codebase-exploring

A read-only guide for finding your way around an unfamiliar codebase, meaning a software project’s source files and supporting documents. It uses prepared maps and models of the project to explain entry points, layers, domains, and central files.

In plain words
What is it for?
Use it to understand how a repository is organized, where a request starts, which files are central, or what rules apply to a module. It is intended for explaining existing code, not changing it.
Why use it?
It gives developers a starting point without requiring them to reconstruct the project structure by reading every file. It also distinguishes orientation from debugging or planned code changes.

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/dhevenddra/forensic-deepdive/codebase-exploring
Any agent
npx skills add Dhevenddra/forensic-deepdive --skill codebase-exploring
Clone the repo
git clone --depth 1 https://github.com/Dhevenddra/forensic-deepdive

Made for: Claude Code, Codex.

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 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 $0.00115 $0.00501
Opus 5 $0.00057 $0.00251
Sonnet 5 $0.00023 $0.00100
Haiku 4.5 $0.00012 $0.00050

Measured yesterday against content hash b3ba9ccc6b66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-exploring 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.

tests/fixtures/prior_release/v0_8_0/.claude/skills/codebase-exploring/SKILL.md · 37 lines

What it actually says

Codebase exploring

Read-only orientation. Answer 'what is this and how is it laid out' without re-deriving structure by walking files.

When to use

  • User is new to a region of code or the whole repo.
  • Question shape: 'what is this', 'how is X organized', 'where does the request flow start', 'what are the main modules'.
  • User just opened an unfamiliar file and asks about it.

When NOT to use

  • User reports a bug or unexpected behavior → codebase-debugging.
  • User wants to change something and asks 'what will break' → codebase-impact-analysis.
  • User is brand new to the team and wants the broad brief → codebase-onboarding.
  • Question is code-semantic ('does this handle null') — just read the file.

How to answer

  1. Always read docs/codebase/AGENT_BRIEF.md first — it's small and pins the never/always rules.
  2. Match the question shape:
Question shape Artifact
'What are the entry points / domains' docs/codebase/MENTAL_MODEL.md
'Most central / load-bearing files' docs/codebase/MAP.md
'Key definitions in this module' docs/codebase/MAP.md (Key definitions)
'What rules apply when editing X' docs/codebase/AGENT_BRIEF.md
  1. If an MCP server (forensic serve) is running, also call context(symbol) to get the symbol's neighborhood in one shot.

Citation rule

Cite docs/codebase/MAP.md:142-158 or docs/codebase/AGENT_BRIEF.md:23. Never paraphrase a fact without a line citation.

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 · 37 lines · 115 tokens per session scan A b3ba9ccc6b66

Subscribe to this mod's changes

codebase-exploring is a skill published in the GitHub repository Dhevenddra/forensic-deepdive (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 115 tokens to every session and 501 once invoked, about $0.0006 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

mistakes

List past mistakes engram has learned in this project — failures, regressions, broken assumptions. Use before starting a non-trivial change to surface relevant prior failures, or when debugging to check if this issue has been seen before.

NickCirv/engram · 46 tokens

query

Query engram's local knowledge graph for structural context — function calls, imports, type relationships, mistake history, ADRs. Use when the user asks "how does X work in this project", "what calls Y", "where is Z used", or any structural question that doesn't need file content.

NickCirv/engram · 60 tokens

chatcrystal-task-writeback

Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through writetaskmemory or emit a structured memory candidate for later save.

ZengLiangYi/ChatCrystal · 62 tokens

chatcrystal-debug-recall

Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.

ZengLiangYi/ChatCrystal · 54 tokens

chatcrystal-task-recall

Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work. Use when the task is non-trivial, has repository or project context, and prior fixes, decisions, pitfalls, or reusable patterns may change the…

ZengLiangYi/ChatCrystal · 66 tokens

slm-recall

Search and retrieve facts, decisions, and past context from SuperLocalMemory. Use when the user asks to recall, find, search, or "what did we decide/say about X". Triggers multi-channel semantic retrieval with reranking; always call before storing anything new.

qualixar/superlocalmemory · 60 tokens