tools-codebase-memory

A skill for gathering code-structure evidence from a persistent repository knowledge graph. It provides architecture overviews, call relationships, dependency analysis, cycles, change impact, module clusters, dead-code findings, and stored decisions.

In plain words
What is it for?
Use it to index a repository, investigate dependencies and call paths, identify cycles or dead code, estimate blast radius, and retrieve architecture records.
Why use it?
It helps an agent understand a large codebase’s structure without repeatedly inspecting every file manually.

Skill for Claude CodeCodex

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/alexei-led/architect/tools-codebase-memory
Any agent
npx skills add alexei-led/architect --skill tools-codebase-memory
Clone the repo
git clone --depth 1 https://github.com/alexei-led/architect

Made for: Claude Code, Codex.

Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,404 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 $0.00152 $0.01404
Opus 5 $0.00076 $0.00702
Sonnet 5 $0.00030 $0.00281
Haiku 4.5 $0.00015 $0.00140

Measured yesterday against content hash 4098ece6b581, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tools-codebase-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 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.

src/skills/tools-codebase-memory/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codebase-memory-mcp

codebase-memory-mcp indexes a repository into a persistent SQLite knowledge graph (tree-sitter ASTs plus a hybrid LSP layer) and exposes it over MCP. It answers the same graph-shaped questions as codegraph — what calls this, what a change reaches, where the hubs, cycles, and clusters are — plus cross-session Architecture Decision Records. Query it instead of re-reading files when the server is installed.

Evidence dimensions: dependency, semantic, and change-impact.

When to use

Use when the session exposes mcp__codebase-memory-mcp__* tools (verify with /mcp; the server reports as codebase-memory-mcp). Index during the system-map step, then query during evidence gathering for module structure, call/dependency edges, cycles, blast radius, and Louvain module clusters. Prefer it over tools-codegraph only when its index is present and fresh; otherwise use whichever graph tool is current.

Tools

All tools are namespaced mcp__codebase-memory-mcp__<name>. The architecture-relevant set:

  • index_repository — build or refresh the graph. repo_path must be ABSOLUTE.
  • list_projects — indexed projects with node/edge counts.
  • index_status — indexing state for a project.
  • get_graph_schema — node labels, edge types, counts. Run this first.
  • get_architecture — overview: languages, packages, routes, hotspots, clusters, dead code.
  • search_graph — find symbols by label / name_pattern / file_pattern.
  • trace_path (alias trace_call_path) — callers/callees of a function; direction in|out|both, depth 1-5 (fan-in/out, blast radius).
  • detect_changes — map the git diff to affected symbols and blast radius.
  • query_graph — read-only Cypher for cycles, dependency direction, hubs.
  • get_code_snippet — source for a symbol by qualified name.
  • search_code — grep-like text search within the index.
  • manage_adr — read ADRs (mode: get); write modes need user approval.

Workflow

  1. list_projects — is the target already indexed? If not, index_repository with the absolute repo path and wait for completion.
  2. get_graph_schema — learn the available labels/edges before querying.
  3. get_architecture — overview before deep dive: packages, entry points, routes, hotspots, clusters, dead code.
  4. search_graph then get_code_snippet — locate and read specific symbols.
  5. trace_path — fan-in/out and call paths for boundary/coupling claims.
  6. detect_changes — blast radius of the working diff before a change.
  7. query_graph — Cypher for cycles and wrong-way dependencies, e.g. MATCH (f:Function)-[:CALLS]->(g) WHERE ... RETURN ....

Read the full file on GitHub · 121 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. yesterday First seen · 121 lines · 152 tokens per session scan A 4098ece6b581

Subscribe to this mod's changes

tools-codebase-memory is a skill published in the GitHub repository alexei-led/architect (2 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 1,404 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

map-wayfind

Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…

azalio/map-framework · 182 tokens

clipboard

Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".

CodeAlive-AI/ai-driven-development · 36 tokens

neo4j-modeling-skill

Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…

neo4j-contrib/neo4j-skills · 152 tokens

alphafold-database

Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

agent-skills-hub/agent-skills-hub · 54 tokens