research-cross-referencer

research-cross-referencer is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 73 tokens per session (1,206 once invoked), scanned A, original, MIT.

A research-file helper that reads a new entry and the research index to find related entries, then adds a Cross-References section to the file.

In plain words
What is it for?
Use it after adding or refreshing a research entry when you want links to 3–8 related entries based on shared domains, technologies, problems, or workflow steps.
Why use it?
It saves readers from searching the whole research collection to find connected topics and tools.

Agent for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Add cross-references to ./research/{category}/{name}.md.

Good fit Use it after adding or refreshing a research entry when you want links to 3–8 related entries based on shared domains, technologies, problems, or workflow steps.

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-cross-referencer

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-cross-referencer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/research-cross-referencer/github.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/research-cross-referencer)
Your own site
<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.

agentmods 80×15 button for research-cross-referencer

Your own site · 80×15
<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>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,206 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 $0.00073 $0.01206
Opus 5 $0.00036 $0.00603
Sonnet 5 $0.00015 $0.00241
Haiku 4.5 $0.00007 $0.00121

Measured 12d ago against content hash 4545b50be8a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.claude/agents/research-cross-referencer.md · 134 lines

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])

Read the full file on GitHub · 134 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. 12d ago First seen · 134 lines · 73 tokens per session scan A 4545b50be8a6

Subscribe to this mod's changes

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.