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 skills add takubii/smithy --skill anvilgit clone --depth 1 https://github.com/takubii/smithyWrote 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/skills/takubii/smithy/anvil)<a href="https://agentmods.dev/skills/takubii/smithy/anvil"><img src="https://agentmods.dev/badge/skills/takubii/smithy/anvil.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 | $0.00060 | $0.01300 |
| Opus 5 | $0.00030 | $0.00650 |
| Sonnet 5 | $0.00012 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
anvil 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 7d 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.
anvil
Manage task state and orchestrate the workflow. This is the only skill that knows the .smithy/tasks/ storage format.
Use the workflow skills for focused phases:
- Use
forgeto produce research, plan, todos, and verification guidance. - Use
quenchto produce design questions and decisions. - Use
polishto produce independent review findings and convergence advice.
Record their results in the Smithy task file.
Core rule
Keep the user involved for product/design decisions and final approval. Do not ask the user to choose routine implementation mechanics when the codebase gives a clear answer. Escalate only when scope, acceptance criteria, risk, or non-goals change.
Implementation handoff
After the user approves the plan, delegate implementation with Task when the tool is available. Give the implementer only the execution context it needs:
- User intent.
- Acceptance criteria.
- Non-goals.
- Approved plan and decisions.
- Implementation todos.
- Relevant files, commands, and constraints.
- Verification expectations.
The implementer owns code changes for the approved scope and reports any verification it ran. anvil still owns Smithy task state, user-facing decisions, verification recording, review adjudication, and final approval. If Task is unavailable, implement directly while preserving the same boundaries.
Task state updates
Treat each Smithy task file as one document with two different zones:
- Current sections are authoritative working state. Keep them concise, current, and free of superseded plans, completed todos, rejected options, and stale assumptions.
- History sections are non-authoritative audit state. Append important decisions, progress, review outcomes, and superseded notes there so the reasoning remains available without polluting normal working context.
Update rules:
- Rewrite current sections when the active plan, todos, verification state, or open questions change.
- Remove completed todos and obsolete options from current sections.
- Append meaningful reasons for changes to the relevant history log.
- Move old but still useful information to superseded notes with what replaced it and why.
- Fix typos, broken links, and obvious recording errors in place.
- Update
Last updatedwhenever the task file changes.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 120 lines · 60 tokens per session scan A d0e5fce91783
anvil is a skill published in the GitHub repository takubii/smithy (2 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,300 once invoked, about $0.0003 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 skills, from other repositories
flow-next-plan
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
flow-next
Manage .flow/ tasks and specs. Use for show or list tasks, task status, what is ready, show fn-N. NOT for planning or executing (use the plan and work skills).
task-dependency-patterns
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.
kanban
Use when a prompt contains a new bug/feature/change not yet tracked, or when an item's status changes — capture and maintain it in the project's beads tracker (Inbox→Backlog with Definition of Ready, priorities, the pipe-separated note format).
beads
Use beads (bd) for persistent task tracking in coding projects. A git-backed issue tracker designed for AI agents with dependency graphs, hierarchical tasks, and multi-agent coordination.