Agent skill

Research Codebase

by bastani-inc in bastani-inc/atomic

Document codebase as-is with research directory for historical context.

Custom licenceAuto-check passed

Install Research Codebase

skills CLI
$ npx skills add bastani-inc/atomic --skill research-codebase -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bastani-inc/atomic research-codebase --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bastani-inc/atomic.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/workflows/skills/research-codebase .claude/skills/research-codebase && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
research-codebase
GitHub stars
846
Token cost
~3.8k tokens
SKILL.md length
1,789 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
Custom licence

At a glance

Document codebase as-is with research directory for historical context.

  • Works in 6 steps: Read any directly mentioned files first → Determine the compatibility posture → Analyze and decompose the research… → …
  • SKILL.md covers Steps to follow after…, Important notes: and Final Output
  • Calls git, curl and gh; reaches github.com

What it does

Research Codebase is an agent skill from bastani-inc/atomic. Document codebase as-is with research directory for historical context.

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The verifiable coding agent runtime. Define your coding agent's process in natural language with stages, checks, and approval gates instead of hoping it follows your…

Example prompts

  • “/research-codebase”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read any directly mentioned files first
  2. Determine the compatibility posture
  3. Analyze and decompose the research question
  4. Spawn parallel sub-agent tasks
  5. Wait for all sub-agents to complete and synthesize
  6. Generate research document

What it can do on your machine

Read from SKILL.md and the folder at commit 1ec2fe8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • curl
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • llmstxt.org
    • developers.cloudflare.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Research Codebase loads about 3.8k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 1,789 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,789 words (~3,830 tokens).

“You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings.”

— opening of SKILL.md by bastani-inc, Custom licence
name
research-codebase

Read the full SKILL.md on GitHub

Files

Just SKILL.md in packages/workflows/skills/research-codebase of bastani-inc/atomic.

Open the folder on GitHubat commit 1ec2fe8

Compare with similar skills

Research Codebase next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Research Codebase compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research Codebase this skillbastani-inc/atomic846—~3.8kAutomated safety check: PassCustom licence
Directory Submissionscoreyhaines31/marketingskills54k2 repos~6.3kAutomated safety check: PassMIT
Brilliant Directories AutomationComposioHQ/awesome-claude-skills77k3 repos~783Automated safety check: PassNone
SEO Directory Backlinkssickn33/agentic-awesome-skills47k1 repos~6.5kAutomated safety check: PassMIT
People Directorysickn33/agentic-awesome-skills47k1 repos~4.5kAutomated safety check: PassMIT
Deploying Active Directory Honeytokensmukul975/Anthropic-Cybersecurity-Skills34k—~2.4kAutomated safety check: PassApache-2.0

Similar skills

  • Directory Submissions

    coreyhaines31/marketingskills

    When the user wants to submit their product to startup, SaaS, AI, agent, MCP, no-code, or review directories for backlinks, domain rating, and discovery.

    54k GitHub starsUsed in 2 repos~6.3k tokens
    Marketing & SEOAuto-check passed
  • Brilliant Directories Automation

    ComposioHQ/awesome-claude-skills

    Automate Brilliant Directories tasks via Rube MCP (Composio).

    77k GitHub starsUsed in 3 repos~783 tokens
    Productivity & AutomationAuto-check passed
  • SEO Directory Backlinks

    sickn33/agentic-awesome-skills

    Directory and backlink register: platform, domain, target URL, follow attribute, authority and spam scores, approval and NAP-match status.

    47k GitHub starsUsed in 1 repo~6.5k tokens
    Marketing & SEOAuto-check passed
  • People Directory

    sickn33/agentic-awesome-skills

    Employee master record: name, employee id, department, job title, grade, manager, employment type, contact and emergency details, access role, start and end dates, status.

    47k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed
  • Deploying Active Directory Honeytokens

    mukul975/Anthropic-Cybersecurity-Skills

    Deploys deception-based honeytokens in Active Directory including fake privileged accounts with AdminCount=1, fake SPNs for Kerberoasting detection (honeyroasting), decoy GPOs with cpassword traps…

    34k GitHub stars~2.4k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Analyzing Active Directory Acl Abuse

    mukul975/Anthropic-Cybersecurity-Skills

    Detect dangerous ACL misconfigurations in Active Directory using ldap3 to identify GenericAll, WriteDACL, and WriteOwner abuse paths

    34k GitHub stars~1.1k tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from bastani-inc/atomic

All 15 skills in this repo
  • How

    bastani-inc/atomic

    A skill your agent uses for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is…

    846 GitHub starsUsed in 3 repos~2.3k tokens
    Auto-check passed
  • Liteparse

    bastani-inc/atomic

    A skill your agent uses whenever a task involves a document file (PDF, DOCX, PPTX, XLSX, or image) and you need to read it or pull text, tables, or specific values out of it — to answer a question…

    846 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Bun

    bastani-inc/atomic

    A skill your agent uses when building, testing, and deploying JavaScript/TypeScript applications.

    846 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Feedback

    bastani-inc/atomic

    Draft, revise and post privacy-scrubbed Atomic bug reports or enhancements through ordinary conversation.

    846 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Prek

    bastani-inc/atomic

    A skill your agent uses when setting up or running hooks with prek in any repository.

    846 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • TDD

    bastani-inc/atomic

    Test-driven development with red-green-refactor loop, plus a value gate and audit workflow for tests.

    846 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Questions about Research Codebase

What does Research Codebase do?

Document codebase as-is with research directory for historical context. Research Codebase is an agent skill from bastani-inc/atomic. Document codebase as-is with research directory for historical context.

How do I install Research Codebase in Claude Code?

Run `npx skills add bastani-inc/atomic --skill research-codebase -a claude-code`. Or copy the skill folder (packages/workflows/skills/research-codebase in bastani-inc/atomic) into .claude/skills/research-codebase in your project. Claude Code loads it when a task matches its description.

How do I install Research Codebase in Codex?

Run `npx skills add bastani-inc/atomic --skill research-codebase -a codex`. Or copy the skill folder (packages/workflows/skills/research-codebase in bastani-inc/atomic) into .agents/skills/research-codebase in your project. Codex loads it when a task matches its description.

Can I use Research Codebase in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bastani-inc/atomic --skill research-codebase -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-codebase, .gemini/skills/research-codebase, .github/skills/research-codebase and .opencode/skills/research-codebase in your project.

What does Research Codebase need to run?

Going by SKILL.md and its folder, Research Codebase needs the command-line tools its instructions call (git, curl and gh).

Does Research Codebase access the network?

SKILL.md names 3 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: llmstxt.org and developers.cloudflare.com. This is read from the text; nothing was executed.

Is Research Codebase safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Research Codebase use?

Research Codebase has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Research Codebase use?

About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Research Codebase?

Skills that share tags, products or a category with Research Codebase: Directory Submissions (coreyhaines31/marketingskills, 54k stars), Brilliant Directories Automation (ComposioHQ/awesome-claude-skills, 77k stars), SEO Directory Backlinks (sickn33/agentic-awesome-skills, 47k stars) and People Directory (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research Codebase?

bastani-inc (a GitHub organization) maintains it in bastani-inc/atomic, which has 846 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 8, 2026.

Source: bastani-inc/atomic on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.