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 instructions/hkust-knowcomp/deeprefine-skill/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.svg" alt="Measured on agentmods" 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 | $0.00372 | $0.00372 |
| Opus 5 | $0.00186 | $0.00186 |
| Sonnet 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 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.
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.
- 4d 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 (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.
Other instructions, from other repositories
kiwifs AGENTS.md
AGENTS.md instructions for kiwifs/kiwifs, covering agents.md, project overview, repository structure, build & run and full build (ui + go binary).
llm-wiki-agent AGENTS.md
AGENTS.md instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki-agent CLAUDE.md
Claude Code instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, slash commands (claude code), directory layout, page format and ingest workflow.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
memvid CLAUDE.md
Claude Code instructions for memvid/memvid, covering claude.md, project overview, architecture, core components and file format (.mv2).
obsidian-llm-wiki AGENTS.md
AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.