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/knowledge-agentnpx skills add MSApps-Mobile/claude-plugins --skill knowledge-agentgit 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 | $0.00106 | $0.00547 |
| Opus 5 | $0.00053 | $0.00273 |
| Sonnet 5 | $0.00021 | $0.00109 |
| Haiku 4.5 | $0.00011 | $0.00055 |
Grade A, and why
knowledge-agent 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
knowledge-agent: Memory as Knowledge Base
Your memory DB contains decisions, insights, and notes from past sessions. Before answering questions from scratch, search it — you may have already figured this out.
Query Workflow
# 1. Semantic search for the concept
COWORK_MEM_DB=~/mnt/.claude/.cowork-mem/memory.db \
python3 {SKILL_DIR}/scripts/vector_search.py "<question>" --limit 8
# 2. Keyword search for specific terms
python3 {SKILL_DIR}/scripts/memory_store.py search "<key term>" --limit 5
# 3. Fetch full text for the most relevant results
python3 {SKILL_DIR}/scripts/memory_store.py get <id1> <id2>
Answering from Memory
After retrieving relevant observations:
- Synthesize, don't quote — distill what the observations say into a direct answer
- Cite the age — "We decided this 3 days ago" gives the user confidence in freshness
- Flag uncertainty — if observations are old or sparse, say so
- Update if stale — if the situation has clearly changed, save a new observation
When Memory Doesn't Know
If search returns nothing relevant:
- Answer from your general knowledge or by reading the codebase
- If you derive something new and useful, save it:
python3 {SKILL_DIR}/scripts/memory_store.py add insight \
"<what you learned>" --tags "<relevant,tags>"
Decision Archaeology
When the user asks "why did we do X this way?":
# Search specifically for past decisions
python3 {SKILL_DIR}/scripts/memory_store.py search "<X>" --type decision --limit 10
If you find a past decision, explain it with context. If you don't, note that "this decision isn't in memory — here's what I'd infer from the codebase."
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 · 61 lines · 106 tokens per session scan A a89d60ae33f8
knowledge-agent is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 6d ago), licensed MIT. It adds 106 tokens to every session and 547 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
change
Track and inspect graph changes, diffs, temporal updates, and the impact of new data on Semantica knowledge graphs.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
scaffold
Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points.
design
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.
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.
organize
Repository structure only: directory layout, file placement, naming conventions, and where-does-this-belong decisions. Detects the project's convention, audits files against it, and executes move plans with import-path updates. Never changes code inside files beyond the import updates a move forces; in-file…