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.
git clone --depth 1 https://github.com/runnithan/claudex-setupWrote 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/commands/runnithan/claudex-setup/extract-social-lessons)<a href="https://agentmods.dev/commands/runnithan/claudex-setup/extract-social-lessons"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/extract-social-lessons.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 5.1 | $0.00052 | $0.04203 |
| Opus 5 | $0.00026 | $0.02101 |
| Sonnet 5 | $0.00010 | $0.00841 |
| Haiku 4.5 | $0.00005 | $0.00420 |
Grade A, and why
extract-social-lessons scanned grade A 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. `curl -sL "https://nitter.tiekoetter.com/<handle>"` (plain curl, no auth) renders How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract Social Lessons
Fan out a small team of research subagents over recent public posts by the
practitioners listed in references/agentic-coding-voices.md (plus the canonical
non-person sources), extract concrete Claude-Code / agentic-coding lessons, dedupe
them against what already exists, and write each new lesson as one file under
lessons/<category>/, indexed in lessons/INDEX.md.
This is the web counterpart to /extract-lessons. That command mines local
YouTube/transcript files; this one mines the open web. Both write into the same
lessons/ archive in the same format, so a lesson is a lesson regardless of where it
came from, the only frontmatter difference is source_type and the sources URL.
Run this from the root of the claudex-setup repo (the one containing references/
and lessons/).
What counts as a lesson
A concrete, actionable thing to do or stop doing when using Claude Code (or a transferable agentic-coding practice), grounded in a real quoted line with its source URL. Test each candidate against all four:
- Actionable, it tells you to do X or stop doing Y, not just "X exists." A bare feature announcement is not a lesson; extract the usage implication ("now do X instead of Y") or drop it.
- Specific, names the command / flag / hook / setting / pattern precisely enough to act on without re-reading the source.
- Grounded, you can quote a real sentence from the post and cite its URL. No quote, no lesson.
- Non-obvious, it isn't already common knowledge or already in
lessons/.
Reject vague sentiment ("Claude Code is great for refactors"), pure marketing, and anything you can't tie to a specific quoted line.
Arguments
$ARGUMENTS, optional. Free text controlling scope. Recognized hints:- empty /
new(default): search for posts not already inlessons/.processed-social.json; all: ignore the processed ledger and re-search everything;- a name/handle (e.g.
boris-cherny): scope the run to that one voice; - a recency window, e.g.
last 30 days,since 2026-06-01(default: the last 8 weeks from today); - a tier filter, e.g.
canonical onlyortier 1 only; dry-run, do everything except write files; report the plan and the candidate lessons instead.
- empty /
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.
- 6d ago First seen · 291 lines · 52 tokens per session scan A 80775c74def4
extract-social-lessons is a command published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 4,203 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
security-review
A security review procedure based on CWE, a list of common software weaknesses, and STRIDE, a method for identifying threats to a system.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
refactor
Analyze code for SOLID violations and suggest targeted improvements.
factcheck
Verify BibTeX entries and cited claims against DBLP and web sources. Checks author names, venues, years, and specific numerical claims.