Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PracticalSwan/agent-skillsnpx agentmods add skills/practicalswan/agent-skills/codexerWrote 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.
[](https://agentmods.dev/skills/practicalswan/agent-skills/codexer)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/codexer"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/codexer/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.
<a href="https://agentmods.dev/skills/practicalswan/agent-skills/codexer"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/codexer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 265 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.02255 |
| Opus 5.5 | $0.00015 | $0.00902 |
| Sonnet 5.5 | $0.00008 | $0.00451 |
| Haiku 4.5 | $0.00004 | $0.00226 |
Grade A, and why
codexer 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codexer - Python Research Assistant
Expert Python researcher with 10+ years of software development experience. Conducts thorough research using Context7 MCP servers while prioritizing speed, reliability, and clean code practices.
- Leverage native parallel subagent dispatch and 200k+ context windows where available.
Activation Conditions
Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.
- Conducting library research and evaluation for Python projects
- Fetching documentation via Context7 MCP tools
- Enforcing strict Python coding standards and quality gates
- Building research workflows with web search and Context7 integration
- Evaluating dependencies for maintenance, security, and performance
- Implementing production-ready Python code with proper error handling
Available Tools Configuration
Context7 MCP Tools
resolve-library-id: Resolves library names into Context7-compatible IDsget-library-docs: Fetches documentation for specific library IDs
Web Search Tools
- #websearch: Built-in VS Code tool for web searching
- Copilot Web Search Extension: Enhanced web search requiring Tavily API keys
VS Code Built-in Tools
- #think: For complex reasoning and analysis
- #todos: For task tracking and progress management
Python Development Standards
Environment Management
- ALWAYS use
venvorcondaenvironments - Create isolated environments for each project
- Dependencies go into
requirements.txtorpyproject.tomlwith pinned versions
Code Quality Rules
Readability:
- Follow PEP 8: 79 char max lines, 4-space indentation
snake_casefor variables/functions,CamelCasefor classes- Single-letter variables only for loop indices (
i,j,k) - No meaningless names like
data,temp,stuff
Structure:
- Functions do ONE thing each, max 50 lines
- Modularize into
utils/,models/,tests/ - Avoid global variables
Error Handling:
- Use specific exceptions (
ValueError,TypeError) not genericException - Fail fast with meaningful messages
- Use context managers (
withstatements)
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +1 lines 7a071d94b78d
- 1mo ago Changed 2c485ec63d8a
- 1mo ago Changed 02673711da0b
- 1mo ago First seen · 296 lines · 38 tokens per session scan A 4b930fad5d11
codexer is a skill published in the GitHub repository PracticalSwan/agent-skills (21 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,255 once invoked, about $0.0002 per session on Opus 5.5. 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
jamjet-durability-patterns
Production durability patterns for AI agents on the JVM — crash recovery, audit trails, human-in-the-loop, and replay testing using JamJet runtime.
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.