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 commands/theclaymethod/artifacture/annotategit clone --depth 1 https://github.com/theclaymethod/artifactureWhat 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 | $0.00020 | $0.00362 |
| Opus 5 | $0.00010 | $0.00181 |
| Sonnet 5 | $0.00004 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
annotate 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 yesterday.
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.
What it actually says
Annotate a Visual Explainer
Open an existing HTML artifact in the local developer preview. This is a Tier 2 command: it operates on an existing file and has no creative choices, so do not ask clarification questions.
Usage
/annotate <file-path>
If no path is supplied, use the most recently generated artifact from the
current task or workspace. Fall back to the most recently modified HTML file in
~/.agent/diagrams/ only when no task-local artifact is available.
Run
node {{skill_dir}}/scripts/preview.mjs <file-path> --no-open
Follow ./references/developer-preview.md exactly: keep the process running, read the local URL from stdout, and navigate the coding agent's integrated preview browser directly to it. Do not ask the user to start the server or open the URL. Do not open preview-shell.html with file://.
The preview provides:
- Preview — interact with the page normally.
- Comment — click an exact rendered element, add a note, and immediately continue to the next element. Notes stay numbered and can be copied for a coding agent.
- Edit text — click a simple heading, label, or paragraph and type directly in the rendered page. Saving writes the owning source when available, rebuilds the artifact, and preserves the current slide; ambiguous matches require confirmation and external changes fail closed. Undo is available for edits made in the current preview process.
The developer shell and bridge are injected only into the served preview. They are never written into the deliverable HTML.
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.
- yesterday First seen · 34 lines · 20 tokens per session scan A 610fa8822ef2
annotate is a command published in the GitHub repository theclaymethod/artifacture (2 stars, last pushed 9d ago), licensed MIT. It adds 20 tokens to every session and 362 once invoked, about $0.0001 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 commands, from other repositories
editor
You are my personal writing editor for MDX/Markdown content. Improve clarity, flow, grammar, and style while preserving the author's voice, meaning, and factual details. Infer the content type and appropriate tone from the context.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.