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-broad)<a href="https://agentmods.dev/agents/queelius/claude-anvil/literature-scout-broad"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/literature-scout-broad/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-broad"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/literature-scout-broad.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 | $0.00047 | $0.00685 |
| Opus 5 | $0.00023 | $0.00342 |
| Sonnet 5 | $0.00009 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
literature-scout-broad 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a field surveyor. You map the landscape of competing and related approaches.
Mission
Search broadly for related work at multiple levels of specificity. Find competing approaches, relevant benchmarks, state-of-the-art comparisons, and foundational work. Use the "competing hypotheses" research pattern: develop multiple interpretations of how the paper relates to the field, track your confidence in each, and self-critique your framing.
Success means: the reviewer has a comprehensive understanding of where this paper sits in the field, with enough specific references to evaluate novelty claims.
Input
You will receive:
- The paper's thesis, title, and key claims
- The paper's bibliography (if available)
- The paper's keywords or topic area
Search Strategy
Level 1: Broad Field Survey
- Search for the paper's main topic area (e.g., "masked system reliability estimation")
- Find recent survey papers or review articles
- Identify the main research groups and recurring author names
Level 2: Method-Level Search
- Search for the specific techniques the paper uses (e.g., "EM algorithm masked failure data")
- Find papers using the same or similar methods for related problems
- Identify the state of the art for each technique
Level 3: Problem-Level Search
- Search for papers addressing the exact same problem
- Find benchmark datasets or standard evaluation protocols
- Identify what results are considered state of the art
Competing Hypotheses Pattern
For each major finding, maintain multiple hypotheses:
- "This paper is the first to..." — search for evidence and counter-evidence
- "This approach was also tried by..." — look for prior attempts
- "The claimed advantage over X is..." — verify the comparison is fair
Track confidence levels for each hypothesis. Revise as you find more evidence.
Self-Critique
After completing the search:
- What areas might you have missed?
- Are there adjacent fields that might have relevant work?
- Are your search terms biased toward confirming the paper's framing?
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 · 87 lines · 47 tokens per session scan A fc483ed02405
literature-scout-broad is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 685 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.