Borrowing it
Nothing to install: this file belongs to susomejias/rembric. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/susomejias/rembric/main/.agents/skills/rembric-tui-installer-e2e/SKILL.mdgit clone --depth 1 https://github.com/susomejias/rembricWrote 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/susomejias/rembric/rembric-tui-installer-e2e)<a href="https://agentmods.dev/skills/susomejias/rembric/rembric-tui-installer-e2e"><img src="https://agentmods.dev/badge/skills/susomejias/rembric/rembric-tui-installer-e2e/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/susomejias/rembric/rembric-tui-installer-e2e"><img src="https://agentmods.dev/badge/skills/susomejias/rembric/rembric-tui-installer-e2e.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 | $0.00180 | $0.02991 |
| Opus 5 | $0.00090 | $0.01496 |
| Sonnet 5 | $0.00036 | $0.00598 |
| Haiku 4.5 | $0.00018 | $0.00299 |
Grade A, and why
rembric-tui-installer-e2e scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rembric TUI installer — e2e validation
Run this before merging/deploying an install/distribution change so a regression is caught locally, not in a broken release. Layers are ordered by cost/feasibility — always run the headless + local layers; run the interactive + Docker layers when a real terminal / Docker is available.
REPO=$(git rev-parse --show-toplevel) in every snippet below.
Layer 1 — Headless (CI-safe, always run)
# 1a. The headless test suite (args, preflight, server install incl. empty-token
# refill, server update, agent routing, output degradation, root-shim parity).
cd "$REPO/apps/server" && pnpm vitest run ../../install.test.ts
# 1b. POSIX syntax — dash-compatible, no bashisms.
cd "$REPO"
sh -n install.sh
sh -n apps/plugin/install.sh
for f in apps/plugin/.*/install.sh apps/plugin/.*/uninstall.sh; do [ -f "$f" ] && sh -n "$f"; done
Layer 2 — Local install round-trips (no network, throwaway HOME)
REMBRIC_SRC makes the installer read everything from the working tree (cp, no curl).
HOME_T=$(mktemp -d); CWD_T=$(mktemp -d)
# opencode install → version detectable → uninstall removes it, leaves config.
HOME="$HOME_T" REMBRIC_SRC="$REPO" REMBRIC_NONINTERACTIVE=1 sh "$REPO/install.sh" --agent=opencode --action=install
test -f "$HOME_T/.config/opencode/plugins/rembric.ts" || echo "FAIL: opencode not installed"
HOME="$HOME_T" REMBRIC_SRC="$REPO" REMBRIC_NONINTERACTIVE=1 sh "$REPO/install.sh" --agent=opencode --action=uninstall
test ! -f "$HOME_T/.config/opencode/plugins/rembric.ts" || echo "FAIL: opencode not removed"
# Pi — registry-CLI backend, no repo-side script. Run this where `pi` is NOT on
# PATH: the installer must PRINT the command and execute nothing. The printed
# spec must carry no version even under --ref, because a pinned spec is skipped
# by the client's own `pi update --extensions` / `--all`.
OUT=$(HOME="$HOME_T" REMBRIC_SRC="$REPO" REMBRIC_NONINTERACTIVE=1 sh "$REPO/install.sh" --agent=pi --action=install --ref=v0.0.0 2>&1)
printf '%s\n' "$OUT" | grep -q 'pi install npm:@rembric/pi' || echo "FAIL: pi install command not printed"
! printf '%s\n' "$OUT" | grep -q '@rembric/pi@' || echo "FAIL: version-pinned spec printed"
printf '%s\n' "$OUT" | grep -q 'REMBRIC_SERVER_URL' || echo "FAIL: pi post-install env step missing"
# The status row must never claim a version it cannot read, and update-all must
# skip an unknown row with `unknown` as the reason and still exit 0.
HOME="$HOME_T" REMBRIC_SRC="$REPO" sh "$REPO/install.sh" --status --json | grep -q '"pi"' || echo "FAIL: pi absent from --status --json"
HOME="$HOME_T" REMBRIC_SRC="$REPO" REMBRIC_NONINTERACTIVE=1 sh "$REPO/install.sh" --action=update >/dev/null || echo "FAIL: update-all did not exit 0"
# server prepare: token generated 64-hex, NO docker started (no --up).
( cd "$CWD_T" && REMBRIC_SRC="$REPO" REMBRIC_NONINTERACTIVE=1 sh "$REPO/install.sh" --server --action=install )
grep -qE '^REMBRIC_ADMIN_TOKEN=[0-9a-f]{64}$' "$CWD_T/.env" || echo "FAIL: token not generated"
rm -rf "$HOME_T" "$CWD_T"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 128 lines · 180 tokens per session scan E 2436ffb35ee8
rembric-tui-installer-e2e is a skill published in the GitHub repository susomejias/rembric (12 stars, last pushed 9d ago), licensed MIT. It adds 180 tokens to every session and 2,991 once invoked, about $0.0009 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
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
uat-testing
Run end-to-end User Acceptance Tests for Agent Brain features. Builds wheels, installs packages, starts a test server, runs tests, and reports results — all without permission prompts.
dogfood
This skill guides you through systematic exploratory QA testing of web applications using the browser toolset. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.
gstack-qa
QA lead with real browser testing. Tests your app, finds bugs, fixes them with atomic commits, generates regression tests. Use when the user says "QA", "test this", "find bugs", "exploratory test", "QA this", or "test the app".
bugbug-automation
Automate Bugbug tasks via Rube MCP (Composio). Always search tools first for current schemas.
browser-automation
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping…