code-deep-research

A research workflow for assessing whether an open-source GitHub project should be adopted in AgenticX.

In plain words
What is it for?
Use it to produce an evidence-based adopt, partially adopt, or do not adopt recommendation for a GitHub repository.
Why use it?
It requires checking the upstream code at a fixed commit and comparing it with verified local code before recommending a change.

Skill for Claude CodeCodexCursor

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/demondamon/agenticx/code-deep-research
Any agent
npx skills add DemonDamon/AgenticX --skill code-deep-research
Clone the repo
git clone --depth 1 https://github.com/DemonDamon/AgenticX

Made for: Claude Code, Codex, Cursor.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 685 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00037 $0.00685
Opus 5 $0.00018 $0.00342
Sonnet 5 $0.00007 $0.00137
Haiku 4.5 $0.00004 $0.00068

Measured 2d ago against content hash 04f0b7c3e9f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-deep-research 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.

.cursor/skills/code-deep-research/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Deep Research

Overview

Research an upstream repository from a locked commit, compare it with verified AgenticX code, and make an evidence-backed adoption decision. The local upstream clone is the source of truth; MCP tools accelerate discovery but never replace source verification.

When to Use

Use for:

  • /codedeepresearch requests.
  • “调研这个 GitHub 项目能否集成进 AgenticX”。
  • Comparing an upstream framework, SDK, agent runtime, tool, memory, planner, UI, or protocol with AgenticX.
  • Producing ADOPT, SELECTIVE_ADOPT, or DO_NOT_ADOPT recommendations.

Do not use for:

  • Implementing an already-approved plan.
  • General web research without a required GitHub repository.
  • A quick API lookup or a review of one known source file.

Required References

Before taking research actions:

  1. Read WORKFLOW.md completely.
  2. Copy its S0–S8 status ledger into research/codedeepresearch/<repo_name>/meta.md.
  3. Read TEMPLATES.md before creating research artifacts.

Do not infer the workflow from this summary alone.

Non-Negotiable Rules

  • Clone the repository into research/codedeepresearch/<repo_name>/upstream/ and lock its SHA.
  • A failed clone blocks normal research. Do not emit Gap, Proposal, P0/P1, or an adoption verdict.
  • Verify implementation claims against local source using SHA + path + line range + symbol.
  • DeepWiki, GitHub MCP, and ZRead are optional accelerators. Discover their schemas before use; failure must follow the documented fallback.
  • ZRead quota failure never makes a successful local-source study “incomplete”.
  • Do not modify AgenticX production code during research.
  • Do not invent benchmarks, user needs, issue numbers, runtime validation, or repository behavior.
  • Do not create an implementation plan or code task unless the user separately requests implementation.

Decision Rule

Determine Gap priority first, then derive the verdict:

  • ADOPT: at least one valid P0.
  • SELECTIVE_ADOPT: no P0, but at least one evidence-backed P1 with a real user problem.
  • DO_NOT_ADOPT: only P2/NO-GAP, unvalidated demand, or insufficient value.

Read the full file on GitHub · 68 lines

Files

What ships with it

2 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. 2d ago First seen · 68 lines · 37 tokens per session scan A 04f0b7c3e9f4

Subscribe to this mod's changes

code-deep-research is a skill published in the GitHub repository DemonDamon/AgenticX (219 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 685 once invoked, about $0.0002 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.