A skill that reads the current Claude Code session log and turns recent work into possible tweets. The log records user prompts and the agent's written responses and tool actions.

Use it after building or debugging something when you want to save the work as tweet material. It helps review the session and shape the relevant events into a social-media draft.

It avoids reconstructing what happened in a coding session from memory. The raw activity is already collected, so the skill can use it as source material for a draft.

seed — Skill for Claude Code by Yrzhe

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Yrzhe/claude-skills

Claude Code

/plugin install seed

Made for: Claude Code.

Or install seed, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yrzhe/claude-skills/seed/github.svg)](https://agentmods.dev/skills/yrzhe/claude-skills/seed)

Your own site

<a href="https://agentmods.dev/skills/yrzhe/claude-skills/seed"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yrzhe/claude-skills/seed"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/seed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,657 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00064	$0.01657
Opus 5	$0.00032	$0.00829
Sonnet 5	$0.00013	$0.00331
Haiku 4.5	$0.00006	$0.00166

Measured 12d ago against content hash 5130aec982aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

seed scanned grade C with 1 finding 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 12d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (hooks/capture-session-seed.sh, scripts/extract_turn.py, scripts/shot.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

A Stop hook silently records every turn of every Claude Code session into a per-session markdown file. When the user wants to tweet about what they just did, you read that file and help them turn raw activity into a draf

plugins/seed/skills/seed/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Seed (auto-recorded, on-demand synthesized)

A Stop hook silently records every turn of every Claude Code session into a per-session markdown file. When the user wants to tweet about what they just did, you read that file and help them turn raw activity into a draft.

Architecture

~/.claude/
├── hooks/capture-session-seed.sh    # Stop hook → appends turn record
├── skills/seed/
│   ├── SKILL.md                     # (this file)
│   ├── scripts/
│   │   ├── extract_turn.py          # called by the hook
│   │   └── shot.py                  # /seed shot — screenshot + session binding
│   └── state/
│       ├── sessions/{session_id}.md        # raw turn logs, one per session
│       ├── sessions/{session_id}/shots/    # screenshots bound to that session
│       └── archive/                        # optional: consumed seeds moved here

The hook is mechanical — it extracts the last user prompt + all assistant text/tool_use blocks for that turn and appends a markdown block. No scoring, no synthesis, no LLM call. De-duped by user-prompt uuid so repeat Stops on the same turn don't double-write.

When User Invokes

`/seed` — read-and-synthesize flow

Get current session's file:
- Read $CLAUDE_SESSION_ID if exported, otherwise ask the user (the ID is the jsonl filename in ~/.claude/projects/.../<session-id>.jsonl)
- Path: ~/.claude/skills/seed/state/sessions/{session_id}.md
Read the full session log. It's a flat list of turns, each with:
- Timestamp
- User prompt
- Tools used (name + short input summary)
- Full assistant output
Synthesize: scan for the genuinely tweet-worthy moments — specific decisions, non-obvious observations, concrete data points, real problems solved. Skip routine back-and-forth.
Present 2–3 draft tweet angles tied to actual evidence from the log. Each draft must:
- Reference a real action from the log (tool used, file touched, problem faced)
- Include specific detail (number, tool name, timing)
- Lead with reframe or observation, not agreement
- Sound human: no AI-slop phrases ("The real X isn't Y, it's Z", "Happy to...", "Makes me think...")
- 200–350 chars for replies; longer is fine for standalone originals
Ask which draft the user wants refined.

Read the full file on GitHub · 134 lines

Files

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.

Changes

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.

12d ago First seen · 134 lines · 64 tokens per session scan C 5130aec982aa

Subscribe to this mod's changes

seed is a skill published in the GitHub repository Yrzhe/claude-skills (33 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 1,657 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

seed