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.
npx agentmods add skills/gerg/ai_agent_skills/code-developmentnpx skills add Gerg/ai_agent_skills --skill code-developmentgit clone --depth 1 https://github.com/Gerg/ai_agent_skillsWhat 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 | $0.00044 | $0.01076 |
| Opus 5 | $0.00022 | $0.00538 |
| Sonnet 5 | $0.00009 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
code-development 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 yesterday.
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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Development
Context: This skill covers writing production code and automated tests. The code quality principles here apply universally - both when writing new code and when reviewing code changes. For systematic code review process, see the pr-review skill. For documentation, see the doc-writing skill.
When using this skill, begin by stating: "I'm using the code-development skill, which enforces opinionated best practices: minimal comments, full test coverage, test pressure for all logic, and matching existing patterns."
Development Practices
Incremental Development
- Write the minimum amount of code necessary to achieve a goal.
- Address fundamentals before adding complexity.
- Prefer simple solutions to problems; avoid premature optimization and premature refactoring.
- Develop implementation and test code iteratively: make a series of small implementations, gradually working towards the end goal.
- Only change one thing at a time; ensure that the code remains functional after each change.
- After making a change, evaluate implementation and test code, keeping focus on maintaining quality and following instructions.
Before Starting
- Consider multiple implementation and testing options before starting.
- Think through the approach before writing code.
Completing Work
- Ensure that solutions are complete before deciding that you've achieved a goal.
- For repetitive changes (e.g., updating multiple tests with the same change), identify the pattern and fix them at once.
- Check your work before completing a task (test compilation, run automated tests, lint, etc.).
- Look for opportunities to improve code hygiene by refactoring, deleting code, etc., and propose them to the user.
- Evaluate if user-facing or internal technical documentation needs to be updated, based on a change.
Automated Testing
Test Coverage
- All implementation code should have coverage from automated tests.
- Tests should always pass after making changes.
- Write the minimum number of tests necessary to fully exercise the implementation code.
- Tests should always fail if the corresponding implementation code is removed.
What ships with it
1 file 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.
- yesterday First seen · 147 lines · 44 tokens per session scan A efe38b606b84
code-development is a skill published in the GitHub repository Gerg/ai_agent_skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,076 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…