remember-codebase

remember-codebase is a skill for Claude Code, Codex from markmhendrickson/neotoma. It costs 31 tokens per session (739 once invoked), scanned A, original, MIT.

A tool for recording a codebase's repositories, structure, dependencies, architecture decisions, and team knowledge in persistent memory. A codebase is the complete set of files and supporting information for a software project.

In plain words
What is it for?
Use it to inventory repositories, identify languages and frameworks, review key directories and configuration files, and save confirmed project context.
Why use it?
It reduces the need to explain the same project structure and conventions to an agent in every session. Important technical decisions and context remain available later.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inventory repositories, identify languages and frameworks, review key directories and configuration files, and save confirmed project context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/markmhendrickson/neotoma/remember-codebase
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 markmhendrickson/neotoma --skill remember-codebase
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/neotoma

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 remember-codebase

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/neotoma/remember-codebase/github.svg)](https://agentmods.dev/skills/markmhendrickson/neotoma/remember-codebase)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/remember-codebase"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/remember-codebase/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 remember-codebase

Your own site · 80×15
<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/remember-codebase"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/remember-codebase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 739 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00031 $0.00739
Opus 5 $0.00015 $0.00369
Sonnet 5 $0.00006 $0.00148
Haiku 4.5 $0.00003 $0.00074

Measured 7d ago against content hash 2d2d9451a329, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

remember-codebase 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 7d 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/remember-codebase/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remember Codebase

Build a persistent inventory of your development context — repositories, architecture decisions, key dependencies, and team knowledge — in Neotoma memory.

When to use

When a developer wants their agent to persistently understand their codebase context across sessions, without re-prompting project structure, conventions, or architectural decisions each time.

Prerequisites

Run the ensure-neotoma skill first if Neotoma is not yet installed or configured in your current harness.

Workflow

Phase 0: Verify Neotoma

Confirm Neotoma MCP is connected (call get_session_identity).

Phase 1: Inventory the current repo

  1. Read project metadata:
    • package.json / pyproject.toml / Cargo.toml (name, version, dependencies)
    • README.md (project description, purpose)
    • Git remote URL and branch structure
  2. Scan for architectural signals:
    • Directory structure (src/, lib/, test/, docs/)
    • Configuration files (.env.example, docker-compose.yml, CI configs)
    • Framework and language markers
  3. Present the inventory: project name, language, framework, key directories, dependency count.
  4. Ask the user to confirm and add any context the scan missed.

Phase 2: Extract entities

  1. Repository: create a repository entity with name, remote URL, language, framework, description.
  2. Architectural decisions: if the repo has ADR files (docs/adr/) or architecture docs, extract each as a decision entity.
  3. Dependencies: create entities for key dependencies that the user wants to track (not all — ask which matter).
  4. Team context: if the user provides team member info, store as contact entities linked to the repo.
  5. Conventions: if the repo has coding conventions docs, extract key rules as note entities.

Phase 3: Store with provenance

Store the repository entity and related entities with provenance:

  • Set source_file for file-derived entities (README, package.json, ADR files).
  • Use the combined store path for any files worth preserving as source.
  • Link all entities to the repository entity via REFERS_TO.

Read the full file on GitHub · 79 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. 7d ago First seen · 79 lines · 31 tokens per session scan A 2d2d9451a329

Subscribe to this mod's changes

remember-codebase is a skill published in the GitHub repository markmhendrickson/neotoma (32 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 739 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 2026-09-03.

Related

Other skills, from other repositories

remember

Routes user requests containing "remember", "recall", "checkpoint", "session", "todo", or "where were we" to the correct OpenEmpiric (OEM) MCP tool. Use when the user wants to persist, retrieve, or contextualize knowledge from project memory.

xpajonx/openempiric · 59 tokens

akf

Trust metadata for files, memories, and skills — check before you trust, stamp what you verify. A stamp costs 15 tokens; re-verifying costs 15,000.

HMAKT99/AKF · 39 tokens

akf

Trust metadata for files, memories, and skills — check before you trust, stamp what you verify. Use before building on existing files, after completing verified work, and when handling agent memories or downloaded skills.

HMAKT99/AKF · 44 tokens

aoa-memo

AoA/Abyss durable memory and owner orientation: use when ongoing work may depend on reviewed prior decisions, provenance, lifecycle/currentness, or an existing memo artifact, even when none is named. Also use to recall, review, or evolve a candidate, export, quarantine packet, object, corpus identity, lifecycle…

8Dionysus/aoa-memo · 116 tokens

soul-archive

Soul Archive — A digital personality persistence system + agentic memory. Builds your digital soul clone through everyday AI conversations, with proactive context injection, cross-session recall, failure-pattern warning, and pattern distillation. All data stored locally as plaintext JSON. Six modes: Soul Extract, Soul…

dqsjqian/soul-archive · 241 tokens

mk:wiki

Capture, gate, query, and render long-term project knowledge through the gated mewkit wiki subsystem. Use to create a wiki, propose/approve candidates (scanner-gated), hand off a skill's terminal artifact as a scanned candidate, recall context, search the FTS index, or list pages. Agents may only PROPOSE candidates…

ngocsangyem/MeowKit · 119 tokens