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/mtvrkan/senior-dev-kit/codebase-overviewnpx skills add mtvrkan/senior-dev-kit --skill codebase-overviewgit clone --depth 1 https://github.com/mtvrkan/senior-dev-kitWhat 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 | $0.00041 | $0.00505 |
| Opus 5 | $0.00020 | $0.00253 |
| Sonnet 5 | $0.00008 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
codebase-overview 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.
What it actually says
codebase-overview
- Reuse BOOT SEQUENCE signals from this session if already known; otherwise glob top-level dirs + manifest.
- Map each top-level source directory to a one-line purpose (skip node_modules/dist/build/.git/.next).
- Trace primary data flow: entry point → routing → key components/screens → data layer (API/store/DB).
- Flag performance-sensitive integration points by file:line — third-party script loading, router/navigation setup, large media/asset loading, analytics init.
- Write/update
PROJECT/.claude/codebase-overview.mdwith the findings — the reusable reference other tasks read instead of re-discovering. Record the architecture explicitly (pattern, boundaries, dependency direction, which layer owns transactions/errors/authz): detected-but-unrecorded is re-detected differently next session. - Run
/arch-checkonce the map exists — it measures the tree against the architecture just recorded; a mixed pattern or an inverted dependency belongs in the overview as a known state, not as a surprise for the next feature. - If root
CLAUDE.mdlacks an architecture section, add ≤10 lines pointing to it (essentials inline, detail lazy-loaded fromcodebase-overview.md) — never let CLAUDE.md itself balloon past its existing budget. - Never modify source files — documentation only.
Output
CODEBASE OVERVIEW: [project name] — written to PROJECT/.claude/codebase-overview.md
DIRECTORIES: [dir → one-line purpose]
DATA FLOW: [entry → routing → components → data layer]
KEY COMPONENTS: [component → responsibility — only non-obvious ones]
PERF-SENSITIVE: [file:line — why it matters]
CLAUDE.md: [updated | already covered | needs manual review — reason]
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 · 33 lines · 41 tokens per session scan A 46b1b9651f9e
codebase-overview is a skill published in the GitHub repository mtvrkan/senior-dev-kit (5 stars, last pushed 12d ago), licensed MIT. It adds 41 tokens to every session and 505 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…