Borrowing it
Nothing to install: this file belongs to freegyes/project-ContemPlace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/freegyes/project-ContemPlace/main/.claude/commands/extract-fragments.mdgit clone --depth 1 https://github.com/freegyes/project-ContemPlaceWrote 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/freegyes/project-contemplace/extract-fragments)<a href="https://agentmods.dev/commands/freegyes/project-contemplace/extract-fragments"><img src="https://agentmods.dev/badge/commands/freegyes/project-contemplace/extract-fragments/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/freegyes/project-contemplace/extract-fragments"><img src="https://agentmods.dev/badge/commands/freegyes/project-contemplace/extract-fragments.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.03078 |
| Opus 5 | $0.00000 | $0.01539 |
| Sonnet 5 | $0.00000 | $0.00616 |
| Haiku 4.5 | $0.00000 | $0.00308 |
Grade A, and why
extract-fragments 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 10d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract fragments
Search an Obsidian vault for notes related to a topic, decompose them into idea fragments re-voiced in the user's natural capture style, and interactively capture approved fragments into ContemPlace.
Arguments
$ARGUMENTS — the topic to search for, described naturally. Examples: "I had thoughts about making a lap steel guitar", "notes about incremental formalization and PKM design", "my reflections on bookbinding techniques". Can be empty.
Prerequisites
This command requires MCP access to both:
- Obsidian vault — semantic search and file read/update tools
- ContemPlace —
search_notesandcapture_notetools
Workflow
Phase 0: Topic selection (when no argument given)
If $ARGUMENTS is empty, help the user pick a topic:
-
Report extraction progress. Count notes with
contemplace: extractedin frontmatter (grep) and total notes withtype: ideaortype: reflectionin frontmatter (grep). Exclude non-note files (CLAUDE.md, command files). Report:Extraction progress: X / Y notes extracted (Z%) -
Identify unextracted clusters. Glob for
MOC*.mdfiles. Read each MOC and check which of its linked notes lackcontemplace: extracted. Rank MOCs by number of unextracted notes. Pick the top 3-5 MOCs with the most unextracted material. -
Present recommendations:
Suggested topics for extraction: - "topic description" — N unextracted notes (MOC Name) - "topic description" — N unextracted notes (MOC Name) ... -
Wait for the user to pick one, then proceed to Phase 1 with that topic.
Phase 1: Gather source material and style reference
Run these in parallel:
-
Search the Obsidian vault for notes matching the topic in
$ARGUMENTS. Use semantic search. Cast a wide net — the user may have written about the topic across multiple notes, under different headings, using different vocabulary. -
Search ContemPlace via
search_notesfor existing fragments related to the same topic. This serves overlap detection: if ContemPlace already has fragments covering an idea from the Obsidian notes, don't re-extract that idea. The goal is to bring in what's missing, not duplicate what exists.
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.
- 10d ago First seen · 210 lines · 0 tokens per session scan A 9e71d2f240ca
extract-fragments is a command published in the GitHub repository freegyes/project-ContemPlace (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,078 tokens. 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
quarry-dev
Manage your quarry knowledge base.
quarry
Manage your quarry knowledge base.
remember-dev
Remember inline text content in your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
learn-dev
Save a distilled lesson that gets retrieval preference. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
remember
Remember inline text content in your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
learn
Save a distilled lesson that gets retrieval preference. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.