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 skills add akseolabs-seo/AK-Threads-booster --skill optimizegit clone --depth 1 https://github.com/akseolabs-seo/AK-Threads-boosterWrote 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/akseolabs-seo/ak-threads-booster/optimize)<a href="https://agentmods.dev/skills/akseolabs-seo/ak-threads-booster/optimize"><img src="https://agentmods.dev/badge/skills/akseolabs-seo/ak-threads-booster/optimize/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/akseolabs-seo/ak-threads-booster/optimize"><img src="https://agentmods.dev/badge/skills/akseolabs-seo/ak-threads-booster/optimize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.01757 |
| Opus 5.5 | $0.00028 | $0.00703 |
| Sonnet 5.5 | $0.00014 | $0.00351 |
| Haiku 4.5 | $0.00007 | $0.00176 |
Grade A, and why
optimize 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 1mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AK-Threads-Booster Skill-Level Compound Module
You are the compound-loop worker for AK-Threads-Booster. /review captures skill-level misses (the sub-skill gave bad advice, the user proved it wrong) into threads_skill_learnings.log. This skill turns that log into concrete rule changes inside the sub-skills themselves.
Ships with this skill. No external meta-skill required. Every proposed edit requires the user's approval before it lands.
Principles & Knowledge
Load knowledge/_shared/principles.md and knowledge/_shared/compound-log-format.md (the log schema). No skill-specific knowledge files beyond those.
Core rules:
- User signal is sacred. Never propose a rule change that is not backed by at least one
user_signalquote in the log. If a cluster has zero user signals, it cannot drive an edit. - Propose, do not auto-patch. Every edit — even trivial wording — waits for an explicit "yes" from the user on that specific proposal. Batch approvals ("do them all") are fine; silent writes are not.
- Strip the log honestly. When the user approves an edit, append a
supersedesline referencing therun_ids addressed. Do not rewrite or delete prior entries. - Stay inside the skill. Only edit files under this skill's tree:
skills/*/SKILL.md,skills/*/references/*.md,knowledge/**/*.md,templates/*.md. Never touch the user's tracker, brand voice, or logs.
User Data Paths
Glob in the working directory and the skill root:
threads_skill_learnings.log— the compound log written by/reviewskills/*/SKILL.md+skills/*/references/*.md— sub-skill rule surfaceknowledge/_shared/*.md— shared rules (red-lines, discovery, principles, config, compound log format)
If threads_skill_learnings.log is missing or empty, tell the user there is nothing to optimize yet and stop cleanly.
Execution Flow
Step 1: Load and Cluster
- Read every JSON line in
threads_skill_learnings.log. Validate each against the schema inknowledge/_shared/compound-log-format.md— skip and warn on malformed lines; do not error out. - Ignore entries whose
statusis already"addressed"or that are superseded by a later entry. Walk forward; keep only the final open entry for eachrun_idchain. - Cluster by
(sub_skill, category). Report cluster sizes:
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.
- 1mo ago First seen · 139 lines · 70 tokens per session scan A 067d3534e3d7
optimize is a skill published in the GitHub repository akseolabs-seo/AK-Threads-booster (281 stars, last pushed 8d ago), licensed MIT. It adds 70 tokens to every session and 1,757 once invoked, about $0.0003 per session on Opus 5.5. 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
gr-social-distill
A content-repurposing workflow that turns one published blog post into several social-media formats, including an X thread, a Xiaohongshu post, a LinkedIn carousel, and a dev.to or Zenn article.
content-pillar-atomizer
Take 1 blog post or article and generate 15-30 platform-native micro-content pieces. Not reformatting — re-contextualizing for each platform's culture. Triggers on: "atomize this content", "repurpose my blog post", "turn this into social posts", "content atomizer", "pillar content", "one to many content", "repurpose…
twitter-thread-writer
Write X/Twitter threads that get bookmarked, shared, and drive affiliate clicks. Use this skill when the user asks about writing Twitter threads, X threads, tweet threads for affiliate marketing, or says "write a thread about X", "Twitter thread promoting X", "X thread for affiliate", "write tweets that go viral"…
instagram-trend-scout
Researches what is currently working on Instagram for a niche using web search only - no API or login - and returns a structured scouting report of top content, winning Reel and carousel formats, reusable hook patterns, content gaps, and an engagement benchmark with honest confidence labels. Use when someone asks…
zernio
Schedule posts, manage inbox, broadcasts, sequences, and automations across 14 platforms from the CLI.
content-pillar-atomizer
Take 1 blog post or article and generate 15-30 platform-native micro-content pieces. Not reformatting — re-contextualizing for each platform's culture. Triggers on: "atomize this content", "repurpose my blog post", "turn this into social posts", "content atomizer", "pillar content", "one to many content", "repurpose…