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/bostonorange/claude-code-framework/searchnpx skills add BostonOrange/claude-code-framework --skill searchgit clone --depth 1 https://github.com/BostonOrange/claude-code-frameworkWhat 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 | $0.00053 | $0.01143 |
| Opus 5 | $0.00026 | $0.00571 |
| Sonnet 5 | $0.00011 | $0.00229 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
search 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search — Semantic Codebase Query
When you need to find code by meaning rather than exact text — "where do we generate invoice numbers?", "what handles rate limiting?", "is there existing logic for tax calculation?" — /search queries the vector index built by /index and returns the most semantically relevant chunks.
/search complements /impact and Grep:
- Grep for exact strings ("find all uses of
requireAuth") - /impact for precise call-site cascades on a known target
- /search for semantic neighborhood ("find code about authentication" without knowing the function names)
Usage
/search "<natural language query>"
/search "<query>" --top-k=20 return top 20 (default 10)
/search "<query>" --include=apex filter by extension/type
Examples:
/search "where do we generate unique invoice numbers"
/search "rate limit logic for API endpoints"
/search "session timeout handling" --top-k=5
/search "after-insert trigger handler" --include=apex
Process
Phase 1: Verify index exists
bash .claude/hooks/codebase-index.sh stats
If no index, halt with: "Run /index first to build the codebase index. See /index skill for setup."
Phase 2: Run the search
bash .claude/hooks/codebase-index.sh search "<query>" [--top-k=N]
The script:
- Embeds the query via the configured provider (must match what
/indexused) - Computes cosine similarity against every chunk in the DB
- Returns top-K results:
<score>\t<file>:<line_start>-<line_end>\t<snippet>
Phase 3: Render results
Show the user a ranked table:
| # | Score | File:Lines | Snippet |
|---|-------|------------|---------|
| 1 | 0.847 | lib/billing/invoice.ts:23-62 | "function generateInvoiceNumber(account: Account)..." |
| 2 | 0.792 | lib/billing/sequence.ts:8-40 | "// Atomic counter for invoice numbers..." |
Phase 4: Hand-off
After showing results, suggest next steps based on the query type:
- Exploration ("where do we handle X?"): "Top hit is
<file>:<line>. Read that to confirm it's the right entry point." - Duplicate check ("is there existing logic for Y?"): "Found N similar chunks. Highest scoring is
<file>:<line>— review before adding new logic." - Pre-change context ("rate limit code"): "These chunks are the rate-limiting surface. Run
/impact <file>:<symbol>on each before modifying."
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 · 110 lines · 53 tokens per session scan A d443006c2576
search is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,143 once invoked, about $0.0003 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…