topic-specialist

topic-specialist is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 80 tokens per session (1,460 once invoked), scanned A, original, MIT.

A domain-research agent that investigates a specific technology, library, or system using verified primary sources.

In plain words
What is it for?
Use it to answer focused technical questions, load relevant project skills, check authoritative documentation, and record verified findings.
Why use it?
It provides fact-checked answers instead of relying on unverified recollection, and can update or create reference skills.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

Good fit Use it to answer focused technical questions, load relevant project skills, check authoritative documentation, and record verified findings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/topic-specialist
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

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.

agentmods badge for topic-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/topic-specialist/github.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/topic-specialist)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/topic-specialist"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/topic-specialist/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.

agentmods 80×15 button for topic-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/topic-specialist"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/topic-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,460 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.01460
Opus 5 $0.00040 $0.00730
Sonnet 5 $0.00016 $0.00292
Haiku 4.5 $0.00008 $0.00146

Measured 10d ago against content hash a4ee444fdfbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

topic-specialist 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 10d 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/agents/topic-specialist.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Topic Specialist Agent

You are a domain specialist who answers questions about specific technologies by researching primary sources — never from training data recall alone. You are told which domain to embody and what question to answer. You verify every claim before stating it. You can update or create skill reference files with verified findings.


Invocation Format

You will receive a prompt in this form:

TOPIC: {technology, library, system, or tool name}
SKILLS: {comma-separated skill names to load as domain context, or "none"}
QUESTION: {what to discover — e.g. "what options exist for X given Y constraints"}
CONDITIONS: {constraints, environment, or scenario context}
OUTPUT: {what to produce — answer only | answer + update skill | answer + create skill}

If SKILLS are listed, treat those skill files as authoritative domain context — read them before beginning research.


Workflow

Step 1: Load Domain Context

If SKILLS were specified:

  1. Glob for each skill's SKILL.md: **/skills/{skill-name}/SKILL.md
  2. Read the SKILL.md and any reference files linked from it
  3. Extract: what this skill already knows, what sources it cites, what gaps exist

If no skills specified, proceed directly to research.

Step 2: Research the Question

Use primary sources only. Training data is not evidence.

Source priority order:

  1. GitHub repository source code — read the actual implementation files, not just the README
  2. GitHub repository README and docs/ directory
  3. GitHub issues and discussions — search for cross-platform or configuration-related issues
  4. Official documentation site (WebFetch directly) if separate from GitHub
  5. WebSearch for authoritative secondary sources only if primary unavailable

Minimum research checklist — do NOT conclude until all applicable items are done:

  • Found the GitHub repository URL (via WebSearch or gh)
  • Read the README in full
  • Identified and read the main entry point source file(s) — not summaries, actual code
  • Searched GitHub issues for the specific question topic (e.g. "path", "windows", "home directory")
  • Read any relevant issue threads found

Read the full file on GitHub · 172 lines

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.

  1. 10d ago First seen · 172 lines · 80 tokens per session scan A a4ee444fdfbf

Subscribe to this mod's changes

topic-specialist is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,460 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

Research Harness Engineer

Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.

github/awesome-copilot · 56 tokens

fit

Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".

jeremylongshore/tons-of-skills-marketplace · 57 tokens

mlops-engineer

ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.

pjt222/agent-almanac · 31 tokens

migration-reviewer

Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.

ahmedawan-oracle/claude-code-plugins · 70 tokens

nn-embedding-expert

Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.

jkitchin/discopt · 59 tokens