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 mulmoterminal-dirsgit 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/mulmoterminal-dirs)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/mulmoterminal-dirs"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-dirs/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/mulmoterminal-dirs"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/mulmoterminal-dirs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 260 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 379 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00395 | $0.06614 |
| Opus 5 | $0.00198 | $0.03307 |
| Sonnet 5 | $0.00079 | $0.01323 |
| Haiku 4.5 | $0.00040 | $0.00661 |
Grade A, and why
mulmoterminal-dirs scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sG "http://localhost:${MULMOTERMINAL_PORT:-34567}/api/dir-config-detail" --data-urlencode "cwd=$path" How it starts
The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Colour and order the directories you work in
MulmoTerminal reads <project>/.mulmoterminal.json to style every terminal opened in that
directory. There is no UI that writes this file — this skill is the way it gets written.
Two files ship next to this one:
palettes.json— colour presets grouped by vibe, for a user with nothing configured yet.dir-config.schema.json— the generated JSON Schema. "Schema" below matches it.
The shape of this conversation
The unit of work is the set of directories the user actually opens, not the current one. Someone who colour-codes projects is doing it so the grid is readable at a glance, and that only works if the colours are decided against each other.
So: gather → infer → propose the whole set → apply → look → adjust.
Ask with AskUserQuestion, one decision at a time, always with concrete options. A beginner should
never have to invent a hex code.
1. Gather — the directories, and what they already say
Read ~/.mulmoterminal/config.json and take cwdPresets ([{ label, path }], most-recent first —
the same list the New-terminal launcher offers). That is the population. Worktrees are not recorded
into it, so it is the user's real projects rather than every task branch they have ever opened; an
older entry that still names one is theirs to keep or remove, not this skill's to prune.
Then, for each of those paths:
curl -sG "http://localhost:${MULMOTERMINAL_PORT:-34567}/api/dir-config-detail" --data-urlencode "cwd=$path"
Let curl encode cwd (-G + --data-urlencode) rather than interpolating the path into the
query: a raw path truncates at the first # or ? and mangles spaces.
Use this route, not your own read of the file. It returns what the app actually parsed: the values in force, the keys the file set, and how each fared — applied, dropped in validation, or not a key we read. A hand-read tells you what the file says; only this tells you what is in effect, and the difference is the entire content of "I set it and nothing happened". It also resolves the path the way the app does (a preset whose project has since been deleted answers as missing rather than silently reporting on some other directory).
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.
- 8d ago Changed · +1 lines cae568bc348c
- 12d ago First seen · 440 lines · 395 tokens per session scan A e6649e4bf508
mulmoterminal-dirs is a skill published in the GitHub repository receptron/mulmoterminal (212 stars, last pushed today), licensed MIT. It adds 395 tokens to every session and 6,614 once invoked, about $0.0020 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 2026-08-30.
Other skills, from other repositories
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
infer-completion-criteria
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly.
nl-router
Route natural language requests to appropriate skills and workflows by parsing intent and matching trigger patterns.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.
summarize-transcript
Analyze and summarize a transcript, meeting notes, or discussion thread into a clear actionable document.