DeepRefine-Skill GEMINI.md

DeepRefine-Skill GEMINI.md is an instructions file for Gemini CLI from HKUST-KnowComp/DeepRefine-Skill. It costs 372 tokens per session, scanned A, original, MIT.

Instructions for using DeepRefine with Graphify knowledge graphs. Graphify stores connected facts and relationships as a graph, while DeepRefine reviews and updates that graph.

In plain words
What is it for?
Use it to sync pending history, query related graph data, create refinement records, review proposed updates, and apply changes through DeepRefine.
Why use it?
It provides a controlled process for finding possible improvements, reviewing them, and applying approved changes without editing the graph file directly.

Instructions file for Gemini CLI

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 instructions/hkust-knowcomp/deeprefine-skill/gemini-md
Clone the repo
git clone --depth 1 https://github.com/HKUST-KnowComp/DeepRefine-Skill

Made for: Gemini CLI.

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 DeepRefine-Skill GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hkust-knowcomp/deeprefine-skill/gemini-md.svg)](https://agentmods.dev/instructions/hkust-knowcomp/deeprefine-skill/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/hkust-knowcomp/deeprefine-skill/gemini-md"><img src="https://agentmods.dev/badge/instructions/hkust-knowcomp/deeprefine-skill/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 372 This file is loaded in full into every session.
When invoked 372 The same file — it is already loaded in full.
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 $0.00372 $0.00372
Opus 5 $0.00186 $0.00186
Sonnet 5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 4d ago against content hash b6414f81945f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DeepRefine-Skill GEMINI.md 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 4d 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.

GEMINI.md · 27 lines

What it actually says

DeepRefine Skill for Gemini CLI

This extension lets Gemini CLI use DeepRefine to refine and evolve Graphify / LLM-Wiki knowledge graphs.

Use the deeprefine skill when the user asks to refine, diagnose, debug, improve, inspect, or query a Graphify-generated knowledge graph.

Core behavior

  1. Prefer the agent-native DeepRefine loop over the terminal-only deeprefine refine command unless the user explicitly requests CLI / FAISS mode.
  2. Follow the same control flow as DeepRefine.refine() from DeepRefine.
  3. Import Graphify memory with deeprefine history sync-memory when running the default queue workflow.
  4. Process pending history entries one by one.
  5. Use Graphify query results and k-hop expansion over graphify-out/graph.json as retrieval evidence.
  6. Create and maintain a valid loop_trace_<query_id>.json before applying graph updates.
  7. Review proposed <refinement>...</refinement> actions before applying them.
  8. Apply graph updates only through deeprefine apply; do not hand-edit graphify-out/graph.json.
  9. Store DeepRefine artifacts under graphify-out/.deeprefine/.
  10. If graph artifacts are missing, ask the user to run /graphify . and /graphify ./ --wiki first.

Commands

  • /deeprefine — run the default agent-native pending-query workflow.
  • /deeprefine:review <query> — review graph evidence for a single query without graph writes.
  • /deeprefine:apply <request> — apply validated refinement actions only from a valid trace and refinement file.

When extension changes are installed or linked, restart Gemini CLI before checking /extensions list or /commands list.

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. 4d ago First seen · 27 lines · 372 tokens per session scan A b6414f81945f

Subscribe to this mod's changes

DeepRefine-Skill GEMINI.md is an instructions file published in the GitHub repository HKUST-KnowComp/DeepRefine-Skill (93 stars, last pushed 11d ago), licensed MIT. It adds 372 tokens to every session, about $0.0019 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.