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 skills/dean0x/devflow/research-codebasenpx skills add dean0x/devflow --skill research-codebasegit clone --depth 1 https://github.com/dean0x/devflowWhat 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 | $0.00021 | $0.00856 |
| Opus 5 | $0.00010 | $0.00428 |
| Sonnet 5 | $0.00004 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
research-codebase 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Research
Local codebase research for finding patterns, tracing call flows, and mapping module dependencies. No external web access — all evidence comes from the local codebase.
Iron Law
CITE CODE, NOT ASSUMPTIONS
Every claim about the codebase must have file:line evidence. Patterns require 3+ examples to count as patterns. "I believe this is the pattern" without citation is a research failure. If you can't find the evidence, say so — don't invent it.
Trust Tier
trusted — Local code is the authoritative source. All findings carry maximum confidence.
When This Activates
Loaded by Research agent when RESEARCH_TYPE is codebase. Covers:
- Finding existing patterns before implementing new features
- Tracing call chains to understand data flow
- Mapping module boundaries and dependencies
- Identifying conventions used across the codebase
Methodology
Step 1: Define Scope
Before reading anything, define the scope:
- Target area (directory, module, or concept)
- What you are looking for (patterns, functions, conventions, dependencies)
- What files are likely NOT relevant (test fixtures, generated files)
Step 2: Structural Scan
Use Glob and Grep to build a map before reading:
Glob: Find all files matching the area (e.g., src/auth/**/*.ts)
Grep: Search for key terms, function names, type names
Use this to build a candidate file list. Do not read more than 15 files total.
Step 3: Deep Read (Targeted)
Read only the files that the structural scan identified as relevant. Read targeted ranges — not entire files — unless the file is under 50 lines.
Step 4: Pattern Extraction
For each observed pattern:
- Record the first 3 occurrences with file:line
- Describe the pattern in one sentence
- Note any deviations from the pattern
Only declare a pattern after finding 3+ consistent examples.
Step 5: Cross-Reference
Before finalizing findings:
- Check if patterns conflict with each other
- Identify exceptions to patterns you found
- Note if something appears in tests vs production code
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.
- yesterday First seen · 136 lines · 21 tokens per session scan A b49afd52f18b
research-codebase is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 856 once invoked, about $0.0001 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 skills, from other repositories
data-engineering
Skill "data-engineering" from fengshao1227/ccg-workflow, covering 数据工程域 · data engineering, 域概览, 数据管道编排, 框架对比 and airflow 核心模式.
verify-change
变更校验关卡。分析代码变更，检测文档同步状态，评估变更影响范围。当用户提到变更检查、文档同步、代码审查、提交前检查、diff分析时使用。在设计级变更、重构完成时自动触发。.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
gen-docs
文档生成器。自动分析模块结构，生成 README.md 和 DESIGN.md 骨架。当用户提到生成文档、创建README、创建DESIGN、文档骨架、文档模板时使用。在新建模块开始时自动触发。.
verify-module
模块完整性校验关卡。扫描目录结构、检测缺失文档、验证代码与文档同步。当用户提到模块校验、文档检查、结构完整性、README检查、DESIGN检查时使用。在新建模块完成时自动触发。.