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.
git clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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.
[](https://agentmods.dev/commands/christopherlouet/claude-base/work-explore)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/work-explore"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/work-explore/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/christopherlouet/claude-base/work-explore"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/work-explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00390 |
| Opus 5.5 | $0.00000 | $0.00156 |
| Sonnet 5.5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
work-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 1mo 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.
What it actually says
WORK-EXPLORE Agent
Analyzes the codebase without writing code. EXPLORATION mode only.
Context
$ARGUMENTS
Goal
Deeply understand a part of the codebase before any modification. Exploration is the mandatory first step: EXPLORE -> (BRAINSTORM) -> SPECIFY -> PLAN -> TDD -> AUDIT -> COMMIT
Workflow
- Identify the scope: search by name (glob), by content (grep), tree navigation
- Locate entry points (routes, App.tsx, index.ts, bin/, commands/)
- Analyze the architecture: folder structure, separation of responsibilities, patterns (MVC, Clean Arch...)
- Analyze the code: naming conventions, style (functional/OOP), error handling, typing
- List the main and internal dependencies
- Examine the tests: framework, coverage, patterns (mocks, fixtures)
- Read the existing documentation (README, docs/, JSDoc, types)
- Identify risks and technical debt
Expected output
- Key files: Table (file, role, lines)
- Architecture: Structure and identified patterns
- Conventions: Naming, style, tests
- Dependencies: Packages and their usages
- Points of attention: Risks and technical debt
- Recommendations: Suggestions for the next steps
Related agents
| After | Usage |
|---|---|
/work:work-plan |
Plan the modifications |
/doc:doc-explain |
Explain complex code |
/doc:doc-onboard |
Full discovery of a project |
IMPORTANT: Never write code in exploration mode - analysis only.
YOU MUST read the source code, not just the file names.
NEVER assume how it works - verify in the code.
Think hard before answering to provide a complete and useful analysis.
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.
- 1mo ago First seen · 50 lines · 0 tokens per session scan A f469a2b3a091
work-explore is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 390 tokens. 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 2026-09-03.
Other commands, from other repositories
migrate
Generate and manage database migrations.
scaffold
Scaffold project components from templates.
deploy
Deploy application with pre/post-deploy checks.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
log-decision
Append an architectural decision to the persistent decision log.
session-log
Explain where session history lives now that the toolkit keeps no session log.