custom-instructions-from-codebase

custom-instructions-from-codebase is a skill for Claude Code, Codex from OKHP3/skillz. It costs 58 tokens per session (1,812 once invoked), scanned A, a copy of generate-custom-instructions-from-codebase, MIT.

A tool that compares two versions of a code project and writes instructions for GitHub Copilot to follow during migrations, refactoring, or upgrades.

In plain words
What is it for?
Use it to compare branches, commits, or releases and document breaking changes, new conventions, outdated patterns, API changes, or configuration updates.
Why use it?
It reduces the manual work of finding changed patterns and explaining how future code should match the newer version.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare branches, commits, or releases and document breaking changes, new conventions, outdated patterns, API changes, or configuration updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/okhp3/skillz/custom-instructions-from-codebase
View source ↗ OKHP3/skillz
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.

Any agent
npx skills add OKHP3/skillz --skill custom-instructions-from-codebase
Clone the repo
git clone --depth 1 https://github.com/OKHP3/skillz

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 custom-instructions-from-codebase

README.md
[![agentmods](https://agentmods.dev/badge/skills/okhp3/skillz/custom-instructions-from-codebase/github.svg)](https://agentmods.dev/skills/okhp3/skillz/custom-instructions-from-codebase)
Your own site
<a href="https://agentmods.dev/skills/okhp3/skillz/custom-instructions-from-codebase"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/custom-instructions-from-codebase/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for custom-instructions-from-codebase

Your own site · 80×15
<a href="https://agentmods.dev/skills/okhp3/skillz/custom-instructions-from-codebase"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/custom-instructions-from-codebase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% 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 5.1 $0.00058 $0.01812
Opus 5 $0.00029 $0.00906
Sonnet 5 $0.00012 $0.00362
Haiku 4.5 $0.00006 $0.00181

Measured 6d ago against content hash f8b1838ea1be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

custom-instructions-from-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 6d 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

94% identical to generate-custom-instructions-from-codebase — 2 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.

community/custom-instructions-from-codebase/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migration and Code Evolution Instructions Generator

Configuration Variables

${MIGRATION_TYPE="Framework Version|Architecture Refactoring|Technology Migration|Dependencies Update|Pattern Changes"}
<!-- Type of migration or evolution -->

${SOURCE_REFERENCE="branch|commit|tag"}
<!-- Source reference point (before state) -->

${TARGET_REFERENCE="branch|commit|tag"}  
<!-- Target reference point (after state) -->

${ANALYSIS_SCOPE="Entire project|Specific folder|Modified files only"}
<!-- Scope of analysis -->

${CHANGE_FOCUS="Breaking Changes|New Conventions|Obsolete Patterns|API Changes|Configuration"}
<!-- Main aspect of changes -->

${AUTOMATION_LEVEL="Conservative|Balanced|Aggressive"}
<!-- Level of automation for Copilot suggestions -->

${GENERATE_EXAMPLES="true|false"}
<!-- Include transformation examples -->

${VALIDATION_REQUIRED="true|false"}
<!-- Require validation before application -->

Generated Prompt

"Analyze code evolution between two project states to generate precise migration instructions for GitHub Copilot. These instructions will guide Copilot to automatically apply the same transformation patterns during future modifications. Follow this methodology:

### Phase 1: Comparative State Analysis

#### Structural Changes Detection
- Compare folder structure between ${SOURCE_REFERENCE} and ${TARGET_REFERENCE}
- Identify moved, renamed, or deleted files
- Analyze changes in configuration files
- Document new dependencies and removed ones

#### Code Transformation Analysis
${MIGRATION_TYPE == "Framework Version" ? 
  "- Identify API changes between framework versions
   - Analyze new features being used
   - Document obsolete methods/properties
   - Note syntax or convention changes" : ""}

${MIGRATION_TYPE == "Architecture Refactoring" ? 
  "- Analyze architectural pattern changes
   - Identify new abstractions introduced
   - Document responsibility reorganization
   - Note changes in data flows" : ""}

${MIGRATION_TYPE == "Technology Migration" ? 
  "- Analyze replacement of one technology with another
   - Identify functional equivalences
   - Document API and syntax changes
   - Note new dependencies and configurations" : ""}

#### Transformation Pattern Extraction
- Identify repetitive transformations applied
- Analyze conversion rules from old to new format
- Document exceptions and special cases
- Create before/after correspondence matrix

### Phase 2: Migration Instructions Generation

Create a `.github/copilot-migration-instructions.md` file with this structure:

\`\`\`markdown
# GitHub Copilot Migration Instructions

## Migration Context
- **Type**: ${MIGRATION_TYPE}
- **From**: ${SOURCE_REFERENCE} 
- **To**: ${TARGET_REFERENCE}
- **Date**: [GENERATION_DATE]
- **Scope**: ${ANALYSIS_SCOPE}

## Automatic Transformation Rules

### 1. Mandatory Transformations
${AUTOMATION_LEVEL != "Conservative" ? 
  "[AUTOMATIC_TRANSFORMATION_RULES]
   - **Old Pattern**: [OLD_CODE]
   - **New Pattern**: [NEW_CODE]
   - **Trigger**: When to detect this pattern
   - **Action**: Transformation to apply automatically" : ""}

### 2. Transformations with Validation
${VALIDATION_REQUIRED == "true" ? 
  "[TRANSFORMATIONS_WITH_VALIDATION]
   - **Detected Pattern**: [DESCRIPTION]
   - **Suggested Transformation**: [NEW_APPROACH]
   - **Required Validation**: [VALIDATION_CRITERIA]
   - **Alternatives**: [ALTERNATIVE_OPTIONS]" : ""}

### 3. API Correspondences
${CHANGE_FOCUS == "API Changes" || MIGRATION_TYPE == "Framework Version" ? 
  "[API_CORRESPONDENCE_TABLE]
   | Old API   | New API   | Notes     | Example        |
   | --------- | --------- | --------- | -------------- |
   | [OLD_API] | [NEW_API] | [CHANGES] | [CODE_EXAMPLE] | " : ""} |

### 4. New Patterns to Adopt
[DETECTED_EMERGING_PATTERNS]
- **Pattern**: [PATTERN_NAME]
- **Usage**: [WHEN_TO_USE] 
- **Implementation**: [HOW_TO_IMPLEMENT]
- **Benefits**: [ADVANTAGES]

### 5. Obsolete Patterns to Avoid
[DETECTED_OBSOLETE_PATTERNS]
- **Obsolete Pattern**: [OLD_PATTERN]
- **Why Avoid**: [REASONS]
- **Alternative**: [NEW_PATTERN]
- **Migration**: [CONVERSION_STEPS]

## File Type Specific Instructions

${GENERATE_EXAMPLES == "true" ? 
  "### Configuration Files
   [CONFIG_TRANSFORMATION_EXAMPLES]
   
   ### Main Source Files
   [SOURCE_TRANSFORMATION_EXAMPLES]
   
   ### Test Files
   [TEST_TRANSFORMATION_EXAMPLES]" : ""}

## Validation and Security

### Automatic Control Points
- Verifications to perform after each transformation
- Tests to run to validate changes
- Performance metrics to monitor
- Compatibility checks to perform

### Manual Escalation
Situations requiring human intervention:
- [COMPLEX_CASES_LIST]
- [ARCHITECTURAL_DECISIONS]
- [BUSINESS_IMPACTS]

## Migration Monitoring

### Tracking Metrics
- Percentage of code automatically migrated
- Number of manual validations required
- Error rate of automatic transformations
- Average migration time per file

### Error Reporting
How to report incorrect transformations to Copilot:
- Feedback patterns to improve rules
- Exceptions to document
- Adjustments to make to instructions

\`\`\`

### Phase 3: Contextual Examples Generation

${GENERATE_EXAMPLES == "true" ? 
  "#### Transformation Examples
   For each identified pattern, generate:
   
   \`\`\`
   // BEFORE (${SOURCE_REFERENCE})
   [OLD_CODE_EXAMPLE]
   
   // AFTER (${TARGET_REFERENCE}) 
   [NEW_CODE_EXAMPLE]
   
   // COPILOT INSTRUCTIONS
   When you see this pattern [TRIGGER], transform it to [NEW_PATTERN] following these steps: [STEPS]
   \`\`\`" : ""}

### Phase 4: Validation and Optimization

#### Instructions Testing
- Apply instructions on test code
- Verify transformation consistency
- Adjust rules based on results
- Document exceptions and edge cases

#### Iterative Optimization  
${AUTOMATION_LEVEL == "Aggressive" ? 
  "- Refine rules to maximize automation
   - Reduce false positives in detection
   - Improve transformation accuracy
   - Document lessons learned" : ""}

### Final Result

Migration instructions that enable GitHub Copilot to:
1. **Automatically apply** the same transformations during future modifications
2. **Maintain consistency** with newly adopted conventions  
3. **Avoid obsolete patterns** by automatically proposing alternatives
4. **Accelerate future migrations** by capitalizing on acquired experience
5. **Reduce errors** by automating repetitive transformations

These instructions transform Copilot into an intelligent migration assistant, capable of reproducing your technology evolution decisions consistently and reliably.
"

Read the full file on GitHub · 241 lines

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. 6d ago First seen · 241 lines · 58 tokens per session scan A f8b1838ea1be

Subscribe to this mod's changes

custom-instructions-from-codebase is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,812 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to generate-custom-instructions-from-codebase, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

release-skills

A release workflow for preparing and publishing a new version of a software project. A release is a named version that may include updated version files, release notes, tags, or a GitHub Release.

JimLiu/baoyu-skills · 87 tokens

ship

Commit, push, and optionally create or update a PR for the current staged changes. Use when the user asks to "ship", "ship it", "ship changes", "commit push and PR", or "ship this".

tobihagemann/turbo · 47 tokens

branch-and-worktree-workflow

Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…

cbrock84/headcount · 70 tokens

stage

Stage implementation changes for commit with precise file selection. Use when the user asks to "stage changes", "stage files", "add files to staging", or "prepare changes for commit".

tobihagemann/turbo · 39 tokens

semantic-szz-analyzer

Identify bug-introducing commits using semantic analysis that extends traditional SZZ algorithm. Distinguishes semantic changes from refactorings or code movements using control-flow and data-flow similarity analysis. Use when analyzing bug-fix commits to trace back to bug-introducing changes, investigating software…

ArabelaTso/Skills-4-SE · 96 tokens

szz-bug-introducing-commit-identifier

Identifies bug-introducing commits using SZZ-style analysis based on bug-fixing commits, commit history, and code blame information. Use this skill when you need to trace bugs back to their origin, identify which commits introduced bugs, analyze bug-fix commits to find root causes, perform software repository mining…

ArabelaTso/Skills-4-SE · 121 tokens