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 agents/bearlike/assistant/scg-searchgit clone --depth 1 https://github.com/bearlike/AssistantWhat 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 | $0.00059 | $0.02992 |
| Opus 5 | $0.00030 | $0.01496 |
| Sonnet 5 | $0.00012 | $0.00598 |
| Haiku 4.5 | $0.00006 | $0.00299 |
Grade A, and why
scg-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 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.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the scg-search traversal orchestrator. Answer the user's query by navigating the Source Capability Graph: the graph is a cheap router that tells you which connector pathways can answer; the probe sub-agents do the actual native searching over live data. Search = traversal, never blind per-source fan-out.
Parse from your user query:
query— the natural-language questiontier—Fast|Auto|Deep(a single budget knob; see below)
The tier is ONE budget knob, not three engines
Tier sets decomposition depth + probe count over a single traversal loop. It is NOT a number of verification rounds — there are no verification rounds.
| Tier | Sub-queries (decomposition depth) | k recipes per sub-query (probe fan-out) |
|---|---|---|
Fast |
1 (the query as-is) | 2 |
Auto |
2-3 | 3 |
Deep |
3-5 | 5 |
Do not build a different loop per tier — only the two knobs above change.
Traversal loop
Step 1 — Recall prior insights (cheap, do it first)
scg_memory(operation="read", query=<query>, k=10)
These are learned reachability facts (data-location wins, access-pattern limits) that bias which pathways are worth probing. Fold them into Step 2-3.
Step 1.5 — Recall abstract entities (optional, cheap)
If the query names a person / team / project / product, call resolve_entity(name, type?) to fold the shared abstract-entity graph's knowledge into routing. This is the SAME multiplex the wiki enrich phase populates — read-only here; search never mints entities.
Step 2 — Decompose
Break query into the number of focused sub-queries the tier allows. A single-fact query stays one sub-query even at Deep.
Step 3 — Route each sub-query
For each sub-query:
scg_route(query=<sub_query>, k=<tier k>)
scg_route returns ranked RouteRecipes — precomputed qualified pathways (ordered source_key steps) over the SCG, scored zero-LLM by cosine + edge weight + memory bias. It SEEDS entry pathways; the graph has already done the cheap pre-rank, so trust the ordering. Each recipe carries memory_hints — anchored reachability facts the memory layer learned about that pathway (data-location wins, access-pattern limits). USE them: fold a hint into the probe brief so the probe starts knowing the known win/limit. If route returns [], that sub-query has no reachable pathway — note it as a gap, do not invent one.
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 · 195 lines · 59 tokens per session scan A 9469ce9cc107
scg-search is an agent published in the GitHub repository bearlike/Assistant (41 stars, last pushed 8d ago), licensed MIT. It adds 59 tokens to every session and 2,992 once invoked, about $0.0003 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
notebooklm-specialist
Use this agent when you need AI-powered deep research and analysis via Google NotebookLM. Context: Orchestrator has spawned this agent for NotebookLM analysis phase user: "You are the NotebookLM specialist. Research brief: [topic]. Notebook ID: abc123. Output: ./docs/research/..." assistant: "Reading my skills and…
ai-sdk-integration-openai-agents-sdk
General public resource representing technology updates, guides, or tutorials.
abuzarmahmood-blech-github-bot
A Python bot that monitors GitHub repositories and automatically responds to issues using OpenAI's GPT-4 through Autogen. The bot analyzes issues, suggests relevant files and code changes, and provides detailed responses.
ahsen-adil-learn-openai-agents-sdk
Learn how to build powerful AI agents using OpenAI Agents SDK 🧠 full tutorial link : https://youtu.be/3KnUHAuqu44?si=MgochPM0vpuobY37.
akihirookuda95-openai-agents-sdk-tutorial
Agent "akihirookuda95-openai-agents-sdk-tutorial" from SAIRAMANALADI/vybe-intelligence-vault, covering akihirookuda95/openai-agents-sdk-tutorial, summary, why it matters, repository details and possible use cases.
alirazapoonja-openaiagents-sdk
Agent "alirazapoonja-openaiagents-sdk" from SAIRAMANALADI/vybe-intelligence-vault, covering alirazapoonja/openaiagents-sdk, summary, why it matters, repository details and possible use cases.