Borrowing it
Nothing to install: this file belongs to zkysar1/Claude-Mind. 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/zkysar1/Claude-Mind/main/.claude/skills/seed/SKILL.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/zkysar1/claude-mind/seed)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/seed"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/seed/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/zkysar1/claude-mind/seed"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/seed.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 | $0.00162 | $0.03800 |
| Opus 5 | $0.00081 | $0.01900 |
| Sonnet 5 | $0.00032 | $0.00760 |
| Haiku 4.5 | $0.00016 | $0.00380 |
Grade D, and why
seed scanned grade D with 2 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`Bash: grep -rn "Ayoai-Mind\|ZakNoCloud\|Zachary" <dest>/.claude/settings.json <dest>/CLAUDE.md <dest>/README.md` Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- If `--fresh-git`: `Bash: rm -rf <dest>/.git && git -C <dest> init` How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/seed — Framework Seed Management
Manages the framework seed: creates the seed manifest, transplants framework files to a destination repo (applying domain → generic transformations at copy time), verifies destination integrity, and diffs source against destination.
The source repo (your working AyoAI deployment, or any domain deployment) stays
UNTOUCHED. Cleanup happens at copy time via transformation rules defined in
core/config/seed-manifest.yaml. This separates "your live working environment"
from "the publishable framework abstraction."
Naming (2026-06-03): this skill's copy verb was renamed
transplant→plant. A seed is domain-free — planting it grows a NEW, empty environment (e.g. claude-mind) with no agents, no world, no learned state. The word transplant is now reserved for relocating a living mind (its agents + world + meta + identity) to another machine — see the/transplantskill.
Mode Gate
This skill requires assistant or autonomous mode (creates new files at source
for manifest/skill maintenance; copies framework files to destination).
Bash: session-mode-get.sh
IF mode is "reader":
Bash: echo "Skill requires assistant mode. Run /start --mode assistant to enable."
STOP.
Step 0: Load Conventions
Bash: load-conventions.sh session-state external-paths
Read only the paths returned (files not yet in context). If output is empty, all conventions already loaded — proceed.
Sub-Commands
/seed create [--manifest <path>] [--dry-run]
/seed plant <destination> [flags]
/seed verify <destination>
/seed diff <destination>
/seed create — Build or Update Seed Manifest
For the initial seed, the manifest is hand-curated and committed at
core/config/seed-manifest.yaml (Phase 1.5a of publication-cleanup-plan.md).
This sub-command is reserved for MAINTENANCE — when new framework files are
added to source, /seed create scans for them and proposes manifest updates.
Step 1: Read existing manifest at core/config/seed-manifest.yaml (or --manifest <path>).
Step 2: Scan source repo for files added/removed since manifest.updated date.
Step 3: Propose include/exclude updates for changed files:
- New SKILL.md → propose addition to
include[".claude/skills/"] - New convention → propose addition to
include["core/config/conventions/"] - Renamed forged skill → propose update to
exclude_childrenStep 4: If--dry-run, print proposed changes; else write updated manifest with bumpedupdateddate. Step 5: Report.
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.
- 9d ago First seen · 297 lines · 162 tokens per session scan D 80b56121d6e5
seed is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 3,800 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.