codebase-memory

A map of a codebase that shows how functions and other parts connect. It can answer questions about call paths, architecture, unused code, and which areas a change may affect.

In plain words
What is it for?
Use it to trace what calls a function, find what it calls, inspect the architecture, locate code by name or label, find unused functions, and identify affected execution flows.
Why use it?
It helps you understand a large codebase without opening files one by one. This reduces the effort needed to trace behavior and estimate change impact.

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/brain-bootstrap/claude-code-brain-bootstrap/codebase-memory
Any agent
npx skills add brain-bootstrap/claude-code-brain-bootstrap --skill codebase-memory
Clone the repo
git clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrap

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 631 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 $0.00043 $0.00631
Opus 5 $0.00022 $0.00316
Sonnet 5 $0.00009 $0.00126
Haiku 4.5 $0.00004 $0.00063

Measured 2d ago against content hash 304743b786c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/codebase-memory/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Memory — Structural Graph

Zero-file-read structural analysis. Always try these tools BEFORE reading files for structural questions.

Quick Decision Matrix

Question Tool
What calls foo()? trace_path(function_name="foo", direction="inbound")
What does foo() call? trace_path(function_name="foo", direction="outbound")
Full call chain trace_path(direction="both", depth=3)
Impact of my change detect_changes(base_branch="main")
Architecture overview get_architecture
Find by name/pattern search_graph(name_pattern="Auth.*")
Find by label search_graph(label="Class")
Dead code search_graph(max_degree=0, label="Function")
Custom query query_graph(query="MATCH (n:Function)-[:CALLS]->(m) RETURN n.name, m.name LIMIT 20")
Execution flows list_flowsget_affected_flows
ADR management manage_adr(mode="get")

Workflow — First Use

  1. index_repository(repo_path=".") — first run only (~6s for 500 files)
  2. list_projects — verify indexed
  3. get_architecture — architecture map

Workflow — Before Reviewing Changes

  1. detect_changes(base_branch="main") → risk score + blast radius
  2. get_affected_flows → which execution paths break
  3. trace_path on highest-risk functions

Workflow — Exploration

  1. get_architecture → community map, entry points
  2. search_graph(name_pattern="<keyword>") → find relevant nodes
  3. trace_path → traverse from found nodes
  4. get_code_snippet(qualified_name="<name>") → source with context

Known Gotchas

  1. search_graph(relationship="HTTP_CALLS") filters by degree — use query_graph for actual edge inspection
  2. query_graph has a 200-row cap — use search_graph with degree filters for counts
  3. trace_path requires exact qualified names — use search_graph(name_pattern=...) first
  4. direction="outbound" misses cross-service callers — use direction="both"
  5. Results default to 10 per page — check has_more and paginate with offset

Read the full file on GitHub · 61 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. 2d ago First seen · 61 lines · 43 tokens per session scan A 304743b786c8

Subscribe to this mod's changes

codebase-memory is a skill published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 631 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 2026-08-30.

Related

Other skills, from other repositories

implement

TRIGGER when: user asks to implement, fix, build, or work on something — whether from a docs/wip plan OR a standalone task (bug fix, GitHub issue, one-off change). Examples: "work on task 1", "fix this bug", "implement feature X from the issue". Provides structured execution with profile detection, dependency…

serpro69/claude-toolbox · 79 tokens

review-spec

Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync. Detects spec deviations, missing implementations, doc inconsistencies, and outdated docs in design and implementation documentation.

serpro69/claude-toolbox · 44 tokens

chain-of-verification

Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.

serpro69/claude-toolbox · 41 tokens

review-design

Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency, and technical soundness. Use after design completes and before starting implement.

serpro69/claude-toolbox · 37 tokens

review-code

Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.

serpro69/claude-toolbox · 37 tokens

dependency-handling

TRIGGER when: adding or upgrading any dependency — library, SDK, framework, API, IaC API version (K8s/Terraform/Helm), CRD, or container image. Use BEFORE writing the call. Forces context7/capy lookup instead of guessing.

serpro69/claude-toolbox · 60 tokens