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/a8cteam51/claude-code-plugins/extractgit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWhat 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 | $0.00035 | $0.00508 |
| Opus 5 | $0.00017 | $0.00254 |
| Sonnet 5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
extract 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
/figma-extract:extract
Extract the images, screenshot, and design context for a Figma selection by
running the bundled, zero-dependency extractor. All MCP transport, asset
parsing, and downloading is delegated to
${CLAUDE_PLUGIN_ROOT}/scripts/extract-figma-assets.mjs — do not reimplement
it or call the Figma MCP tools yourself. This command mirrors the
extract-figma-assets skill; the skill's body has the full reference.
Inputs
Parse $ARGUMENTS (all optional):
- A bare node id (
1:23/1-23) or a Figma URL (contains?node-id=…) → pass as--node <value>. If absent, the script uses the current selection in Figma desktop. --out <dir>→ output directory. If the user didn't specify one, default to./figma-extract.- The script saves images + screenshot only by default. Pass
--context(alias--full) through to the script only if the user also asks for the generated code, variables, or metadata.
Run
node "${CLAUDE_PLUGIN_ROOT}/scripts/extract-figma-assets.mjs" \
[--node <id|url>] --out <dir> --json
Progress goes to stderr; a JSON manifest is printed to stdout.
Report
Summarise from the JSON manifest: number of assets downloaded (raster/svg split), any cached/failed counts, the absolute output path, and the image filenames.
If the script reports Nothing is selected, tell the user to select a frame in
Figma desktop (or pass a node id / URL) and re-run — do not retry blindly. If
counts.referenced is 0, say the selection referenced no placed images; the
screenshot and design context were still saved.
Requires Figma desktop running with Dev Mode MCP enabled and Node.js 20+.
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 · 49 lines · 0 tokens per session scan A de4a0ad19307
extract is a command published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 508 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 commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.