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/obiwancenobi/klamben/extractgit clone --depth 1 https://github.com/obiwancenobi/klambenWrote 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/commands/obiwancenobi/klamben/extract)<a href="https://agentmods.dev/commands/obiwancenobi/klamben/extract"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/extract.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 | $0.00030 | $0.00530 |
| Opus 5 | $0.00015 | $0.00265 |
| Sonnet 5 | $0.00006 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
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 5d 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.
What it actually says
/extract
Mine existing screens for reusable design system pieces. The opposite of building top-down — this works bottom-up from what already exists.
When to use
- After building 3+ screens and seeing repeated patterns
- Before a design system formalization effort
- User says "we keep building the same thing" / "extract a component"
Process
- Check design context: If
.klamben.mdexists in the project root, read it first. Apply the project's brand, platform targets, accessibility tier, and existing patterns to your work below. - Scan for repetition — Walk the target path looking for:
- Repeated color literals → extract to
ColorSchemeextensions - Repeated spacing values → extract to
Spacingtheme extension - Repeated
TextStylepatterns → map totextThemeroles - Repeated widget subtrees (3+ occurrences) → extract to shared widgets
- Repeated padding/margin patterns → extract to spacing tokens
- Repeated color literals → extract to
- Group findings by type:
- Tokens (colors, spacing, typography, durations)
- Components (buttons, cards, list items, headers)
- Patterns (loading states, error handling, form layouts)
- Propose extractions to the user:
Found 3 reusable patterns: 1. UserAvatar widget (used in 4 screens) → lib/widgets/user_avatar.dart 2. Spacing tokens (8, 16, 24 used 47 times) → lib/theme/spacing.dart 3. SectionHeader widget (used in 3 screens) → lib/widgets/section_header.dart - Ask for approval before creating files
- Create shared files in
lib/widgets/orlib/theme/ - Replace inline usage with the new shared references
- Show the diff — before/after for each screen touched
Do NOT
- Extract one-off patterns (YAGNI)
- Create a shared widget library without user approval
- Move files without showing the plan first
- Break existing functionality
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.
- 5d ago First seen · 53 lines · 30 tokens per session scan A dc703df1a561
extract is a command published in the GitHub repository obiwancenobi/klamben (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 530 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
grill-me
Relentless checkpointed discovery interview that interrogates a half-formed idea until its shape is clear, then hands off to ISA Scaffold. Routes to the ISA skill's Grill workflow. USE WHEN /grill-me, grill me, discovery interview, figure out the shape, brainstorm before scaffolding an ISA. NOT FOR filling an existing…
update-faq
could you please update DESIGNFAQ & DXFAQ based on the changes we are trying to achieve.
is-not-duplicated
please investigate the codebase based on your changes - do we have code duplication? After analysis, write updates to DUPLICATIONREPORT.md with the results. Keep in mind that other agents could keep their records, so you need to check the document first, decided to update or add new information.
speckit.gh-triage.feature
Create a GitHub issue describing a new feature, label it with the configured feature label, and optionally auto-run speckit.specify to turn it into a spec.
speckit.tdd.plan
Derive the feature's test list by delegating to zfa tdd plan (deterministic engine); falls back to LLM-guided derivation only when zfa is unavailable.
speckit.tdd.verify
Audit TDD discipline by delegating to zfa tdd verify (mutation testing, evidence integrity); the LLM interprets the verdict and drives remediation.