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/Cristhianzl/claude-skills-czlWrote 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/cristhianzl/claude-skills-czl/update-langflow)<a href="https://agentmods.dev/commands/cristhianzl/claude-skills-czl/update-langflow"><img src="https://agentmods.dev/badge/commands/cristhianzl/claude-skills-czl/update-langflow/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/commands/cristhianzl/claude-skills-czl/update-langflow"><img src="https://agentmods.dev/badge/commands/cristhianzl/claude-skills-czl/update-langflow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.00624 |
| Opus 5 | $0.00015 | $0.00312 |
| Sonnet 5 | $0.00006 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade B, and why
update-langflow scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Variant guard.** Read the installed variant: `installed=$(cat .claude/.variant 2>/dev/null)`. If it is non-empty and **not `langflow`** (e.g. `agnostic`), **STOP**: this project has the `$installed` config, and `/upd Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://github.com/Cristhianzl/claude-skills-czl/archive/refs/heads/main.tar.gz | tar -xz -C "$tmp" What it actually says
Update the project's .claude/ to the latest langflow config from
https://github.com/Cristhianzl/claude-skills-czl, without losing local additions.
Run these steps carefully and report at the end. Stop and ask if anything is ambiguous.
-
Pre-checks.
- If
.claudeis a symlink (test -L .claude), it already tracks the kit — tell the user togit pullin the kit repo instead, then stop. - Variant guard. Read the installed variant:
installed=$(cat .claude/.variant 2>/dev/null). If it is non-empty and notlangflow(e.g.agnostic), STOP: this project has the$installedconfig, and/update-langflowwould switch variants — replacing the agnostic setup with the Langflow-specific one. Tell the user to run/update-$installedto stay on their variant, or to re-run only after explicitly confirming they want to switch tolangflow. - Confirm with the user before overwriting
.claude/.
- If
-
Download the latest config to a temp dir:
tmp=$(mktemp -d) curl -fsSL https://github.com/Cristhianzl/claude-skills-czl/archive/refs/heads/main.tar.gz | tar -xz -C "$tmp" new="$tmp/claude-skills-czl-main/configs/langflow"If
curl/tarfail, report and stop. -
Back up the current config:
cp -R .claude ".claude.bak-$(date +%Y%m%d-%H%M%S)". -
Preserve local additions (copy them aside, then restore after the sync):
- every
learnings/*.mdthat is notREADME.md(project-accumulated knowledge), settings.local.jsonif present,- any
rules/*.mdorskills/*that exist locally but not in$new(project-specific).
- every
-
Apply the update: replace the tracked parts of
.claude/(CLAUDE.md, skills, commands, hooks, rules, settings.json) with the contents of$new, then restore everything from step 4 on top. -
Report: what was updated, what was preserved, and the backup path. If the project commits
.claude/, remind the user to review the diff before committing. Clean up$tmp.
Never delete the user's learnings/ content. (Forks: change the repo URL above to your own.)
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.
- 12d ago First seen · 36 lines · 29 tokens per session scan B 296688bbd9e4
update-langflow is a command published in the GitHub repository Cristhianzl/claude-skills-czl (5 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 624 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, 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
color-palette
Generate an accessible colour palette from a hex value.
ux-extract
Exhaustively extract UX patterns from a reference web app into a reusable pattern library.
tanstack-start
Build a full-stack TanStack Start app on Cloudflare Workers from scratch.
surgical
Enforce strict scope on a task — build only what was explicitly asked, nothing more.
adr
Write an architecture decision record as Markdown in the user's repository. Use when invoked as /document-design-system:adr. Produce designed HTML or PDF only when asked.
evaluate
Execute Evaluate stage to validate generated framework artifacts.