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/sergebulaev/threads-skills/threads-profile-optimizernpx skills add sergebulaev/threads-skills --skill threads-profile-optimizergit clone --depth 1 https://github.com/sergebulaev/threads-skillsWrote 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/sergebulaev/threads-skills/threads-profile-optimizer)<a href="https://agentmods.dev/skills/sergebulaev/threads-skills/threads-profile-optimizer"><img src="https://agentmods.dev/badge/skills/sergebulaev/threads-skills/threads-profile-optimizer.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.01457 |
| Opus 5 | $0.00056 | $0.00728 |
| Sonnet 5 | $0.00022 | $0.00291 |
| Haiku 4.5 | $0.00011 | $0.00146 |
Grade A, and why
threads-profile-optimizer 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 5d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threads Profile Optimizer
Audit the parts of a Threads profile (photo, name, @handle, bio, link, pinned post) against what actually converts a profile-visitor into a follower in 2026, then rewrite each part that needs it. On Threads the whole decision happens in a couple of seconds on the profile card: name, bio, pinned post. Threads runs warmer than X, so the bio should read like a person, not a company. And because a Threads account is stapled to an Instagram account, a strong Instagram presence feeds Threads discovery, so this skill checks that cross-pull too.
When to use
- User pastes their Threads profile or handle and asks for an audit
- "Fix my Threads bio", "rewrite my bio", "what should I pin on Threads"
- User is starting to post seriously and wants the profile to match
- Any of: "review my Threads profile", "profile audit", "what to pin on Threads"
Not for writing posts (use threads-post-writer) or auditing a single draft
(use threads-humanizer).
Input
- Profile URL / handle (or a screenshot of the profile card)
- Goal: grow a following / drive signups / land clients / build authority. The bio close and the pinned post change by goal.
- Optional: their best-performing posts, to pick a pin
- Optional: the connected Instagram handle, to score the cross-pull
Output
- Scorecard (each part: pass / needs-work / fail)
- Priority fixes ranked by impact (bio and pin first, always)
- Before -> After rewrites for each failing part
- Pinned-post pick with the reason
- Instagram cross-pull note: what to fix on IG so it feeds Threads
Steps
- Intake. Collect the profile state, the goal, and the connected Instagram handle if they want the cross-pull scored.
- Score each part against the scorecard below.
- Rewrite the bio (150 chars). Shape:
who you help or what you post about + one specific + a warm human line. Lead with the value, not a job title. Write it like you talk. No "I help X do Y" cliche opener unless the rest is specific. Fit inside 150 chars, tight wins. - Fix the name. Real name plus a searchable keyword people actually type (e.g. "Sam Rivera, AI agents"). The name field is searchable; the @handle mostly is not, so the keyword belongs in the name.
- Check the @handle. Short, memorable, matches the Instagram handle if possible (Threads and Instagram share the handle, so consistency helps discovery). No stray numbers or underscores if avoidable.
- Pick the pinned post. Their single best proof of what a new follower gets: a top post, a mini-thread that teaches, or a clear offer matched to the goal. You can pin up to 3 on Threads; lead with the strongest. An empty pin slot wastes the most valuable real estate on the card.
- Set the link. One link matched to the goal (newsletter / offer / site). If they need several, a single link-hub, not a bare homepage.
- Photo check. Clear face, fills the frame, recent, high contrast. It renders as a small circle for most viewers, so detail is wasted but contrast is not. Match the Instagram photo so the two profiles read as one person.
- Score the Instagram cross-pull. A connected, active Instagram with an aligned name, photo, and bio feeds Threads suggestions and "who to follow". Flag a dormant or mismatched IG as a discovery leak, and name the one fix.
- Deliver the before/after diff plus the two-second test: read only name, bio, and pin, and ask "would a stranger follow from this alone?"
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.
- 5d ago First seen · 105 lines · 111 tokens per session scan A 6bcb0db47e92
threads-profile-optimizer is a skill published in the GitHub repository sergebulaev/threads-skills (21 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 1,457 once invoked, about $0.0006 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
x-marketing
Plan, draft, audit, and publish posts and threads for X (Twitter). Use when the user wants to write a single tweet or an auto-numbered thread, build a long-form tweetstorm, remove AI tells from a draft, reverse-engineer the hook from a viral tweet, draft a reply or quote tweet, or plan a week of X content. Tweets and…
x-humanizer
Scrub AI tells from any tweet or thread draft, or audit a finished draft against the 2026 X (Twitter) checklist. Strips em dashes, AI vocabulary (leverage, fundamentally, delve, harness), rule-of-three lists, and uniform tweet rhythm, then adds human fingerprints. Includes a --mode audit pre-publish check (280-char…
facebook-marketing
Plan, draft, audit, and publish posts for a Facebook Page. Use when the user wants to write a short punchy Page post or a longer story post, remove AI tells from a draft, reverse-engineer the hook from a high-share Page post, draft replies to comments on their Page, or plan a week of Facebook Page content. Page posts…
fb-humanizer
Scrub AI tells from any Facebook Page post draft, or audit a finished draft against the 2026 Facebook checklist. Strips em dashes, AI vocabulary (leverage, delve, harness), "We are thrilled to announce" openers, and corporate auto-pilot, then adds human fingerprints. Includes a --mode audit pre-publish check (under-80…
tiktok-marketing
Plan, script, caption, and publish short-form video for TikTok. Use when the user wants to write the first 1-3 second hook (spoken line plus on-screen text), draft a caption under 2,200 chars with TikTok settings and hashtags, ride a trending sound without being cringe, strip AI tells from a spoken script to sound…
tt-humanizer
Strip AI-script tells from a TikTok spoken script and caption so it sounds like a person talking on camera, not a teleprompter. Removes em dashes, AI vocabulary (leverage, fundamentally, delve, harness), rule-of-three lists, written-not-spoken phrasing, and "hey guys" filler, then adds contractions and one specific…