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 baselinegit 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/baseline)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/baseline"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/baseline/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/baseline"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/baseline.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 | $0.00624 |
| Opus 5.5 | $0.00016 | $0.00250 |
| Sonnet 5.5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
blueprint-repo-baseline 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 19d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Green before anything moves
Every later change claims "this behaves the same". That claim is measured against these gates, so they must be the repository's own, and they must be green on the untouched code. A gate that is already red cannot tell a regression from the state it was in.
- Package manager from the lockfile:
yarn.lock→ yarn,pnpm-lock.yaml→ pnpm,package-lock.json→ npm,bun.lockb/bun.lock→ bun. The install command must not rewrite the lockfile:yarn install --frozen-lockfile,pnpm install --frozen-lockfile,npm ci,bun install --frozen-lockfile. - Gates from
package.jsonscripts, in this order when present: a format CHECK (format:check, never a script that rewrites files),lint,typecheck,build,test. Read what each script runs.- Leave out a script that needs a service, a browser download or network the machine may not have
(
test:e2eand the like), and write why in the record. - Read the CI workflows too: CI is the ground truth these approximate. A gate CI runs and
package.jsonlacks is worth noting.
- Leave out a script that needs a service, a browser download or network the machine may not have
(
- Write
.blueprint/gates.json:{ "packageManager": "yarn", "install": "yarn install --frozen-lockfile", "gates": [{ "name": "lint", "command": "yarn lint" }, { "name": "test", "command": "yarn test" }], "skipped": [{ "name": "test:e2e", "why": "needs a browser download" }] }nameis the script name exactly aspackage.jsonhas it. - Run the install, then every gate, and read each exit code — never the last line of output.
- If any gate is red on the untouched code, ask: it is the person's decision whether to fix it first (as its own change) or leave that gate out with a reason. Do not change the repository in this step.
Done when the check passes: every recorded gate exits 0 on the untouched default branch.
Always
- Read
.blueprint/spec.mdif it exists. It is the agreed plan; do not widen it. - When you need a decision, ask it through the blueprint question tool and stop. Do not guess.
- Change nothing in the repository in this step.
- 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.
- 19d ago First seen · 43 lines · 41 tokens per session scan A 894960607f8c
blueprint-repo-baseline is a skill published in the GitHub repository receptron/mulmoterminal (239 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 624 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 2026-09-28.
Other skills, from other repositories
verify
Pre-commit verification entry point. Claude Code 2.1.286+ instructs the model to run a skill named verify right before committing (docs-only and tests-only commits exempt); this thin wrapper delegates that call to the MoAI quality gate instead of hand-rolling substitute checks.
using-orc
If you were dispatched as a subagent to execute a specific task, skip this skill.
clean-merge-lands-line-guard-on-a-value-neither-branch-predicted
Two branches each contain a guard, test or document that pins a line NUMBER in a third file, each side correctly re-aims that number for its own tree, and git merges both edits with NO conflict — leaving a merged tree whose real line can be neither number. Use when: (1) two parallel PRs both insert or delete lines in…
isolate-subagent-verification-from-live-worktree
A verification / gate-running subagent you dispatched into YOUR OWN worktree silently measures the branch PLUS your uncommitted edits, and reports the mixture as the branch's result. Nothing is clobbered and nothing errors — the suite really ran, the counts are real, they are just counts of a tree nobody will ever…
prove-test-failures-pre-existing-via-clean-worktree
After making a change you run the test suite and it shows failures — especially in files/areas your diff never touched, or a count that "feels unrelated." Before you either panic-debug them OR wave them off as "probably pre-existing," PROVE it: run the exact failing tests against a clean checkout of origin/main (a…
worktree-historical-test-replay-missing-dirs
Fix pytest exit 4 ("file or directory not found") when running a test command in a git worktree checked out at an OLD commit. Use when: (1) you're doing historical replay (incident replay, mutation testing, git bisect with tests) and the suite errors out in 1-2 seconds with no test execution, (2) the test command…