research-utilization-assessor

research-utilization-assessor is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 70 tokens per session (1,444 once invoked), scanned A, original, MIT.

A research review agent that checks whether a researched tool can be connected to an existing local workflow through an API, software package, command-line tool, or webhook.

In plain words
What is it for?
Use it to assess research entries and write a proposal when a tool offers a usable integration point.
Why use it?
It separates practical integrations from ideas that cannot be directly connected to the project.

Agent for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Assess utilization opportunities from ./research/{category}/{name}.md.

Good fit Use it to assess research entries and write a proposal when a tool offers a usable integration point.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills
agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/research-utilization-assessor

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 research-utilization-assessor

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/research-utilization-assessor"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/research-utilization-assessor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,444 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 $0.00070 $0.01444
Opus 5 $0.00035 $0.00722
Sonnet 5 $0.00014 $0.00289
Haiku 4.5 $0.00007 $0.00144

Measured 10d ago against content hash 1d9667b4b3b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

research-utilization-assessor 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/research-utilization-assessor.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Utilization Assessor

Takes one completed research entry and determines whether any existing local system (skill, agent, hook, or workflow script) could directly call or depend on the described tool as an external service. This is distinct from pattern adoption: the question is not "can we borrow the idea?" but "can we call this API, install this package, or invoke this CLI in our workflow?"

Input (from orchestrator prompt):

Assess utilization opportunities from ./research/{category}/{name}.md

Output (when utilization surface exists):

  • ./research/insights/{YYYY-MM-DD}-{resource-name}-utilization.md — utilization proposal file

Workflow

flowchart TD
    Start([Receive research entry path]) --> Read[Read the full research entry]
    Read --> Surface{Does the entry document a callable API<br>SDK package CLI tool or webhook?}
    Surface -->|"No — conceptual only, no integration surface"| Skip(["Return STATUS: no_utilization_surface<br>Do not write an output file. Stop."])
    Surface -->|"Yes — integration surface exists"| Extract[Extract integration surfaces:<br>API endpoints SDK package names CLI commands webhooks]
    Extract --> MapSystems[Identify local systems that could be callers:<br>agents in .claude/agents/<br>skills in .claude/skills/<br>hooks in plugin hooks.json<br>workflow scripts]
    MapSystems --> ForEach[For each candidate local system]
    ForEach --> ReadLocal[Read the local system file]
    ReadLocal --> Assess{Would integrating this service<br>replace a weaker local implementation<br>OR add a capability the system lacks?}
    Assess -->|"No — already covered or incompatible"| Skip2[Document skip reason]
    Assess -->|"Yes — concrete opportunity"| Proposal[Write utilization proposal with:<br>caller system path<br>integration mechanism<br>what it replaces or adds<br>setup cost<br>integration surface grounded in research entry]
    Skip2 --> More{More candidate systems?}
    Proposal --> More
    More -->|Yes| ForEach
    More -->|No| AnyProposals{Were any proposals written?}
    AnyProposals -->|"Yes"| WriteFile[Write proposals to<br>./research/insights/YYYY-MM-DD-resource-name-utilization.md]
    AnyProposals -->|"No — all candidates skipped"| NoProposals(["Return STATUS: complete<br>PROPOSALS_WRITTEN: 0<br>Do not write an output file. Stop."])
    WriteFile --> Return([Return structured result])

Read the full file on GitHub · 165 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 · 165 lines · 70 tokens per session scan A 1d9667b4b3b4

Subscribe to this mod's changes

research-utilization-assessor is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 1,444 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 2026-08-30.