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 skills add receptron/mulmoterminal --skill acceptance-supabasegit clone --depth 1 https://github.com/receptron/mulmoterminalWrote 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/receptron/mulmoterminal/acceptance-supabase)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/acceptance-supabase"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/acceptance-supabase/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/receptron/mulmoterminal/acceptance-supabase"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/acceptance-supabase.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 | $0.00041 | $0.00484 |
| Opus 5.5 | $0.00016 | $0.00194 |
| Sonnet 5.5 | $0.00008 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
blueprint-from-collection-acceptance 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 24d 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
Must-haves, proven on Supabase
The spec numbers the must-haves. For EACH one, in test/acceptance.test.ts, name the test after it
(must-have 1: …):
- Walk the real flow against the local stack through
test/local-stack.ts, as the kind of user the spec names (a fresh signed-in user, an owner, a role): create what it needs, do the action, and read back what that user would see. - Then the refusal: the same action by someone who must not be able to do it (another signed-in user, a signed-out
visitor) is refused by the database — a
42501, or a read that comes back empty. - If a must-have does not work yet, make it work — this step is where gaps between the spec and the app close.
When that means building one of the source's actions and
.blueprint/actions.jsondecides itfeature, build it as its entry says; the actions step then finds it done. If the entry decidesmanualordrop, the spec contradicts itself: ask through the blueprint question tool which one holds, and stop. - If a must-have is purely visual, test the screen instead and say so in a comment on the test.
Do not add features that are not must-haves.
Done when the check passes: test/acceptance.test.ts exists, and against a fresh local database yarn build and
yarn test succeed.
Always
- Read
.blueprint/spec.mdfirst. It is the agreed specification; do not widen it. - When you need a decision, ask it through the blueprint question tool and stop. Do not guess.
- Do not run
git init: a new repository loses the folder's trust and the next unattended step stops at Claude Code's trust prompt. The user adds git themselves after the build if they want it. - Say you are done by stopping; the executor runs the check. Do not claim success yourself.
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.
- 24d ago Changed · +3 lines · +5 tokens per session 68a909753a8b
- 25d ago First seen · 31 lines · 36 tokens per session scan A 76b5ddb0fc27
blueprint-from-collection-acceptance is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 484 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
moai-ref-testing-pyramid
Test pyramid strategy, coverage targets, test patterns, and quality metrics reference. Agent-extending skill that amplifies manager-develop test-creation and quality-validation work with production-grade testing patterns. NOT for: production code implementation, architecture design, DevOps, security audits.
moai-e2e
Create and run E2E tests across web, mobile, and desktop with auto-detection and CLI-first toolchains.
browser-qa
A live browser quality-checking workflow that replays user journeys with Playwright-compatible scripts, screenshots, and reports. It stores test cases and run evidence under `.agents/qa/`.
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
loom-e2e-testing
End-to-end testing for web applications with Playwright, Cypress, Selenium, and Puppeteer.