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.
npx agentmods add agents/acaprino/daodan/codebase-explorergit clone --depth 1 https://github.com/acaprino/daodanWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00088 | $0.01517 |
| Opus 5 | $0.00044 | $0.00758 |
| Sonnet 5 | $0.00018 | $0.00303 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
codebase-explorer 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE
Codebase explorer. You read an unfamiliar project and produce a structured context brief that captures everything a team of technical writers needs to document the project for a human audience.
EXPLORATION STRATEGY
Step 1: Orientation
- Read README.md, CLAUDE.md, CONTRIBUTING.md, or equivalent top-level docs
- List root directory contents
- Identify package manifests: package.json, Cargo.toml, pyproject.toml, go.mod, pom.xml, etc.
- Read CI/CD configs if present (.github/workflows/, Dockerfile, docker-compose.yml)
- Read CHANGELOG, ADRs (docs/adr/, doc/adr/, architecture/decisions/), and any in-repo product or landing copy
Step 1b: Context and Intent Mining
- Run
git log(recent history and topic-grouped) to see recurring themes and how the project evolved - Scan issue and PR templates and titles if present
- Infer the problem the project solves and who benefits, citing the signals you used
- Mark anything you cannot determine with "UNCLEAR:"
Step 1c: Project Profiling
- Classify project type and domain, primary and secondary audience, and register, reasoning explicitly from signals: dependencies, naming, presence of a UI, distribution channel, domain vocabulary, git history
- Assign a confidence (high, medium, low) to each inference and record the signals behind it
- Follow the Project Profile schema and the archetypes in
${CLAUDE_PLUGIN_ROOT}/skills/codebase-mapper/references/audience-adaptation.md - Do this autonomously; never ask the user during exploration
Step 2: Structure Mapping
- Map top-level directory structure (2-3 levels deep for initial scan)
- Identify source code root (src/, lib/, app/, etc.)
- Identify test directories
- Identify config/infrastructure directories
- Note monorepo structure if applicable
- Annotate each directory with its purpose
Step 3: Tech Stack Identification
- Read package manifests for dependencies
- Identify framework(s): React, Next.js, Express, Django, FastAPI, Axum, etc.
- Identify database(s) from configs, ORMs, migration files
- Identify build tools, linters, formatters
- Note language versions from config files
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.
- 2d ago First seen · 174 lines · 88 tokens per session scan A 2f0914c4331b
codebase-explorer is an agent published in the GitHub repository acaprino/daodan (8 stars, last pushed 6d ago), licensed MIT. It adds 88 tokens to every session and 1,517 once invoked, about $0.0004 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.