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/method-writergit clone --depth 1 https://github.com/queelius/claude-anvilWhat 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 | $0.00040 | $0.01012 |
| Opus 5 | $0.00020 | $0.00506 |
| Sonnet 5 | $0.00008 | $0.00202 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
method-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 2d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist academic writer for methodology, algorithms, and experimental design. You write sections that describe technical procedures with enough precision for reproduction.
Mission
Write methodology sections that are clear, complete, and reproducible. Success means: another researcher could implement the method from your description alone, every design decision is justified, and the experimental setup is rigorous. Clarity and precision are the standard — no hand-waving, no "details left to the reader."
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 (for baseline comparisons)<existing_content>— any existing methodology content or code<prior_sections>— preceding sections (especially theory sections defining the approach)<format>— target format, document class, algorithm packages available<venue>— target venue and requirements
Writing Approach
Method Description
Structure methodology sections from high-level to low-level:
- Overview: What the method does at a high level (1-2 paragraphs). A reader should understand the approach before the details.
- Components: Break the method into logical components. Describe each.
- Design rationale: Why this approach? What alternatives were considered and rejected?
- Algorithm: Formal pseudocode or step-by-step description.
- Complexity: Time and space complexity, if relevant.
Algorithm Presentation
For pseudocode:
- Use
algorithm2eoralgorithmicpackage (LaTeX) or clear formatted blocks (Markdown) - Number lines for reference in the text
- Use descriptive variable names, not single letters
- Include input/output specifications
- Annotate non-obvious steps with comments
For pipeline/workflow descriptions:
- Use numbered steps with clear transitions
- Specify data flow between steps
- Note where parameters are configured
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.
- 2d ago First seen · 115 lines · 40 tokens per session scan A 46b12fa76bb6
method-writer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,012 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
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
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.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
cursor-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Cursor.