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/outlinedriven/odin-gemini-cli-extension/improve-codebase-architecturenpx skills add OutlineDriven/odin-gemini-cli-extension --skill improve-codebase-architecturegit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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/outlinedriven/odin-gemini-cli-extension/improve-codebase-architecture)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/improve-codebase-architecture.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00069 | $0.01206 |
| Opus 5 | $0.00034 | $0.00603 |
| Sonnet 5 | $0.00014 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00121 |
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 5d 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.
This is a copy
100% identical to improve-codebase-architecture — 0 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iteration loop: explore for friction, present deepening candidates, grill the chosen one, update domain artifacts inline. Vocabulary is load-bearing — see references/LANGUAGE.md.
Vocabulary [LOAD-BEARING]
Use these terms exactly. Do not substitute "component," "service," "API," or "boundary." Full definitions in references/LANGUAGE.md.
- Module — anything with an interface and an implementation (function, class, package, slice). Scale-agnostic.
- Interface — every fact a caller must know: types, invariants, ordering, error modes, config, performance shape. Not just signature.
- Depth — leverage at the interface. Deep = much behaviour behind a small interface. Shallow = interface as complex as implementation.
- Seam (Feathers) — where an interface lives; a place behaviour can be altered without editing in place. Use this, not "boundary."
- Adapter — a concrete thing satisfying an interface at a seam. Role, not substance.
- Leverage — capability callers gain per unit of interface learned.
- Locality — concentration of change, bug, and knowledge at one site for maintainers.
Principles
- Deletion test: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
- Interface = test surface. Tests cross the same seam callers cross. Wanting to test past the interface = wrong shape.
- One adapter = hypothetical seam. Two adapters = real seam. No port without two real implementations (production + test).
Process
1. Explore
First tool call MUST be Explore-agent dispatch — not direct reads. The agent's brief:
- Read
CONTEXT.md(orCONTEXT-MAP.md+ per-contextCONTEXT.md) and anydocs/adr/. If absent, proceed silently. - Walk the codebase organically; classify friction:
- Concept understanding requires bouncing across many small modules → shallow cluster.
- Interface complexity matches implementation complexity → shallow module.
- Pure functions extracted only for testability while real bugs hide in callers → no locality.
- Tightly coupled modules leaking across their seams.
- For each suspect, run the deletion test before reporting.
What ships with it
3 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.
- 5d ago First seen · 83 lines · 69 tokens per session scan A e9c05aae49cd
improve-codebase-architecture is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,206 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to improve-codebase-architecture, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.