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.
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsnpx agentmods add agents/jamie-bitflight/claude_skills/research-utilization-assessorWrote 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.
[](https://agentmods.dev/agents/jamie-bitflight/claude_skills/research-utilization-assessor)<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.
<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>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 | $0.00070 | $0.01444 |
| Opus 5 | $0.00035 | $0.00722 |
| Sonnet 5 | $0.00014 | $0.00289 |
| Haiku 4.5 | $0.00007 | $0.00144 |
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.
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])
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.
- 10d ago First seen · 165 lines · 70 tokens per session scan A 1d9667b4b3b4
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.