original, MIT.

A required lookup process for finding project information before reading files or searching the code. It checks project memory, a code relationship graph, text and file searches, and only then reads a small part of a file.

In plain words
What is it for?
Use it to answer questions about project conventions, function callers, module dependencies, interface implementations, and matching text or files.
Why use it?
It reduces unnecessary file reading and searches by stopping as soon as the answer is found. It also provides a consistent way to investigate where code is connected or where text appears.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

not rated 18repo +1 changed 1mo ago A scan 32 tokens original MIT

Good fit Use it to answer questions about project conventions, function callers, module dependencies, interface implementations, and matching text or files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yeisonrestrepo/code-conductor/memory-first
View source ↗ yeisonrestrepo/code-conductor
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.

Any agent
npx skills add yeisonrestrepo/code-conductor --skill memory-first
Clone the repo
git clone --depth 1 https://github.com/yeisonrestrepo/code-conductor

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 memory-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/yeisonrestrepo/code-conductor/memory-first/github.svg)](https://agentmods.dev/skills/yeisonrestrepo/code-conductor/memory-first)
Your own site
<a href="https://agentmods.dev/skills/yeisonrestrepo/code-conductor/memory-first"><img src="https://agentmods.dev/badge/skills/yeisonrestrepo/code-conductor/memory-first/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.

agentmods 80×15 button for memory-first

Your own site · 80×15
<a href="https://agentmods.dev/skills/yeisonrestrepo/code-conductor/memory-first"><img src="https://agentmods.dev/badge/skills/yeisonrestrepo/code-conductor/memory-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00032 $0.00303
Opus 5.5 $0.00013 $0.00121
Sonnet 5.5 $0.00006 $0.00061
Haiku 4.5 $0.00003 $0.00030

Measured 1mo ago against content hash b06751726bad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-first 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 1mo 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/memory-first/SKILL.md · 35 lines

What it actually says

Memory-First Protocol

Follow this lookup chain in strict order before reading any file, running any search, or spawning any tool. Stop at the first step that answers the question.

Chain

1. Memory

Check .claude/memory/project.md (project) and ~/.claude/memory/personal.md (global preferences).

Use the Grep tool on both files:

Grep pattern="<keyword>" path=".claude/memory/project.md"
Grep pattern="<keyword>" path="~/.claude/memory/personal.md"

If Grep returns matches, use that information and stop. If no matches, proceed to step 2.

2. Grep / Glob

For pattern searches, use the Grep or Glob tools inline. Never read a full file to find a pattern.

3. Targeted Read

Last resort. Only when steps 1–2 cannot answer.

  • Always specify offset and limit.
  • Max 150 lines per call.
  • Know approximately which lines to read before calling.

The pre-tool-use hook blocks Read calls on files >150 lines with no explicit limit. If blocked, return to step 1.

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. 1mo ago Changed · +1 lines · +2 tokens per session b06751726bad
  2. 1mo ago Changed · -17 lines · -7 tokens per session 785dd3d0f4af
  3. 1mo ago First seen · 51 lines · 37 tokens per session scan A aab5cfe38163

Subscribe to this mod's changes

memory-first is a skill published in the GitHub repository yeisonrestrepo/code-conductor (18 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 303 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-23.

Memory and contextProductivityagentic-developmentai-agentsclaudeclaudecodeskillsspec-driven-development
Related

memory-first compared with skills from other repositories

memory-first next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
memory-firstyeisonrestrepo/code-conductorSkill18todayMITA32Claude Code, Codex
digital-brainforyourhealth111-pixel/Vibe-SkillsSkill3.8k5d agoApache-2.0A57Claude Code, Codex
chief-of-staffvinvcn/mattpocock-skills-zh-CNSkill5.8k4d agoMITA20Claude Code, Codex
relevance-coarse-filterelvisun/newsjackSkill1.7k3d agoMITA57Claude Code
context-bankruptcymohitagw15856/pm-claude-skillsSkill1.5kyesterdayMITA108Claude Code
context-engineering-reviewmohitagw15856/pm-claude-skillsSkill1.5kyesterdayMITA111Claude Code
memory-file-maintenancemohitagw15856/pm-claude-skillsSkill1.5kyesterdayMITA146Claude Code