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/stevesolun/ctx/improve-codebase-architecturenpx skills add stevesolun/ctx --skill improve-codebase-architecturegit clone --depth 1 https://github.com/stevesolun/ctxWhat 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 | $0.00040 | $0.00454 |
| Opus 5 | $0.00020 | $0.00227 |
| Sonnet 5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
improve-codebase-architecture 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 2d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Codebase Architecture
Look for architectural friction that a focused structural change could reduce. Favor improvements that shrink interfaces, concentrate related complexity, and make important behavior easier to test and understand.
Scope the investigation
Follow the user's named subsystem or pain point. Otherwise use recent changes, repeated maintenance friction, test difficulty, or dependency structure to select a useful area. Read relevant domain language and ADRs when present so recommendations respect intentional boundaries.
Use the codebase-design skill when its deep-module vocabulary will sharpen the
analysis. Explore independently in parallel only when the repository is large
enough to benefit and the lanes do not duplicate work.
Find evidence
Consider:
- interfaces that expose nearly as much complexity as their implementations;
- behavior spread across modules that change together;
- dependency seams that leak internal details;
- testing that bypasses the real call path because no stable seam exists; and
- repeated wrappers or indirection that add little leverage.
Treat these as prompts for investigation, not violations. Apply the deletion test where useful: would removing a layer concentrate complexity behind a better interface, or merely move it elsewhere?
Present candidates
For each material candidate, cite the affected code and explain:
- the observed friction;
- the structural change being considered;
- expected benefits and tradeoffs;
- evidence that the seam is real rather than hypothetical;
- test impact and migration risk; and
- conflicts with existing decisions.
Rank recommendations by evidence and likely leverage. Keep speculative ideas clearly labeled and avoid proposing a wide refactor solely for aesthetic consistency.
Use prose, a compact table, or diagrams according to what best communicates the relationships. When a visual HTML artifact is useful and authorized, load the HTML report guide.
What ships with it
2 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.
- 2d ago First seen · 59 lines · 40 tokens per session scan A 0a2c458a7a89
improve-codebase-architecture is a skill published in the GitHub repository stevesolun/ctx (581 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 454 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 2026-08-30.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
haiku
When writing a haiku for this bot, follow these conventions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.