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/quangphu1912/codebase-analyzer/test-hypothesisnpx skills add quangphu1912/codebase-analyzer --skill test-hypothesisgit clone --depth 1 https://github.com/quangphu1912/codebase-analyzerWhat 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 | $0.00032 | $0.01017 |
| Opus 5 | $0.00016 | $0.00508 |
| Sonnet 5 | $0.00006 | $0.00203 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
test-hypothesis 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Announce at start: "Using codebase-analyzer to test hypothesis: [hypothesis]."
Overview
User states a hypothesis. Plugin runs targeted analysis focused on confirming or denying it. This is hypothesis-driven analysis, not exploratory scanning.
Prerequisite Bypass
This skill carries its own prerequisite resolution. It can invoke ANY skill (Track A or Track B) regardless of normal phase prerequisites. Trade-off: invoking Track B without Phase 1 produces shallower analysis, but still produces a valid verdict. Check .state and note which prerequisites were unavailable so the user can interpret confidence levels correctly.
When a prerequisite skill was skipped or unavailable, explicitly note this in the verdict:
- Which prerequisite was missing
- How it affects the depth of evidence gathered
- Whether running the prerequisite first would likely change the verdict
Process
- Parse hypothesis: Extract the specific claim and what evidence would confirm/deny it
- Select relevant skills: Which Track A/B skills address this hypothesis?
- Run targeted analysis: Only invoke skills relevant to the hypothesis
- Gather evidence: Collect file:line references that support or contradict
- Render verdict: CONFIRMED / DENIED / PARTIALLY CONFIRMED / INCONCLUSIVE
- Present evidence: For each piece of evidence, explain how it relates to the hypothesis
Example Hypotheses
| Hypothesis | Skills to Run | Evidence to Find |
|---|---|---|
| "This app sends data to third parties" | tech-stack, deps, trace-data-flows | Outbound HTTP calls to non-first-party domains, data flow paths to external sinks |
| "There's a hidden admin panel" | architecture, api-surface, extract-tool-graph, map-feature-gates | Routes gated by role, undocumented endpoints, tool nodes not reachable from main UI |
| "This code was decompiled, not original" | provenance, build-pipeline | Sourcemap artifacts, decompiled patterns |
| "Feature X is coming but not yet released" | dead-code, extract-tool-graph, map-feature-gates | Dead code behind feature flags, unreleased API endpoints, gated tool nodes |
| "This system can do more than it exposes" | extract-tool-graph, map-feature-gates, prompt-influence | Tools defined but gated, capabilities hidden behind config |
| "Two modules depend on the same hidden contract" | detect-hidden-contracts | Implicit interfaces, shared assumptions between modules |
| "What was this system originally designed to do?" | reconstruct-system-intent, provenance | Design traces, architectural intent recovered from structure |
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 · 86 lines · 32 tokens per session scan A 383ac68afab9
test-hypothesis is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,017 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.