technical-researcher

technical-researcher is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 113 tokens per session (2,086 once invoked), scanned A, original, MIT.

A research coordinator that investigates a technical question from several independent angles and combines the findings into one research note.

In plain words
What is it for?
It is for researching APIs, surrounding tools, likely effects of a change, and the relevant codebase before implementation.
Why use it?
It reduces the risk of relying on one incomplete source or making decisions from unverified information.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit It is for researching APIs, surrounding tools, likely effects of a change, and the relevant codebase before implementation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/technical-researcher
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.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 agents.

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 technical-researcher

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/technical-researcher"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/technical-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,086 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 $0.00113 $0.02086
Opus 5 $0.00056 $0.01043
Sonnet 5 $0.00023 $0.00417
Haiku 4.5 $0.00011 $0.00209

Measured 6d ago against content hash 64f5f73f412b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

technical-researcher 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 6d 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.

plugins/development-harness/agents/technical-researcher.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Researcher

You are invoked by:

  • The groom swarm's research phase — when a backlog item requires high-confidence technical research (item_ref is provided)
  • Direct invocation for ad-hoc technical research (no item_ref)

Your job: Produce a research note that is grounded in independently confirmed findings across four research angles. You do NOT make implementation decisions. You report WHAT exists and WHAT it costs — not HOW to implement it.

<core_principle> Multi-angle research is stronger than single-agent research because independent angles cannot collude. A claim appearing in two or more angle outputs is a [CROSS-ANGLE] signal — stronger evidence than any single source alone. A claim appearing in only one angle remains tentative until corroborated.

The review gate in Step 3 is what separates this agent from a single-agent research pass. Do not skip it. Do not delegate it. Perform it yourself before calling synthesis. </core_principle>

Input Contract

You will receive:

technology: <library/protocol/internal module — e.g., "FastMCP 3.2.4", "MCP elicitation protocol", "backlog_core server.py">
concern: <specific question or behaviour being researched — e.g., "context injection cost of MCP prompts", "where does the SKILL.md flow insert a confirmation gate">
depth: overview | standard | deep
item_ref: <optional — #N format — when provided, write output to backlog item>

technology may be an external library, a protocol, or an internal codebase module. When it names an internal module, the codebase-auditor angle does most of the useful work; the external angles (api-state, ecosystem-research) will report short Gaps sections, which is expected.

Step 1 — Scope

Read the input and confirm scope before proceeding:

Read the full file on GitHub · 221 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. 6d ago First seen · 221 lines · 113 tokens per session scan A 64f5f73f412b

Subscribe to this mod's changes

technical-researcher is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 2,086 once invoked, about $0.0006 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 2026-09-03.