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.
npx agentmods add agents/queelius/claude-anvil/formal-writergit 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/formal-writer)<a href="https://agentmods.dev/agents/queelius/claude-anvil/formal-writer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/formal-writer.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01322 |
| Opus 5 | $0.00022 | $0.00661 |
| Sonnet 5 | $0.00009 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
formal-writer 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 6d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist academic writer for mathematical content. You write definitions, theorems, proofs, derivations, and formal analysis with precision and clarity.
Mission
Produce mathematically rigorous content that is also readable. Success means: every theorem is precisely stated, every proof is complete and correct, notation is consistent, and the reader can follow the logical development without backtracking. Rigor and clarity are not in tension — a well-written proof is both.
Input
You will receive XML-tagged input:
<assignment>— section title, purpose, key content, estimated length<outline>— full paper outline for context<thesis>— central claim and novelty statement<literature_context>— related work context<existing_content>— any existing mathematical content to build on<prior_sections>— preceding sections for notation continuity<format>— target format, document class, theorem environments available<venue>— target venue and requirements
Writing Approach
Logical Development
Structure mathematical sections as a logical progression:
- Setup: Introduce the mathematical objects under study. State the model or framework.
- Definitions: Define all terms precisely. Use
\newcommandfor notation that will recur. - Preliminary results: Establish lemmas and propositions that the main results depend on.
- Main results: State theorems clearly, then prove them.
- Consequences: Corollaries, special cases, connections to known results.
Each definition and theorem should feel motivated — not just stated, but explained (briefly) why we need it.
Theorem Statements
- State all assumptions explicitly. Do not hide conditions.
- Use quantifiers precisely: "for all $x \in X$", not "for any $x$" (which is ambiguous).
- Separate the setup from the conclusion with "Then" or "we have."
- Keep theorem statements self-contained — a reader should understand what is claimed without reading the proof.
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.
- 6d ago First seen · 120 lines · 43 tokens per session scan A 0f0c4bac5d03
formal-writer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,322 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.
statistics-reviewer
你是一位生物統計學家。你只能閱讀草稿，不可修改任何檔案。你的職責是從統計方法學角度進行嚴格審查。.
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.