MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
A skill your agent uses when an AI coding agent is guessing API names or framework behavior from incomplete docs.
Install Source Code Context
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill source-code-context -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering source-code-context --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/source-code-context .claude/skills/source-code-context && rm -rf skills-srcUse ~/.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/
Install the "source-code-context" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/source-code-context into .claude/skills/source-code-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "source-code-context", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/source-code-contextType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill source-code-context -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering source-code-context --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/source-code-context .agents/skills/source-code-context && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "source-code-context" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/source-code-context into .agents/skills/source-code-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "source-code-context", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill source-code-context -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering source-code-context --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/source-code-context .cursor/skills/source-code-context && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "source-code-context" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/source-code-context into .cursor/skills/source-code-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "source-code-context", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/pawel-cell/micky-podcast-agentic-engineering.git --path skills/source-code-context--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill source-code-context -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering source-code-context --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/source-code-context .gemini/skills/source-code-context && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "source-code-context" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/source-code-context into .gemini/skills/source-code-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "source-code-context", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering source-code-contextInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill source-code-context -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/source-code-context .github/skills/source-code-context && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "source-code-context" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/source-code-context into .github/skills/source-code-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "source-code-context", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill source-code-context -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering source-code-context --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/source-code-context .opencode/skills/source-code-context && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "source-code-context" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/source-code-context into .opencode/skills/source-code-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "source-code-context", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
source-code-context- GitHub stars
- 141
- Token cost
- ~800 tokens
- SKILL.md length
- 269 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when an AI coding agent is guessing API names or framework behavior from incomplete docs.
- Works in 3 steps: Identify the package/repo you are using. → Add the repo/source into a clearly named… → Add a short instruction in AGENTS.md,…
- An AI coding agent is guessing API names
- SKILL.md covers Overview, When to Use, Setup and Feature Prompt Template, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Source Code Context is an agent skill from pawel-cell/micky-podcast-agentic-engineering. Use when an AI coding agent is guessing API names or framework behavior from incomplete docs. Shows how to provide local source-code references so the agent searches the real implementation before coding.
Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. The repository describes itself as: Micky podcast agentic engineering workflow bundle. The licence is MIT.
When your agent uses it
- An AI coding agent is guessing API names
- Framework behavior from incomplete docs
Example prompts
- “/source-code-context”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Identify the package/repo you are using.
- Add the repo/source into a clearly named folder in your project, for example
- Add a short instruction in AGENTS.md, CLAUDE.md, or your harness memory
What it can do on your machine
Read from SKILL.md and the folder at commit ac337fe. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Source Code Context loads about 800 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 269 words of instructions outside code blocks.
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
The full file from pawel-cell/micky-podcast-agentic-engineering at commit ac337fe, republished under its MIT licence (© pawel-cell). 269 words, ~800 tokens.
Download SKILL.mdSave it as
.claude/skills/source-code-context/SKILL.md (or your agent's skills folder).- name
- source-code-context
- description
- Use when an AI coding agent is guessing API names or framework behavior from incomplete docs. Shows how to provide local source-code references so the agent searches the real implementation before coding.
- version
- 1.0.0
- author
- David Ondrej / Michael Shimeles interview notes
- license
- MIT
Source Code as Agent Context
Overview
Code is often the best source of truth. Docs can be outdated, examples can be incomplete, and blog posts can lag behind the current API. When an agent has access to the actual repo/package source, it can search for real function names, types, examples, and edge cases.
Use this skill to stop the agent from guessing.
When to Use
- You are integrating a package, SDK, API client, framework, or open-source tool.
- The agent keeps hallucinating functions that do not exist.
- Docs are weak, stale, or too abstract.
- You want the agent to follow the package's actual internal patterns.
Do not paste an entire repo into chat. Put the source on disk and point the agent to it.
Setup
- Identify the package/repo you are using.
- Add the repo/source into a clearly named folder in your project, for example:
reference/repos/github.com/company/projectopen-source/repos/github.com/company/project
- Add a short instruction in
AGENTS.md,CLAUDE.md, or your harness memory:
When working with <library/tool>, reference the local source under:
`reference/repos/github.com/company/project`.
Do not guess API names. Search the source first, then implement.Feature Prompt Template
Build <feature>. We use <library/tool>.
Before coding:
1. Search `reference/repos/github.com/company/project` for the correct API and patterns.
2. Identify the files/functions/examples you used as reference.
3. Implement only the minimal service function and one calling route/component.
4. Keep the diff small.
5. Explain which source files you referenced.Example
We need to integrate Daytona sandboxes into this app.
Reference the local Daytona source under `reference/repos/github.com/daytonaio/daytona`.
Find the current SDK pattern for creating a sandbox and running a command.
Then implement only the minimal service function and one calling route.Common Pitfalls
- Dumping too much context into chat. This bloats the context window. Let the agent search files on disk.
- Trusting old docs over current code. Fast-moving packages change quickly.
- Letting the agent install alternatives. If it cannot find the API, make it search the source before adding new dependencies.
- No path convention. Use a predictable folder name so every future agent knows where references live.
Verification Checklist
- Reference source exists in a stable folder.
- Agent was explicitly told where to search.
- Agent reported which files/functions it referenced.
- No random replacement package was installed without approval.
- The implementation matches current source-code patterns.
© pawel-cell, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/source-code-context of pawel-cell/micky-podcast-agentic-engineering.
Open the folder on GitHubat commit ac337fe
Compare with similar skills
Source Code Context 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Source Code Context this skillpawel-cell/micky-podcast-agentic-engineering | 141 | — | ~800 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
More from pawel-cell/micky-podcast-agentic-engineering
Agentic Engineering Workflow
pawel-cell/micky-podcast-agentic-engineering
A skill your agent uses when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding.
Grep Loop Review Workflow
pawel-cell/micky-podcast-agentic-engineering
A skill your agent uses when you have a small PR or feature and want an agent to repeatedly fix review feedback until tests pass and the PR is merge-ready.
Code Structure Cleanup
pawel-cell/micky-podcast-agentic-engineering
Use after an AI-built feature works but the code has duplicated mechanics, repeated API calls, or messy structure.
Related
Categories
Questions about Source Code Context
What does Source Code Context do?
A skill your agent uses when an AI coding agent is guessing API names or framework behavior from incomplete docs. Source Code Context is an agent skill from pawel-cell/micky-podcast-agentic-engineering. Use when an AI coding agent is guessing API names or framework behavior from incomplete docs.
When should I use Source Code Context?
Source Code Context fits situations like: an AI coding agent is guessing API names; framework behavior from incomplete docs.
How do I install Source Code Context in Claude Code?
Run `npx skills add pawel-cell/micky-podcast-agentic-engineering --skill source-code-context -a claude-code`. Or copy the skill folder (skills/source-code-context in pawel-cell/micky-podcast-agentic-engineering) into .claude/skills/source-code-context in your project. Claude Code loads it when a task matches its description.
How do I install Source Code Context in Codex?
Run `npx skills add pawel-cell/micky-podcast-agentic-engineering --skill source-code-context -a codex`. Or copy the skill folder (skills/source-code-context in pawel-cell/micky-podcast-agentic-engineering) into .agents/skills/source-code-context in your project. Codex loads it when a task matches its description.
Can I use Source Code Context 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 pawel-cell/micky-podcast-agentic-engineering --skill source-code-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/source-code-context, .gemini/skills/source-code-context, .github/skills/source-code-context and .opencode/skills/source-code-context in your project.
What does Source Code Context need to run?
SKILL.md names no scripts, command-line tools or credentials: Source Code Context is instructions for the agent only.
Does Source Code Context access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Source Code Context 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 Source Code Context use?
Source Code Context is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Source Code Context use?
About 800 tokens (SKILL.md is roughly 3.2k 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 Source Code Context?
Skills that share tags, products or a category with Source Code Context: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Source Code Context?
pawel-cell (a GitHub user) maintains it in pawel-cell/micky-podcast-agentic-engineering, which has 141 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on May 19, 2026.
Source: pawel-cell/micky-podcast-agentic-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.