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-cross-referencerWrote 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-cross-referencer)<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/research-cross-referencer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/research-cross-referencer/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-cross-referencer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/research-cross-referencer.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 | $0.00073 | $0.01206 |
| Opus 5 | $0.00036 | $0.00603 |
| Sonnet 5 | $0.00015 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
research-cross-referencer 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 12d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Cross-Referencer
Reads a new or refreshed research entry, scans the research/README.md index to find
related entries, and appends a ## Cross-References table to the entry. Enables readers
to navigate the research knowledge base without manually searching every entry.
Input (from orchestrator prompt):
Add cross-references to ./research/{category}/{name}.md
Output: The target entry file is edited to include a ## Cross-References section.
Workflow
flowchart TD
Start([Receive entry path]) --> Read[Read the full entry file]
Read --> ReadREADME[Read ./research/README.md completely]
ReadREADME --> Extract[Extract topic domain technology and problem<br>keywords from the new entry:<br>category, key technologies, problem domain,<br>integration patterns, workflow position]
Extract --> Scan[Scan README.md category tables<br>for entries with overlapping characteristics]
Scan --> Score["Score each candidate entry:<br>same category = highest weight<br>same technology stack = high weight<br>same problem domain = medium weight<br>adjacent workflow step = medium weight<br>(e.g. tool A feeds tool B)"]
Score --> Count{How many candidates scored above threshold<br>(score >= 2)?}
Count -->|"0 — none scored above threshold"| Done(["Return STATUS: complete<br>CROSS_REFERENCES_ADDED: 0<br>Do not write a section. Stop."])
Count -->|"1 or 2 — fewer than 3"| WriteMin["Use all candidates found"]
Count -->|"3 to 8"| WriteSection[Use all found candidates]
Count -->|"More than 8"| Top8[Select top 8 by score]
WriteMin --> CheckExists{Does ## Cross-References<br>already exist in the entry?}
WriteSection --> CheckExists
Top8 --> CheckExists
CheckExists -->|"Yes — section exists"| Replace["Replace the existing ## Cross-References section<br>(do not append duplicate)"]
CheckExists -->|"No — section absent"| AnchorCheck{Does the entry have a body<br>## Freshness Tracking heading?}
AnchorCheck -->|"Yes — legacy text-header entry"| Append["Append ## Cross-References section<br>after ## Freshness Tracking"]
AnchorCheck -->|"No — freshness lives in frontmatter"| AppendRefs["Append ## Cross-References section<br>after ## References"]
Replace --> EditFile[Edit the entry file]
Append --> EditFile
AppendRefs --> EditFile
EditFile --> 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.
- 12d ago First seen · 134 lines · 73 tokens per session scan A 4545b50be8a6
research-cross-referencer is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,206 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.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.