Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/yusufkaraaslan/skill_seekers/chatnpx skills add yusufkaraaslan/Skill_Seekers --skill chatgit clone --depth 1 https://github.com/yusufkaraaslan/Skill_SeekersWhat 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 | $0.00012 | $0.01105 |
| Opus 5 | $0.00006 | $0.00553 |
| Sonnet 5 | $0.00002 | $0.00221 |
| Haiku 4.5 | $0.00001 | $0.00111 |
Grade A, and why
golden-chat 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 yesterday.
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Golden_Chat Slack Chat Skill
Use when testing the golden_chat golden build
📋 Slack Chat Information
Platform: Slack
Source: fixtures/slack-export/
Total Messages: 6
Unique Users: 3
Channels: #engineering, #random
💡 When to Use This Skill
Use this skill when you need to:
- Find solutions discussed in golden_chat chat history
- Reference code snippets shared by team members
- Understand team decisions and architectural discussions
- Look up troubleshooting steps from past conversations
- Find shared links and resources from the team
📖 Content Overview
Total Sections: 3
Content Breakdown:
- #engineering: 2 sections
- #random: 1 sections
🔑 Key Discussion Topics
Topics frequently discussed in chat
- Troubleshooting: 1 conversations
- Setup: 1 conversations
📝 Top Code Snippets
High-quality code shared in chat
Python (2 snippets)
Snippet 1 (by bob) (Quality: 9.5/10):
def long_helper():
y0 = 0
y1 = 1
y2 = 2
y3 = 3
y4 = 4
y5 = 5
y6 = 6
y7 = 7
y8 = 8
y9 = 9
y10 = 10
y11 = 11
y12 = 12
y13 = 13
y14 = 14
y15 = 15
y16 = 16
y17 = 17
y18 = 18
y19 = 19
y20 = 20
y21 = 21
y22 = 22
y23 = 23
y24 = 24
y25 = 25
y26 = 26
y27 = 27
y28 = 28
y29 = 29
y30 = 30
y31 = 31
y32 = 32
y33 = 33
y34 = 34
y35 = 35
y36 = 36
y37 = 37
y38
...
Snippet 2 (by bob) (Quality: 7.0/10):
print('patched')
Unknown (1 snippets)
Snippet 1 (by alice) (Quality: 4.0/10):
kubectl get pods
🔗 Shared Links (21)
Key resources shared in chat
- https://example.com/resource/0 (by alice, in #engineering)
- https://example.com/resource/1 (by carol, in #random)
- https://example.com/resource/2 (by alice, in #engineering)
- https://example.com/resource/3 (by carol, in #random)
- https://example.com/resource/4 (by alice, in #engineering)
- https://example.com/resource/5 (by carol, in #random)
- https://example.com/resource/6 (by alice, in #engineering)
- https://example.com/resource/7 (by carol, in #random)
- https://example.com/resource/8 (by alice, in #engineering)
- https://example.com/resource/9 (by carol, in #random)
- https://example.com/resource/10 (by alice, in #engineering)
- https://example.com/resource/11 (by carol, in #random)
- https://example.com/resource/12 (by alice, in #engineering)
- https://example.com/resource/13 (by carol, in #random)
- https://example.com/resource/14 (by alice, in #engineering)
- https://example.com/resource/15 (by carol, in #random)
- https://example.com/resource/16 (by alice, in #engineering)
- https://example.com/resource/17 (by carol, in #random)
- https://example.com/resource/18 (by alice, in #engineering)
- https://example.com/resource/19 (by carol, in #random)
What ships with it
3 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.
- yesterday First seen · 166 lines · 12 tokens per session scan A 3a914bd08604
golden-chat is a skill published in the GitHub repository yusufkaraaslan/Skill_Seekers (14,860 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 1,105 once invoked, about $0.0001 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
verify
Visual verification as the Definition of Done for any change with a runtime surface (a rendered page, a UI, a live view). Use whenever you are about to call a UI or frontend change done, before moving an item to done, whenever an item is marked ui: true, or when someone asks "does it actually render / work". Proves…
lighthouse-fix
Analyzes and fixes common Lighthouse performance score issues.
post
Post content directly to X via browser automation. Use when the user wants to publish a composed post or thread to X/Twitter without copy-pasting. Requires claude-in-chrome.
engage
Manage replies and conversations on X via browser automation. Surfaces comments worth replying to, drafts optimized replies, and posts them with your approval. Activates the 75-150x conversation velocity multiplier. Requires claude-in-chrome.
media
Plan and create visual content for X posts. Use when the user wants to add images, videos, GIFs, screenshots, or any visual media to their X content. Also use when deciding what kind of visual would best complement a post.
compose
Draft algorithm-optimized X posts. Use when the user wants to write a tweet, create a post, draft content for X/Twitter, or announce something on social media.