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/tokenbender/agent-guides/x-thread-readernpx skills add tokenbender/agent-guides --skill x-thread-readergit clone --depth 1 https://github.com/tokenbender/agent-guidesWhat 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 | $0.00066 | $0.00460 |
| Opus 5 | $0.00033 | $0.00230 |
| Sonnet 5 | $0.00013 | $0.00092 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
x-thread-reader 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 2d 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.
What it actually says
X Thread Reader
Use this skill whenever an X/Twitter post may need more than the top-post text.
Workflow
-
Extract the tweet id from the URL.
- Match
x.com/<user>/status/<id>,twitter.com/<user>/status/<id>, or equivalent status URLs. - Ignore query parameters such as
?s=20.
- Match
-
Build the thread-reader URL:
https://twitter-thread.com/t/<tweet_id> -
Fetch the Twitter Thread Reader page before drawing conclusions from a single X post.
- Use it to recover the thread text, tweet count, linked media alt text, quoted/replied context, and embedded links when available.
- Cite the thread-reader URL in the final answer when it shaped the answer.
-
Fall back only if Twitter Thread Reader fails or is missing tweets.
- Try
api.fxtwitter.com,cdn.syndication.twimg.com/tweet-result, X embed/oEmbed, web search, or browser-rendered inspection as appropriate. - State uncertainty when mirrors fail or only partial text is available.
- Try
Output Rules
- Do not infer a thread's meaning from the opening tweet alone when a thread-reader page is available.
- When comparing a thread to a local project, read the thread first, then compare it against the relevant local docs or code.
- Preserve exact user output contracts. For title/capture tasks, return only the requested title format.
- Avoid guessed content. If the full thread cannot be verified, say what was verified and what was not.
Example
https://x.com/FredKSchott/status/2050274923852210397?s=20
-> https://twitter-thread.com/t/2050274923852210397
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.
- 2d ago First seen · 45 lines · 66 tokens per session scan A 1f7a6d0b7364
x-thread-reader is a skill published in the GitHub repository tokenbender/agent-guides (368 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 460 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…