cc-dejavu: Skill for Claude Code

.claude/skills/ingest-codebase/SKILL.md

ingest-codebase is a skill for Claude Code from Michaelliv/cc-dejavu. It costs 57 tokens per session (2,566 once invoked), scanned A, original, MIT.

A guide for building a clear mental model of a codebase: its main areas, capabilities, cross-cutting concerns, and design decisions.

In plain words
What is it for?
Use it when onboarding to a codebase, starting or improving its model, or checking the model after major changes.
Why use it?
It helps an agent understand how a system actually works instead of only listing its files.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Michaelliv/cc-dejavu's own configuration. It tells Claude Code how to work on cc-dejavu itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cc-dejavu configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Michaelliv/cc-dejavu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Michaelliv/cc-dejavu/main/.claude/skills/ingest-codebase/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Michaelliv/cc-dejavu

Made for: Claude Code.

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 ingest-codebase

README.md
[![agentmods](https://agentmods.dev/badge/skills/michaelliv/cc-dejavu/ingest-codebase.svg)](https://agentmods.dev/skills/michaelliv/cc-dejavu/ingest-codebase)
Your own site
<a href="https://agentmods.dev/skills/michaelliv/cc-dejavu/ingest-codebase"><img src="https://agentmods.dev/badge/skills/michaelliv/cc-dejavu/ingest-codebase.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,566 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 $0.00057 $0.02566
Opus 5 $0.00028 $0.01283
Sonnet 5 $0.00011 $0.00513
Haiku 4.5 $0.00006 $0.00257

Measured 7d ago against content hash 469ad08751c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ingest-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.

.claude/skills/ingest-codebase/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ingest Codebase - Mental Model Creation

Create a comprehensive mental model that captures how a system actually works - not just what files exist, but the conceptual boundaries, responsibilities, decisions, and connections that shape it.

When to Use

  • Starting a new mental model for a codebase
  • The existing model feels incomplete or shallow
  • Onboarding to understand a system's architecture
  • After major changes to verify the model is still accurate

Philosophy

A good domain model answers:

  • "What are the core things this system deals with?" → Domains
  • "What can this system do?" → Capabilities (with --operates-on connections!)
  • "What concerns cut across multiple parts?" → Aspects (with --applies-to connections!)
  • "Why was it built this way?" → Decisions

CRITICAL: Every capability MUST have --operates-on linking it to domains. Every aspect MUST have --applies-to. Orphan entities indicate incomplete modeling.


Phase 1: Rapid Codebase Survey (Launch 5-10 Agents in Parallel)

Before modeling, understand the codebase structure. Launch parallel agents to explore different aspects simultaneously:

Agent 1: "Read README.md, package.json, and entry points. What problem does this solve? Who are the users?"
Agent 2: "List all top-level directories. What's in each? (src/, lib/, apps/, packages/, etc.)"
Agent 3: "Find configuration files (*.config.*, .env*, etc.). What can be configured?"
Agent 4: "Search for 'export class' or 'export function' in key directories. What are the main abstractions?"
Agent 5: "Look for test directories. What's being tested? This reveals important functionality."
Agent 6: "Search for API routes, CLI commands, or event handlers. What are the entry points?"
Agent 7: "Look for database models, schemas, or types. What data does this system manage?"
Agent 8: "Search for external integrations (HTTP clients, SDKs, third-party services)."

Output: A map of the codebase with preliminary domain candidates.

Read the full file on GitHub · 284 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 · 284 lines · 57 tokens per session scan A 469ad08751c8

Subscribe to this mod's changes

ingest-codebase is a skill published in the GitHub repository Michaelliv/cc-dejavu (22 stars, last pushed 7mo ago), licensed MIT. It adds 57 tokens to every session and 2,566 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens