What is tool-search-change?

A development guide for changing the part of a tool router that searches for and invokes available tools.

It guides updates to search, invocation, discovery hints, name normalization, the search index, catalog snapshots, and related checks.

It helps prevent changes that make tool discovery too large, break common entry points, or disconnect searching from tool invocation.

How berntpopp/genefoundry-router configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to berntpopp/genefoundry-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/berntpopp/genefoundry-router/main/.claude/skills/tool-search-change/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/berntpopp/genefoundry-router

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/tool-search-change/github.svg)](https://agentmods.dev/skills/berntpopp/genefoundry-router/tool-search-change)

Your own site

<a href="https://agentmods.dev/skills/berntpopp/genefoundry-router/tool-search-change"><img src="https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/tool-search-change/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/berntpopp/genefoundry-router/tool-search-change"><img src="https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/tool-search-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 358 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00042	$0.00358
Opus 5	$0.00021	$0.00179
Sonnet 5	$0.00008	$0.00072
Haiku 4.5	$0.00004	$0.00036

Measured 11d ago against content hash dde83f5ecd93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tool-search-change 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 11d 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.

.claude/skills/tool-search-change/SKILL.md · 22 lines

What it actually says

Tool-Search Change

Follow AGENTS.md first. The router doesn't author backend tools; it exposes two synthetic meta-tools over the federated fleet — search_tools (BM25 discovery, token-lean serialization) and call_tool (invoke a discovered tool by name) — in tool_search.py, plus discovery hints/normalization in hints.py / normalization.py / discovery.py.

Workflow

Work in tool_search.py (search_tools / call_tool), and discovery.py / hints.py / normalization.py for the catalog and rewrites.
Keep search_tools output token-lean (the default serialization drops _meta and trims to a one-line returns); don't regress payload size.
Preserve the pinned entrypoints (the common first-call tools) and the search_tools -> call_tool contract in the tool descriptions.
Regenerate the discovery catalog (make snapshot-catalog) and keep golden-task / guard tests green; make list-tools to sanity-check the surface.
Tune GF_SEARCH_MAX_RESULTS / GF_REWRITE_HINTS via config, not hard-coded values. Run make ci-local.

Common mistakes

Bloating search_tools results with full schemas/_meta — it's the token-lean discovery path.
Breaking the search_tools -> call_tool handshake the tool descriptions promise.

Changes

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.

11d ago First seen · 22 lines · 42 tokens per session scan A dde83f5ecd93

Subscribe to this mod's changes

tool-search-change is a skill published in the GitHub repository berntpopp/genefoundry-router (5 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 358 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.

Building agents api-gateway bioinformatics claude clinical-genetics fastmcp gateway

experimental-design

Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls…

K-Dense-AI/scientific-agent-skills · 200 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

scientific-visualization

Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use for figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning.

K-Dense-AI/scientific-agent-skills · 58 tokens

pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…

K-Dense-AI/scientific-agent-skills · 98 tokens

genefoundry-router: Skill for Claude Code