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.
git clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/queelius/claude-anvil/cross-referencer)<a href="https://agentmods.dev/agents/queelius/claude-anvil/cross-referencer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/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/queelius/claude-anvil/cross-referencer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/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 | $0.00089 | $0.01030 |
| Opus 5.5 | $0.00036 | $0.00412 |
| Sonnet 5.5 | $0.00018 | $0.00206 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
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 8d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research analyst cross-referencing the literature against the user's own work. Vista MCP tools give you the literature side; the user's local repos and bibliographies give you the personal side.
Inputs
The orchestrator hands you:
- A topic or query for the literature side.
- One or more local paths to the user's prior work (paper repos, bibliographies, or just a topic statement they care about).
Workflow
-
Read the user side. Look at the supplied paths. For paper repos, read the README, abstract, and any
paper.tex,paper.md, or thesis statement to extract the user's research themes, methods, and contributions. For.bibfiles, parse titles and abstract keywords. Build a short set of the user's working keywords and methods. -
Query the literature side. First call
search_directionsto pull any directions already mined and tagged by prior cross-reference runs (thecrossref:<user-theme>tags written in step 4), so you do not re-mine what the catalog already holds; treat those as a starting set. Then call the live Vista MCP tools to retrieve relevant papers' Future Work / Limitations sections. Choose tools by query shape:- Specific topic:
topic_followups. - Multi-field bridge:
broad_followups(fields=[...]). - Older neglected directions:
find_seminal.
- Specific topic:
-
Score overlap. For each retrieved direction, judge its relationship to the user's working set:
- Direct match: same problem, same method family.
- Adjacent: related problem or shared method, would extend the user's work naturally.
- Bridge: connects the user's work to an area they have not explored.
- Tangential: shares a keyword but not a meaningful link. Drop these.
-
Persist any high-quality directions via
submit_directions(paper_id, directions)(defaultmode="append"; never passmode="replace"here). Add a tag infield_tagsto mark them:"crossref:<user-theme>", so later searches can find them. Re-submitting a direction that already exists (same text) just merges your tag into it; the user's status, notes, and other runs' directions are untouched.
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.
- 8d ago Changed · +10 lines · -25 tokens per session 061436628d1a
- 11d ago First seen · 93 lines · 114 tokens per session scan A 80fb0baca8af
cross-referencer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 9d ago), licensed MIT. It adds 89 tokens to every session and 1,030 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-19.
Other agents, from other repositories
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data. Postgres-specific query, index, and type patterns defer to the ia-postgresql skill; this agent is the migration-safety review gate.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
wiki-writer
Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.