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 skills/msapps-mobile/claude-plugins/smart-explorenpx skills add MSApps-Mobile/claude-plugins --skill smart-exploregit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWhat 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 | $0.00092 | $0.00498 |
| Opus 5 | $0.00046 | $0.00249 |
| Sonnet 5 | $0.00018 | $0.00100 |
| Haiku 4.5 | $0.00009 | $0.00050 |
Grade A, and why
smart-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 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.
What it actually says
smart-explore: Memory-Guided Project Exploration
Before reading files blindly, check what memory already knows. Past sessions may have documented the architecture, key files, gotchas, and current status.
Exploration Workflow
1. Check memory first
# What do we know about this project?
COWORK_MEM_DB=~/mnt/.claude/.cowork-mem/memory.db \
python3 {SKILL_DIR}/scripts/vector_search.py "project architecture overview" --limit 8
# Any recent decisions or file edits?
python3 {SKILL_DIR}/scripts/memory_store.py timeline --hours 168 --limit 20
2. Orient from memory → fill gaps with file reads
Use what memory tells you to target your file reads:
- If memory mentions
src/auth.pywas refactored, read that file - If memory notes a known bug in the API layer, look there first
- Skip files that memory says are stable/untouched
3. Build a mental model
After combining memory recall + targeted file reads, produce a brief summary:
- What the project does (1 sentence)
- Current state (what's working, what's in progress)
- Key files / architecture (3-5 most relevant)
- Active issues or blockers (from memory)
- What to work on next (from last session summary)
4. Save any new insights
python3 {SKILL_DIR}/scripts/memory_store.py add insight \
"Project overview: <what you learned>" --tags "architecture,overview"
What Makes This "Smart"
Regular exploration = read every file from scratch. Smart-explore = memory tells you where to look, so you read 20% of the files and understand 80% of the project state.
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 · 56 lines · 92 tokens per session scan A c2266fcf34a7
smart-explore is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 6d ago), licensed MIT. It adds 92 tokens to every session and 498 once invoked, about $0.0005 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 skills, from other repositories
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.