semblent-search

semblent-search is a skill for Claude Code, Codex from humanerd-drew/opencode-drewgent. It costs 0 tokens per session (662 once invoked), scanned A, original, MIT.

A code search tool that finds files by describing what the code does in everyday language, rather than matching exact words. It returns ranked results with file locations and relevance scores.

In plain words
What is it for?
Use it to find code for an authentication flow, cache invalidation, task delegation, or another behavior described in natural language, and to find code similar to a result.
Why use it?
It helps when you do not know the function name or exact text to search for, especially in an unfamiliar codebase. It also helps locate related code during debugging and refactoring.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/humanerd-drew/opencode-drewgent/semble-research
Any agent
npx skills add humanerd-drew/opencode-drewgent --skill semble-research
Clone the repo
git clone --depth 1 https://github.com/humanerd-drew/opencode-drewgent

Made for: Claude Code, Codex.

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.

agentmods badge for semblent-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/semble-research.svg)](https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/semble-research)
Your own site
<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/semble-research"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/semble-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 662 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00662
Opus 5 $0.00000 $0.00331
Sonnet 5 $0.00000 $0.00132
Haiku 4.5 $0.00000 $0.00066

Measured 3d ago against content hash 9b05b1c99d00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

semblent-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 3d 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.

@action/skills/semble-research/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semble indexes codebases and answers natural-language queries about code. It returns ranked results with file locations and relevance scores.

Available Tools

semble_search

Search using natural language intent.

semble_search(query="authentication flow", path="/repo", top_k=5)
semble_search(query="where is cache invalidation", path=".", top_k=5)
semble_search(query="how does delegate_task spawn subagents", path=".", top_k=3)

semble_find_related

Find similar code given a file:line from a prior result.

semble_find_related(file_path="tools/delegate_tool.py", line=287, path=".", top_k=5)

Decision Matrix: When to Use Semble

Situation Tool
Find code by what it does (intent) semble_search
Find code by exact pattern (regex) search_files (grep)
Find code by filename search_files (glob)
Need full file context read_file
Explore unfamiliar codebase semble_search first
Debugging "where did this error come from" semble_search
Refactoring related code semble_search + semble_find_related

Workflow

  1. Start with semble_search to find relevant chunks by describing intent
  2. Use semble_find_related with promising results to discover related implementations
  3. Use read_file only when you need full context of a specific file
  4. Use search_files (grep) only for exact string matches or exhaustive searches

Index Location

Semble indexes are stored at ~/.semble/. Indexes persist across sessions — no re-indexing needed on each query.

Limitations

  • Index updates happen on-demand (server-side, no local control)
  • Very large codebases may take longer to return results
  • Best for exploratory queries, not exhaustive searches

Examples

Find where AIAgent is initialized:

semble_search(query="AIAgent __init__ constructor", path=".", top_k=5)

Find workflow/integration patterns:

semble_search(query="workflow integration P0 P1 brain", path=".", top_k=3)

Read the full file on GitHub · 87 lines

Changes

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.

  1. 3d ago First seen · 87 lines · 0 tokens per session scan A 9b05b1c99d00

Subscribe to this mod's changes

semblent-search is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 662 tokens. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens