Borrowing it
Nothing to install: this file belongs to egregore-labs/egregore. 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/egregore-labs/egregore/main/.claude/skills/harvest/SKILL.mdgit clone --depth 1 https://github.com/egregore-labs/egregoreWrote 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/skills/egregore-labs/egregore/harvest)<a href="https://agentmods.dev/skills/egregore-labs/egregore/harvest"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/harvest/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/skills/egregore-labs/egregore/harvest"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/harvest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 181 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00052 | $0.02968 |
| Opus 5 | $0.00026 | $0.01484 |
| Sonnet 5 | $0.00010 | $0.00594 |
| Haiku 4.5 | $0.00005 | $0.00297 |
Grade A, and why
harvest 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run an adaptive harvest — directed elicitation that extracts, deepens, and synthesizes what people actually think about a topic.
When to invoke
User says: "harvest", "run a harvest", "I want to understand what the team thinks about", "elicit", "let's do a structured interview about", "harvest the team on", "I need to align the team on"
Not this: casual question → just answer · survey/form → different tool · unstructured chat → just talk
Arguments: $ARGUMENTS (Optional: [topic] [--respondents name1,name2] [--seed path])
Rendered surface: /harvest is the only command. When a round's findings are decision-shaped (each a real fork with 2–4 distinct options), /harvest renders them as an interactive Meridian decision surface the respondent decides on and pastes back, instead of asking inline. Decision surface is the rendered format /harvest produces — not a separate command. See the rendered-surface section below.
What to do
This command is a thin entry point. The intelligence lives in the sibling contracts next to this file — .claude/skills/harvest/PROCESS.md (the cognitive process), .claude/skills/harvest/QUESTION_PALETTE.md (question intent → move → answer shape), .claude/skills/harvest/FORMAT.md (synthesis format), .claude/skills/harvest/AUDIT.md (persistence contracts + design audit; §14 owns the rendered-surface absorb machine). Load and apply them.
Step 0: Parse invocation
From $ARGUMENTS, extract:
- topic — what the harvest is about (freeform text, everything that isn't a flag)
- respondents — if
--respondentsprovided, parse comma-separated names. Otherwise, determine from context or ask. - seed — if
--seedprovided, read the file as seed context
Get current user:
git config user.name
Step 0.5: Check graph availability
GRAPH_OK=$(bash bin/graph.sh test 2>/dev/null | jq -r '.status // "offline"')
If not "ok": note "Graph offline — running solo harvest." All graph-op calls below are non-fatal — skip them and continue conversationally. The synthesis file is the canonical record.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 210 lines · 52 tokens per session scan A 7d638d20e3a1
harvest is a skill published in the GitHub repository egregore-labs/egregore (288 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 2,968 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
xiaohongshu-image-creator
An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.
atomic-tdd
Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit…
docs-framework
This skill should be used when the user asks to "create a review report", "write a status log", "add documentation", "name this artifact", or creates files in the .devflow/docs/ directory. Provides naming conventions, templates, and directory structure for reviews, debug sessions, design docs, and all persistent…