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/barnett-studios/cxpak/codebase-contextnpx skills add Barnett-Studios/cxpak --skill codebase-contextgit clone --depth 1 https://github.com/Barnett-Studios/cxpakWhat 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 | $0.00035 | $0.00429 |
| Opus 5 | $0.00017 | $0.00215 |
| Sonnet 5 | $0.00007 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
codebase-context scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Codebase Context via cxpak
When this skill is triggered, gather structured codebase context using cxpak before answering the user's question.
Steps
-
Ask for token budget. Ask the user: "How large a context budget should I use? (default: 50k tokens)" If they don't specify, use
50k. -
Resolve the cxpak binary. Run the ensure-cxpak script to get the binary path:
CXPAK="$("${CLAUDE_PLUGIN_ROOT}/lib/ensure-cxpak")" -
Run cxpak overview. Execute:
"$CXPAK" overview --tokens <budget> --format markdown .Where
<budget>is what the user specified (e.g.,50k,100k,20k). -
Use the output. The command outputs a structured codebase summary including:
- Project metadata (file counts, languages, tokens)
- Directory tree
- Module/component map with public symbols
- Dependency graph (import relationships)
- Key files (README, configs, manifests)
- Function/type signatures
- Git context (recent commits, churn)
-
Answer the user's question using the cxpak output as your primary source of codebase understanding.
-
Mention the source. Tell the user that cxpak provided the structured codebase context, e.g., "Based on the cxpak overview of this repo..."
Important
- Always use
--format markdown— it's native to your context window. - If cxpak fails (not a git repo, no files found), fall back to standard file reading.
- The overview may include
.cxpak/detail file pointers if the repo exceeds the budget — you can read those for deeper context.
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 · 43 lines · 35 tokens per session scan A 95be083cce5e
codebase-context is a skill published in the GitHub repository Barnett-Studios/cxpak (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 35 tokens to every session and 429 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
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…