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/donpx skills add MSApps-Mobile/claude-plugins --skill dogit 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 | $0.00575 |
| Opus 5 | $0.00046 | $0.00287 |
| Sonnet 5 | $0.00018 | $0.00115 |
| Haiku 4.5 | $0.00009 | $0.00057 |
Grade A, and why
do 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
do: Memory-Aware Task Execution
Every task you run should start from what you know, not from zero.
Execution Workflow
Before you start: Load context
# What's already done / decided related to this task?
COWORK_MEM_DB=~/mnt/.claude/.cowork-mem/memory.db \
python3 {SKILL_DIR}/scripts/vector_search.py "<task description>" --limit 8
# Any relevant errors or blockers?
python3 {SKILL_DIR}/scripts/memory_store.py search "<key term>" --type error --limit 5
Use the recalled context to:
- Skip work that's already done
- Avoid approaches that previously failed (check errors)
- Follow established patterns (check past decisions)
- Build on existing file structure (check file_edits)
During execution: Save what matters
As you work, save observations for significant actions:
# When you make a choice
python3 {SKILL_DIR}/scripts/memory_store.py add decision \
"<what you chose and why>" --tags "<task-tag>"
# When you discover something non-obvious
python3 {SKILL_DIR}/scripts/memory_store.py add insight \
"<what you learned>" --tags "<task-tag>"
# When you hit an error and solve it
python3 {SKILL_DIR}/scripts/memory_store.py add error \
"<error encountered + solution>" --tags "<task-tag>"
Don't over-log. Save things future-you would want to know that aren't obvious from the code.
After completion: Close the loop
python3 {SKILL_DIR}/scripts/memory_store.py add note \
"Completed: <what was done>. Status: <done/partial>. Next: <what remains>" \
--tags "completed,<task-tag>"
Parallelism with PostToolUse Hook
If the PostToolUse hook is active, file edits and bash commands are captured automatically. Focus your manual saves on:
- Decisions (why you chose this approach)
- Insights (non-obvious things you discovered)
- Errors (problems and solutions)
The hook handles the "what happened"; you handle the "why it matters."
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 · 69 lines · 92 tokens per session scan A 3d37ba9887e4
do 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 575 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.