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/harvest-ideas.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/harvest-ideas)<a href="https://agentmods.dev/commands/freegyes/project-contemplace/harvest-ideas"><img src="https://agentmods.dev/badge/commands/freegyes/project-contemplace/harvest-ideas/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/harvest-ideas"><img src="https://agentmods.dev/badge/commands/freegyes/project-contemplace/harvest-ideas.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 | $0.01887 |
| Opus 5 | $0.00000 | $0.00944 |
| Sonnet 5 | $0.00000 | $0.00377 |
| Haiku 4.5 | $0.00000 | $0.00189 |
Grade A, and why
harvest-ideas 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 11d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harvest ideas
Search the ContemPlace corpus for captured thoughts about ContemPlace itself, PKM, and related topics. Cross-reference with open GitHub issues. Surface ideas worth acting on — as new issues, comments on existing ones, or notes that a prior idea has evolved.
Arguments
$ARGUMENTS — optional search focus (e.g., "synthesis", "gardening", "capture quality"). Defaults to a broad sweep of ContemPlace/PKM-related fragments.
Workflow
Phase 1: Pull relevant fragments from the corpus
Run these MCP searches in parallel. Cast a wide net — the user captures thoughts about their own system in many registers:
search_notes— query: "ContemPlace"search_notes— query: "personal knowledge management"search_notes— query: "note-taking workflow"search_notes— query: "capture and retrieval"search_notes— query: "linking and synthesis"- If
$ARGUMENTSprovides a focus term, add a targeted search for that term.
Deduplicate results by note ID. The search results already include body text — only call get_note for fragments that look actionable (to get raw_input for quoting). Don't fetch full records for everything; it's expensive and most older fragments won't survive filtering.
Also call list_recent with limit 20 and scan for any fragments that touch ContemPlace/PKM topics but didn't match the keyword searches. The user often captures system ideas without naming the system explicitly — look for fragments about workflows, information structure, tagging, memory, curation, friction, tools.
Weight recent fragments heavily. Fragments from the last 48-72 hours are where actionable material lives. Older fragments from the initial corpus load are likely already encoded in docs/philosophy.md, existing issues, or ADRs. Don't re-surface design principles that are already planted — only older fragments that represent genuinely untracked ideas.
Phase 2: Pull open GitHub issues
Fetch the current issue landscape using gh CLI via Bash to get a concise list (the GitHub MCP list_issues tool returns enormous payloads):
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.
- 11d ago First seen · 115 lines · 0 tokens per session scan A 4f27fa45f2f7
harvest-ideas 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 1,887 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.