A codebase investigation phase in specification-driven development. It traces where behavior starts, how data moves, what depends on what, and which parts of the code may constrain a proposed change.

Use it to find entry points, follow data through a system, map internal and external dependencies, identify complex or poorly tested code, and record existing commitments.

It gives the team context before anyone proposes a solution. This reduces the risk of overlooking public interfaces, side effects, performance limits, security requirements, or difficult areas of the code.

How PedroMosquera/squadai configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to PedroMosquera/squadai. 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/PedroMosquera/squadai/main/.claude/skills/sdd/sdd-explore/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/PedroMosquera/squadai

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-explore.svg)](https://agentmods.dev/skills/pedromosquera/squadai/sdd-explore)

Your own site

<a href="https://agentmods.dev/skills/pedromosquera/squadai/sdd-explore"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-explore.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 443 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.00443
Opus 5	$0.00008	$0.00221
Sonnet 5	$0.00003	$0.00089
Haiku 4.5	$0.00002	$0.00044

Measured 7d ago against content hash e17719d5169e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sdd-explore 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/sdd/sdd-explore/SKILL.md · 71 lines

What it actually says

SDD Explore Skill

Analyze an existing codebase to gather context before proposing solutions. This is the first phase of the SDD pipeline — understand before proposing.

Steps

Identify entry points: Find where the relevant system behavior begins.
- Main functions, HTTP handlers, CLI commands, event listeners
- Public API surfaces (exported functions, interfaces)
- Configuration loading points
Trace data flow: Follow data through the system.
- How does input enter the system?
- What transformations does it undergo?
- Where is data persisted or returned?
- What are the side effects?
Map dependencies: Understand what depends on what.
- Internal package dependencies
- External library dependencies
- Interface boundaries and their implementations
- Circular dependency risks
Identify hotspots: Flag areas of concern.
- Files changed frequently in git log
- Code with high complexity or low test coverage
- Undocumented magic behavior
- Areas where the feature request will require changes
Document constraints: Note existing commitments.
- Public API contracts that must not break
- Performance SLAs or resource limits
- Security requirements (auth, input validation)
- Compatibility requirements (old data formats, deprecated paths)
Summarize for the Proposer: Produce a context document.
- Overview of relevant system components
- Key data structures and their relationships
- Constraints the Proposer must respect
- Open questions that need clarification

Output Format

## Exploration Report: <topic>

### Entry Points
- <file/function>: <description of role>

### Data Flow
<brief description or diagram>

### Key Data Structures
- <type>: <description and purpose>

### Constraints
- <constraint>: <why it exists>

### Hotspots
- <area>: <risk or complexity reason>

### Open Questions
1. <question needing clarification before proposing>

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.

7d ago First seen · 71 lines · 15 tokens per session scan A e17719d5169e

Subscribe to this mod's changes

sdd-explore is a skill published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 443 once invoked, about $0.0001 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.

Claude Code Planning ai-agents bubbletea cli cursor developer-tools

harness-engineering

Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.

paladini/harness-score · 55 tokens

gap

Measure the loaded-versus-fired gap - what fraction of each category of loaded context is ever actually invoked, and which MCP tools return mostly noise. Use when asked how much of the context is earning its place, or which categories are worst.

thousandflowers/skillreaper · 48 tokens

reap

Report how much of the context this agent loads is never used - unused skills, MCP servers, subagents, hooks and always-loaded prose - measured from real session transcripts. Use when asked why the context window is full, what is wasting tokens, or what is safe to remove.

thousandflowers/skillreaper · 56 tokens

replay

Find, analyze, and share AI coding sessions with vibe-replay. Use when the user asks for a replay, wants to find a past session, run a session retro, share Cursor/Claude/Codex session context, or attach session context to a PR.

tuo-lei/vibe-replay · 56 tokens

skill-doctor

Use the skill-doctor CLI or UI to inspect and manage AI-agent skills, rules, instructions, MCP resources, and context cost across supported platforms. Trigger when the user asks to scan or audit agent skills, find duplicates or trigger conflicts, investigate unsafe instructions, estimate context-token cost, compare…

evilstar2016/skill-doctor · 103 tokens

skill-doctor-context-optimizer

Interactively keep the skills, MCP servers/tools, and plugins relevant to the user's current task, preview project-local disables for the rest, apply only explicitly confirmed controls through skill-doctor, and report approximate context-token savings. Trigger when the user asks to slim, optimize, prune, or reduce the…

evilstar2016/skill-doctor · 79 tokens

squadai: Skill for Claude Code