Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/myths-labs/musenpx agentmods add skills/myths-labs/muse/semantic-searchWrote 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/skills/myths-labs/muse/semantic-search)<a href="https://agentmods.dev/skills/myths-labs/muse/semantic-search"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/semantic-search/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/skills/myths-labs/muse/semantic-search"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/semantic-search.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 | $0.00032 | $0.00495 |
| Opus 5 | $0.00016 | $0.00247 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
semantic-search 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 10d 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
Semantic Search
Search across your entire MUSE project context using TF-IDF ranking.
When to Use
- User asks "where did we discuss X?"
- User wants to find a past decision or lesson
- User needs to locate a specific skill
- Context recovery when resuming work
Usage
# Search everything
./scripts/search.sh "auth jwt oauth"
# Search only memory files
./scripts/search.sh "database migration" --scope memory
# Search only role files
./scripts/search.sh "dashboard" --scope roles --top 3
# Search only skills
./scripts/search.sh "testing" --scope skills --top 10
How It Works
- Tokenization: Query is split into lowercase terms
- TF (Term Frequency): For each file, count occurrences of each query term, normalized by file length
- IDF (Inverse Document Frequency): Terms that appear in fewer files get higher weight
- Score: TF × IDF summed across all query terms
- Ranking: Files sorted by score, top N shown with best-matching line as context snippet
Scopes
| Scope | Files Indexed |
|---|---|
all (default) |
memory/ + .muse/ + MEMORIES.md + skills/ |
memory |
memory/*.md + MEMORIES.md |
roles |
.muse/*.md |
skills |
skills//SKILL.md + .agent/skills//SKILL.md |
Integration
When resuming a conversation, you can use search to quickly find relevant context:
# Before /resume — find what was done last week
./scripts/search.sh "migration deploy" --scope memory --top 3
Limitations
- Pure TF-IDF, no semantic understanding (no embeddings/vectors)
- Exact term matching only (no synonyms)
- Best for keyword-based queries with specific terms
- For semantic search, consider integrating with mem0 or memsearch
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.
- 10d ago First seen · 68 lines · 32 tokens per session scan A f3bf315c81e4
semantic-search is a skill published in the GitHub repository myths-labs/muse (32 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 495 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
context-receipts
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
memory
Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…
ijfw-handoff
Session handoff generation and loading. Trigger: session end, context full, /handoff.
ijfw-summarize
Generate optimized project context from codebase scan. Trigger: new project, no CLAUDE.md, /ijfw-summarize.
repo-context-ledger
Record every behavior-changing feature addition, fix, and adjustment as durable, evidence-based repository knowledge, then use that ledger to continue accurately across AI windows, tools, Git collaboration, and pull requests. Use the deterministic runtime to route bounded context, isolate private drafts, publish…