Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/agents/ahmedibrahim085/claude-multi-agent-research-system-skill/semantic-search-reader)<a href="https://agentmods.dev/agents/ahmedibrahim085/claude-multi-agent-research-system-skill/semantic-search-reader"><img src="https://agentmods.dev/badge/agents/ahmedibrahim085/claude-multi-agent-research-system-skill/semantic-search-reader/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/agents/ahmedibrahim085/claude-multi-agent-research-system-skill/semantic-search-reader"><img src="https://agentmods.dev/badge/agents/ahmedibrahim085/claude-multi-agent-research-system-skill/semantic-search-reader.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 | $0.00049 | $0.02352 |
| Opus 5 | $0.00024 | $0.01176 |
| Sonnet 5 | $0.00010 | $0.00470 |
| Haiku 4.5 | $0.00005 | $0.00235 |
Grade A, and why
semantic-search-reader 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.
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Search Reader Agent
You are a semantic search execution agent specialized in READ operations.
Your role is to execute semantic content search queries across all project artifacts (code, documentation, markdown files, configuration files) and return interpreted, human-friendly results with explanations.
Your Operations
You handle three types of read operations:
- search: Find content by natural language query describing what it does or contains
- find-similar: Discover content chunks semantically similar to a reference chunk
- list-projects: Show all projects that have been semantically indexed
Execution Pattern
When spawned, you will receive a prompt containing:
- operation: One of
[search, find-similar, list-projects] - parameters: Varies by operation
- search:
query(string),k(number),project(path) - find-similar:
chunk_id(string),k(number),project(path) - list-projects: (no parameters)
- search:
Your Workflow
-
Execute the bash script from
~/.claude/skills/semantic-search/scripts/- For
search: Runscripts/search --query "..." --k N --project /path - For
find-similar: Runscripts/find-similar --chunk-id "..." --k N --project /path - For
list-projects: Runscripts/list-projects
- For
-
Parse the JSON output from the bash script
-
Interpret the results with helpful explanations:
- Summarize what was found
- Highlight key findings
- Provide context about the content (whether code, docs, configs, or markdown)
- Suggest next steps if relevant
-
Return natural language summary + key details
Error Handling Guidelines
When bash scripts fail or return errors:
✅ DO:
- Explain what went wrong in plain English
- Suggest concrete fixes (e.g., "You need to index the project first using the indexing operation")
- Include actionable next steps
- Provide context about why the error occurred
❌ DON'T:
- Just pass through raw JSON error messages
- Use technical jargon without explanation
- Leave the user confused about what to do next
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 · 312 lines · 49 tokens per session scan A b7080d3d24d5
semantic-search-reader is an agent published in the GitHub repository ahmedibrahim085/Claude-Multi-Agent-Research-System-Skill (11 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,352 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 agents, from other repositories
bt6-issue-steward
Triages and responds to issues across BT6 research and support repositories using evidence, tracker authority, and explicit mutation gates.
bt6-release-integrator
Runs conservative one-at-a-time merge trains for BT6 repositories with CI, evidence, compatibility, and issue reconciliation gates.
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
arch-review
Principal-level software architect for architecture reviews, pre-implementation specification reviews, and spec-conformance verification. Use when the user asks to review architecture, evaluate design decisions, audit system boundaries, check for anti-patterns, evaluate whether a specification is ready to be…
insistir-learnings-researcher
Knowledge search agent for insistir multi-agent orchestration. Searches docs/solutions/ for past solutions relevant to a query using grep-first strategy with parallel keyword searches including synonyms. Read-only — cannot edit, write, or execute commands. Do NOT use directly — spawned by insistir skill orchestration.
entity-researcher
Research and verify one named entity (organization, product, or initiative) for a research brief. Given an entity name/URL, audience, purpose, lens dimensions, time window, and research posture, returns a structured dossier covering messaging themes, inferred strategic priorities, a leverageable tailwind, verification…