Borrowing it
Nothing to install: this file belongs to HKUST-KnowComp/DeepRefine-Skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HKUST-KnowComp/DeepRefine-Skill/main/GEMINI.mdgit clone --depth 1 https://github.com/HKUST-KnowComp/DeepRefine-SkillWrote 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/instructions/hkust-knowcomp/deeprefine-skill/gemini-md)<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/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/instructions/hkust-knowcomp/deeprefine-skill/gemini-md"><img src="https://agentmods.dev/badge/instructions/hkust-knowcomp/deeprefine-skill/gemini-md.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 | $0.00372 | $0.00372 |
| Opus 5.5 | $0.00149 | $0.00149 |
| Sonnet 5.5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
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 2mo 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
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
- Prefer the agent-native DeepRefine loop over the terminal-only
deeprefine refinecommand unless the user explicitly requests CLI / FAISS mode. - Follow the same control flow as
DeepRefine.refine()from DeepRefine. - Import Graphify memory with
deeprefine history sync-memorywhen running the default queue workflow. - Process pending history entries one by one.
- Use Graphify query results and k-hop expansion over
graphify-out/graph.jsonas retrieval evidence. - Create and maintain a valid
loop_trace_<query_id>.jsonbefore applying graph updates. - Review proposed
<refinement>...</refinement>actions before applying them. - Apply graph updates only through
deeprefine apply; do not hand-editgraphify-out/graph.json. - Store DeepRefine artifacts under
graphify-out/.deeprefine/. - If graph artifacts are missing, ask the user to run
/graphify .and/graphify ./ --wikifirst.
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.
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.
- 2mo ago First seen · 27 lines · 372 tokens per session scan A b6414f81945f
DeepRefine-Skill GEMINI.md is an instructions file published in the GitHub repository HKUST-KnowComp/DeepRefine-Skill (90 stars, last pushed 2mo ago), licensed MIT. It adds 372 tokens to every session, about $0.0015 per session on Opus 5.5. 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.
DeepRefine-Skill GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| DeepRefine-Skill GEMINI.mdHKUST-KnowComp/DeepRefine-Skill | Instructions file | 90 | 2mo ago | MIT | A | 372 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |