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 collindjohnson/manas --skill setup-manasgit clone --depth 1 https://github.com/collindjohnson/manasWrote 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/collindjohnson/manas/setup-manas)<a href="https://agentmods.dev/skills/collindjohnson/manas/setup-manas"><img src="https://agentmods.dev/badge/skills/collindjohnson/manas/setup-manas/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/collindjohnson/manas/setup-manas"><img src="https://agentmods.dev/badge/skills/collindjohnson/manas/setup-manas.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 | $0.00063 | $0.00757 |
| Opus 5.5 | $0.00025 | $0.00303 |
| Sonnet 5.5 | $0.00013 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
setup-manas 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Manas
Guide the user through Manas setup without choosing an archive or enabling a scheduler on their behalf.
Workflow
-
Confirm the
manascommand is available. For a verified release binary that is not yet installed, run itsinstallsubcommand. In a source checkout where it is not installed, replacemanasin every command below withbun run src/cli.ts. -
Inspect without mutation:
manas setup --detect-only --json -
Summarize detected providers, readable conversations, and warning/failure counts. Explain that the default archive is Manas-owned. If the user wants Obsidian, iCloud, or another location, collect an explicit archive path.
-
Ask the user to approve the archive location before writing configuration.
-
Generate a read-only preview using the approved location:
manas setup --preview --archive <approved-path> --jsonOmit
--archivewhen the user approves the Manas default. -
Report exact create, update, skip, warning, and failure totals. Do not continue if failures are nonzero.
-
Ask for explicit approval to perform the initial sync and enable the daily macOS scheduler. Offer configuration without scheduling when requested.
-
After approval, run one of:
manas setup --yes --archive <approved-path> --json manas setup --yes --archive <approved-path> --no-schedule --json -
Verify archive integrity and inspect scheduler status using the
configPathreturned by setup:manas verify --config <config-path> manas sync-status --config <config-path> -
Report the configured archive, detected providers, initial totals, scheduler state, last successful sync, and warnings.
-
For a broken installed scheduler, use the release binary's repair mode and require a fresh preview/approval. For an old chat-history-sync LaunchAgent, explain that it is retained by default; only run
manas setup --retire-legacy --yes --jsonafter the user explicitly approves its timestamped backup and unload.
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.
- 1mo ago First seen · 60 lines · 63 tokens per session scan A 862010791858
setup-manas is a skill published in the GitHub repository collindjohnson/manas (0 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 757 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
kb
Set up, evolve, or operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design KB conventions or a recurring KB ritual; search or query a KB or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git…
siyuan-plugin-development
Official frontend plugin development workflow. After the user explicitly opts in, clarify missing requirements, confirm a short plan, implement in a managed copy, verify, and package. Installation and activation require separate authorization.
starcat-ui-prototype
A design skill for creating macOS interface prototypes and visual designs for Starcat, a GitHub star-management and AI knowledge-organising app. It follows Apple’s Liquid Glass design language for macOS 26.
starcat-update-changelog
Update Starcat changelog documents in supports/starcat-pro/ by reading ALL git commits from the main Starcat project and generating categorized release notes in both English and Chinese. Use this skill whenever the user wants to update changelog, release notes, update records, or sync the changelog with recent…
starcat-release
A project-specific procedure for releasing the Starcat macOS app through its App Store and direct-download channels.
starcat-localization-sync
A process for managing Starcat’s app translations from draft text through review, import, and release across 18 languages. It keeps the app’s translation catalogue and the public translation repository aligned.