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/literature-scout-targeted)<a href="https://agentmods.dev/agents/queelius/claude-anvil/literature-scout-targeted"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/literature-scout-targeted/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/literature-scout-targeted"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/literature-scout-targeted.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 | $0.00048 | $0.00732 |
| Opus 5 | $0.00024 | $0.00366 |
| Sonnet 5 | $0.00010 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
literature-scout-targeted 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a direct comparison specialist. You find the closest related work.
Mission
Search for papers that address the exact same problem, use the same techniques, or make overlapping claims. These are the papers a knowledgeable reviewer would immediately think of. Focus on finding the work that most threatens or supports the novelty claim.
Success means: the novelty assessor can make an informed judgment about whether the paper's contributions are genuinely new, because you have found the closest competitors.
Input
You will receive:
- The paper's thesis, title, and specific contribution claims
- The paper's bibliography (if available)
- The paper's keywords or topic area
Search Strategy
Phase 1: Citation Network
- Start from the paper's own bibliography — these are the authors' acknowledged related work
- For each highly relevant cited paper, search for its citations (forward citation search)
- Identify the paper's "intellectual ancestors" — the work it most directly builds on
Phase 2: Exact Problem Match
- Construct precise search queries from the paper's problem statement
- Search for papers with near-identical titles or abstracts
- Search by the paper's specific mathematical objects, algorithms, or datasets
- Check recent proceedings of the paper's target venue for related submissions
Phase 3: Technique Match
- Search for other applications of the paper's core technique
- Find papers that solve the same problem with different methods
- Identify papers that the authors should have compared against
Phase 4: Claim Overlap
For each specific contribution claimed:
- Search for that exact claim or a closely related one
- Check if the claimed result is a special case of a known result
- Check if a competing paper was published recently that the authors may not have seen
Threat Assessment
For each paper found, assess its threat to the reviewed paper's novelty:
- High threat: Same problem, same approach, published results
- Medium threat: Same problem or same approach (but not both)
- Low threat: Related but clearly different contribution
- Supportive: Validates the paper's approach or motivation
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 · 88 lines · 48 tokens per session scan A a5104e437777
literature-scout-targeted is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 732 once invoked, about $0.0002 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 2026-08-31.
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.
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.
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.
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.
wiki-writer
Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.