deeprefine

deeprefine is a skill for Claude Code, Codex from HKUST-KnowComp/DeepRefine-Skill. It costs 73 tokens per session (1,526 once invoked), scanned A, a copy of deeprefine, MIT.

An adapter for DeepRefine, a workflow for reviewing and improving Graphify or LLM-Wiki knowledge graphs. It connects that workflow to the DeepSeek Harness command-line tool.

In plain words
What is it for?
Use it to inspect, refine, repair, or review a knowledge graph, or apply a previously reviewed refinement.
Why use it?
It provides a defined process for diagnosing graph issues and pauses for review before changing graph data.

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/hkust-knowcomp/deeprefine-skill/dsh_skill
Any agent
npx skills add HKUST-KnowComp/DeepRefine-Skill --skill dsh_skill
Clone the repo
git clone --depth 1 https://github.com/HKUST-KnowComp/DeepRefine-Skill

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 deeprefine

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkust-knowcomp/deeprefine-skill/dsh_skill.svg)](https://agentmods.dev/skills/hkust-knowcomp/deeprefine-skill/dsh_skill)
Your own site
<a href="https://agentmods.dev/skills/hkust-knowcomp/deeprefine-skill/dsh_skill"><img src="https://agentmods.dev/badge/skills/hkust-knowcomp/deeprefine-skill/dsh_skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,526 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00073 $0.01526
Opus 5 $0.00036 $0.00763
Sonnet 5 $0.00015 $0.00305
Haiku 4.5 $0.00007 $0.00153

Measured 5d ago against content hash 905738d00195, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deeprefine 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 5d 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.

Origin

This is a copy

89% identical to deeprefine — 47 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

deeprefine_skill/dsh_skill/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepRefine - DeepSeek Harness (dsh) Adapter

This file is the dsh-specific entrypoint. It keeps the platform rules small and loads longer DeepRefine procedure details only when needed:

Do not reimplement or shorten the algorithm from memory. Load the relevant reference file before executing that part of the workflow.

dsh Invocation

Trigger this skill when the user:

  • explicitly invokes /deeprefine;
  • asks to refine, improve, diagnose, repair, inspect, or review a Graphify knowledge graph;
  • asks to apply a previously reviewed DeepRefine refinement.

Run from the knowledge-base project root, where graphify-out/graph.json exists. If the user is planning or asking how DeepRefine works, explain the workflow and do not mutate files.

If deeprefine is unavailable, tell the user to install it:

pip install deeprefine-cli

For source development:

pip install -e /path/to/DeepRefine-Skill

Hard Safety Policy

A normal /deeprefine invocation is dry-run only and MUST NEVER call deeprefine apply.

The default workflow must stop after:

  1. deeprefine loop validate
  2. deeprefine review
  3. showing the proposed actions and HIGH/MEDIUM/LOW review report to the user

Then ask for explicit approval.

Only if the user's next message explicitly says to approve/apply/write the graph may you run:

deeprefine apply --trace-file ... --refinement-file ...
deeprefine loop finish --trace-file ... --refinement-file ...

Do not treat any of these as approval:

  • generation of a <refinement> block;
  • a valid loop_trace_<query_id>.json;
  • a prior user message;
  • a successful deeprefine review.

Read the full file on GitHub · 188 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 188 lines · 73 tokens per session scan A 905738d00195

Subscribe to this mod's changes

deeprefine is a skill published in the GitHub repository HKUST-KnowComp/DeepRefine-Skill (93 stars, last pushed 12d ago), licensed MIT. It adds 73 tokens to every session and 1,526 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to deeprefine, differing in 47 lines, and is treated as a copy.

Related

Other skills, from other repositories

llm-wiki

Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).

zosmaai/pi-llm-wiki · 52 tokens

braindb

Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.

dimknaf/braindb · 36 tokens

braindb-agent

Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.

dimknaf/braindb · 40 tokens

braindb-custom-profile

How to author a BrainDB custom profile — prompt add/replace fragments and an optional keyless ingestor — that shapes wiki naming/structure and feeds a custom ingestion source, with zero effect on defaults when inactive.

dimknaf/braindb · 49 tokens

mindbase

Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…

frankchu91/mindbase-llm-wiki · 105 tokens

run-wenlan-app

Build, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS (WKWebView) or Windows (WebView2). Use when asked to run or start the app, verify a UI change in the real running app (not just tests), or take a screenshot of it.

7xuanlu/wenlan · 71 tokens