Agent skill

Code Necromancer

by curiositech in curiositech/some_claude_skills

Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases.

MITAuto-check: notesDevelopment

Install Code Necromancer

skills CLI
$ npx skills add curiositech/some_claude_skills --skill code-necromancer -a claude-code

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

GitHub CLI
$ gh skill install curiositech/some_claude_skills code-necromancer --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/curiositech/some_claude_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/code-necromancer .claude/skills/code-necromancer && 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
code-necromancer
GitHub stars
243
Token cost
~1.6k tokens
SKILL.md length
551 words
Files
13 (incl. scripts, references)
Skills in repo
108
Repo updated
First seen
Licence
MIT

At a glance

Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases.

  • Works in 9 steps: ARCHAEOLOGY → RESURRECTION → REJUVENATION → …
  • Tasks that involve Legacy modernization
  • SKILL.md covers When to Activate, The Three Phases, Key Commands and Anti-Patterns to Avoid, plus 3 more sections
  • Runs Shell scripts from its folder; calls npm, gh and pip

What it does

Code Necromancer is an agent skill from curiositech/some_claude_skills. Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases. Activate on "legacy code", "inherited codebase", "no documentation", "technical debt", "resurrect", "modernize". NOT for greenfield projects or well-documented active codebases.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including scripts and reference files (for example `.claude-plugin/plugin.json`, `CHANGELOG.md` and `references/archaeology-guide.md`).

It sits in Development, covering Legacy modernization and Technical debt. The repository describes itself as: Claude skills that make my life easier. The licence is MIT.

When your agent uses it

  • Tasks that involve Legacy modernization
  • Tasks that involve Technical debt

Example prompts

  • “legacy code”
  • “inherited codebase”
  • “no documentation”
  • “/code-necromancer”

Requirements

  • Python 3
  • Node.js
  • A Bash shell
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, WebFetch, Grep, Glob

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. ARCHAEOLOGY
  2. RESURRECTION
  3. REJUVENATION
  4. Premature Resurrection
  5. Scope Creep
  6. Big Bang Updates
  7. Ignoring Tests
  8. Undocumented Changes
  9. Trusting Old Documentation

What it can do on your machine

Read from SKILL.md and the folder at commit 6713fc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash
    • WebFetch
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • npm
    • gh
    • pip
    • go

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

  • Network

    No URLs in SKILL.md. Its commands use npm, gh and pip, which can reach the network depending on how they are called.

    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

Code Necromancer loads about 1.6k tokens when it runs, and up to ~9.8k if it reads all its reference files. Until then it costs about 81 tokens; SKILL.md has 551 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9.8k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Bash, WebFetch, Grep, Glob

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); the scripts in this folder are not scanned.

SKILL.md

The full file from curiositech/some_claude_skills at commit 6713fc7, republished under its MIT licence (© curiositech). 551 words, ~1,584 tokens.

Download SKILL.mdSave it as .claude/skills/code-necromancer/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
code-necromancer
description
Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases. Activate on "legacy code", "inherited codebase", "no documentation", "technical debt", "resurrect", "modernize". NOT for greenfield projects or well-documented active codebases.
allowed-tools
Read, Write, Edit, Bash, WebFetch, Grep, Glob
metadata.category
Code Quality & Testing
metadata.tags
legacy, modernization, technical-debt, archaeology, refactoring

Code Necromancer

Tagline: Raise dead codebases from the grave

Systematic framework for understanding, resurrecting, and modernizing legacy codebases.

When to Activate

✅ Use when:

  • Inheriting a codebase with 5+ repos and no documentation
  • Resurrecting a product dormant for 2+ years
  • Joining a company with significant technical debt and tribal knowledge loss
  • Performing due diligence on acquired codebases
  • Modernizing legacy systems without breaking existing functionality

❌ NOT for:

  • Greenfield projects (start fresh instead)
  • Well-documented active codebases
  • Simple bug fixes in maintained systems

The Three Phases

Phase 1: ARCHAEOLOGY

Objective: Create a complete map before touching anything.

OutputDescription
repo-inventory.jsonAll repos with metadata, languages, activity
dependency-graph.mmdInter-repo and external dependencies
architecture-diagram.mmdVisual system topology
tech-stack-matrix.mdLanguage/framework versions per repo
maturity-assessment.mdCode quality, test coverage, docs quality
missing-pieces.mdGaps, orphaned repos, broken integrations

Process: Inventory → Deep Scan → Cross-Reference → Visualize → Assess

→ See references/archaeology-guide.md for detailed techniques.

Phase 2: RESURRECTION

Objective: Get the system running in development.

OutputDescription
dependency-audit.mdOutdated packages, vulnerabilities, breaking changes
environment-variables.mdAll required env vars with defaults
secrets-needed.mdAPI keys, certs, OAuth credentials
infrastructure-status.mdCloud resources, what exists vs deleted
resurrection-blockers.mdCritical issues preventing launch
integration-tests/Tests verifying components work and communicate

Process: Audit Dependencies → Map Environment → Check Infrastructure → Write Tests → Document Blockers

→ See references/integration-test-patterns.md for resurrection test patterns.

Phase 3: REJUVENATION

Objective: Modernize while maintaining feature parity.

OutputDescription
security-recommendations.mdVulnerability fixes, compliance
modernization-roadmap.mdPrioritized upgrades with effort estimates
architecture-improvements.mdScalability, performance, maintainability

Process: Security First → Infrastructure (containerize, CI/CD) → Code Quality → Architecture

Key Commands

bash
# List all repos in org
gh repo list ORG --limit 1000 --json name,primaryLanguage,pushedAt

# Dependency analysis
npm audit && npm outdated      # Node.js
pip list --outdated && safety check  # Python
go mod graph                    # Go

# Find env vars in code
grep -rn 'process\.env\|os\.environ' --include="*.js" --include="*.py"

→ See references/framework-detection.md for framework/stack identification. → See references/infrastructure-mapping.md for cloud resource discovery. → See references/dependency-patterns.md for dependency detection.

Anti-Patterns to Avoid

1. Premature Resurrection

What it looks like: Running npm install before reading any code Why it's wrong: You'll fix the same bug 5 times; dependencies have changed Fix: Complete archaeology first; understand before touching

2. Scope Creep

What it looks like: "Let's also refactor while we're here" Why it's wrong: Scope explosion; never actually resurrect Fix: Strict phase separation; refactoring is Phase 3

Show full SKILL.md (225 more words)Show less
3. Big Bang Updates

What it looks like: Update all dependencies in one commit Why it's wrong: Something breaks, no idea what Fix: Update incrementally; test after each

4. Ignoring Tests

What it looks like: "It runs, ship it" Why it's wrong: Regression city; no baseline for changes Fix: Write resurrection tests as you go; they prove progress

5. Undocumented Changes

What it looks like: "I fixed it but forgot what I changed" Why it's wrong: Tribal knowledge returns; next person is you in 6 months Fix: Document everything you learn and change

6. Trusting Old Documentation

What it looks like: Following README from 2019 Why it's wrong: APIs change, services get deprecated Fix: Verify every instruction; documentation lies

Success Metrics

Archaeology Complete When:
  • All repos cataloged with metadata
  • Dependency graph visualized
  • Architecture diagram created
  • Core vs peripheral repos identified
  • Missing pieces documented
Resurrection Complete When:
  • All services start locally
  • Services can communicate with each other
  • Integration tests pass
  • At least one full user flow works
Rejuvenation Complete When:
  • No critical security vulnerabilities
  • All dependencies reasonably current
  • CI/CD pipeline working
  • Documentation current
  • Team can develop new features

References

→ references/archaeology-guide.md - Deep code archaeology techniques → references/dependency-patterns.md - Dependency detection across ecosystems → references/framework-detection.md - Framework/stack identification → references/infrastructure-mapping.md - Cloud resource discovery → references/integration-test-patterns.md - Resurrection test patterns

Templates

→ templates/repo-inventory.json - Repository catalog → templates/archaeology-report.md - Phase 1 output → templates/resurrection-plan.md - Phase 2 output → templates/rejuvenation-roadmap.md - Phase 3 output

© curiositech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (scripts, references) in .claude/skills/code-necromancer of curiositech/some_claude_skills.

  • SKILL.md
  • .claude-plugin/plugin.json
  • CHANGELOG.md
  • references/archaeology-guide.md
  • references/dependency-patterns.md
  • references/framework-detection.md
  • references/infrastructure-mapping.md
  • references/integration-test-patterns.md
  • scripts/analyze-repo.sh
  • scripts/scan-repos.sh
  • templates/archaeology-report.md
  • templates/repo-inventory.json
  • templates/resurrection-plan.md

Open the folder on GitHubat commit 6713fc7

Compare with similar skills

Code Necromancer 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.

Code Necromancer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Necromancer this skillcuriositech/some_claude_skills243—~1.6kAutomated safety check: NotesMIT
Code Refactoring Workflowluongnv89/claude-howto42k—~3.1kAutomated safety check: PassMIT
Rails Upgrade Assistantombulabs/claude-code_rails-upgrade-skill387—~2.7kAutomated safety check: PassMIT
Fowler-Style Refactoringlhfer/claude-howto-zh-cn2.3k—~156Automated safety check: PassMIT
Refactoring Skill (Vietnamese)luongnv89/claude-howto42k—~3.1kAutomated safety check: PassMIT
Legacy ModernizerJeffallan/claude-skills12k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Code Refactoring Workflow

    luongnv89/claude-howto

    Guides systematic, test-backed refactoring in the style of Martin Fowler, moving through research, planning and small incremental changes with your approval at each phase.

    42k GitHub stars~3.1k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Rails Upgrade Assistant

    ombulabs/claude-code_rails-upgrade-skill

    Analyzes a Rails app and builds an upgrade report with breaking changes, deprecations and step-by-step migration guides, one version at a time from Rails 2.3 through 8.1.

    387 GitHub stars~2.7k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Fowler-Style Refactoring

    lhfer/claude-howto-zh-cn

    基于 Martin Fowler 方法论做系统化重构。Use when users ask to refactor code, improve structure, reduce technical debt, clean up legacy code, or improve maintainability.

    2.3k GitHub stars~156 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Refactoring Skill (Vietnamese)

    luongnv89/claude-howto

    Vietnamese edition of a systematic refactoring skill based on Martin Fowler's book, working in approved phases with small, test-backed changes.

    42k GitHub stars~3.1k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Legacy Modernizer

    Jeffallan/claude-skills

    Plans incremental migrations of aging systems with the strangler fig pattern, using dependency maps, rollback plans, characterization tests and gradual traffic shifts.

    12k GitHub stars~1.6k tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • Tech Debt Tracker

    alirezarezvani/claude-skills

    Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans.

    28k GitHub starsUsed in 1 repo~1.2k tokens
    DevelopmentAuto-check passed

More from curiositech/some_claude_skills

All 108 skills in this repo
  • Crisis Detection Intervention AI

    curiositech/some_claude_skills

    Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols.

    243 GitHub starsUsed in 3 repos~3.8k tokens
    Auto-check passed
  • Form Validation Architect

    curiositech/some_claude_skills

    End-to-end form handling with react-hook-form, Zod schemas, validation patterns, error messaging, field arrays, and multi-step wizards.

    243 GitHub stars~3.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Competitive Cartographer

    curiositech/some_claude_skills

    Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations.

    243 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • GitHub Actions Pipeline Builder

    curiositech/some_claude_skills

    Build production CI/CD pipelines with GitHub Actions. An agent skill from curiositech/some_claude_skills.

    243 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check: notes
  • Computer Vision Pipeline

    curiositech/some_claude_skills

    Build production computer vision pipelines for object detection, tracking, and video analysis.

    243 GitHub starsUsed in 1 repo~4k tokens
    Auto-check passed
  • Design Archivist

    curiositech/some_claude_skills

    Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction…

    243 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Categories

Questions about Code Necromancer

What does Code Necromancer do?

Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases. Code Necromancer is an agent skill from curiositech/some_claude_skills. Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases.

When should I use Code Necromancer?

Code Necromancer fits situations like: tasks that involve Legacy modernization; tasks that involve Technical debt.

How do I install Code Necromancer in Claude Code?

Run `npx skills add curiositech/some_claude_skills --skill code-necromancer -a claude-code`. Or copy the skill folder (.claude/skills/code-necromancer in curiositech/some_claude_skills) into .claude/skills/code-necromancer in your project. Claude Code loads it when a task matches its description.

How do I install Code Necromancer in Codex?

Run `npx skills add curiositech/some_claude_skills --skill code-necromancer -a codex`. Or copy the skill folder (.claude/skills/code-necromancer in curiositech/some_claude_skills) into .agents/skills/code-necromancer in your project. Codex loads it when a task matches its description.

Can I use Code Necromancer 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 curiositech/some_claude_skills --skill code-necromancer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-necromancer, .gemini/skills/code-necromancer, .github/skills/code-necromancer and .opencode/skills/code-necromancer in your project.

What does Code Necromancer need to run?

Going by SKILL.md and its folder, Code Necromancer needs a shell for the scripts in its folder and the command-line tools its instructions call (npm, gh, pip and go). Our summary lists: Python 3; Node.js; A Bash shell. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, WebFetch, Grep, Glob.

Does Code Necromancer access the network?

SKILL.md contains no URLs. Its commands use npm, gh and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Code Necromancer safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Code Necromancer use?

Code Necromancer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Necromancer use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.3k tokens, read only when the agent opens those files.

What are the alternatives to Code Necromancer?

Skills that share tags, products or a category with Code Necromancer: Code Refactoring Workflow (luongnv89/claude-howto, 42k stars), Rails Upgrade Assistant (ombulabs/claude-code_rails-upgrade-skill, 387 stars), Fowler-Style Refactoring (lhfer/claude-howto-zh-cn, 2.3k stars) and Refactoring Skill (Vietnamese) (luongnv89/claude-howto, 42k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Necromancer?

curiositech (a GitHub organization) maintains it in curiositech/some_claude_skills, which has 243 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on September 6, 2026.

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