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 agentmods add skills/brsbl/moss-skills/moss-notesnpx skills add brsbl/moss-skills --skill moss-notesgit clone --depth 1 https://github.com/brsbl/moss-skillsWrote 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/brsbl/moss-skills/moss-notes)<a href="https://agentmods.dev/skills/brsbl/moss-skills/moss-notes"><img src="https://agentmods.dev/badge/skills/brsbl/moss-skills/moss-notes.svg" alt="Measured on agentmods" 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 | $0.01784 |
| Opus 5 | $0.00020 | $0.00892 |
| Sonnet 5 | $0.00008 | $0.00357 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
moss-notes 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 6d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moss Notes
This is the canonical entry point for note layout, node selection, and core persisted syntax. Focused skills own the full contracts for frontmatter, comments, links, formulas and variables, canvas, and HTML.
Quickstart
- Edit the existing Markdown content file inside the note directory.
- For a new workspace note, create
~/Moss/Notes/<Title>/<Title>.md; never create app-owned sidecars. - Put optional frontmatter first, followed by one
# H1title and then the body. - Start the body with a standalone takeaway, following
moss-writing-guidelines. - Choose nodes with the routing table below and follow the focused skill for their exact syntax.
A workspace note is a canonical note bundle under ~/Moss/Notes/. An external note is a Markdown file opened from another location and may use a Moss-provided sidecar path. Do not assume the workspace bundle layout for an external note.
File Ownership
| Path | Owner | Authoring rule |
|---|---|---|
<Note>/<Note>.md |
Note content | Create or edit directly. |
<Note>/assets/ |
Note media | Add referenced note-local files here. |
<Note>/comments.json |
Comment content | Edit only while following moss-comments. |
meta.json, .folder.json, layout.json |
Moss | Never create or edit directly. |
Folders and nested folders under ~/Moss/Notes/ are valid. Preserve existing frontmatter and sidecars unless the task explicitly changes them.
Node Selection
This table owns the default selection rule. Focused skills explain how to author the selected node but do not override creation authority.
| Need | Use | Boundary |
|---|---|---|
| Prose, grouped points, or steps | Paragraphs, bullets, numbered lists | Prefer the simplest readable structure. |
| Execution state | Markdown checklist | Use - [ ] and - [x]. |
| Repeated inline attributes | Table | Moss Markdown tables support inline content, not nested block nodes. |
| Peer views inspected one at a time | Tabs | Use two to four panels unless the user asks for more. |
| Source, literal text, logs, or readable diagrams | Fenced code block | Generic flows and wireframes default to ASCII code. |
| Existing canvas, or an explicitly requested canvas/editable spatial diagram | moss-canvas |
Do not create canvas for a generic diagram request. |
| Genuine interactive design or behavior unavailable in native nodes | moss-html |
Do not rebuild native tabs, tables, callouts, checklists, or review workflow. |
| High-signal information, warning, or priority | moss-callout |
Keep ordinary body prose outside the callout. |
| Numeric comparison or trend | moss-chart |
Prefer a short table when visual shape adds no value. |
| Exact question, decision, approval, or review point | Comment | Fix ordinary editorial issues directly, except when annotating your own edits to an existing large note per moss-comments. |
| Note navigation or external destination | Wiki or Markdown link | Follow moss-links. |
| Reused or computed inline value | Variable or formula | Follow moss-formulas-variables. |
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.
- 6d ago First seen · 171 lines · 41 tokens per session scan A 88ea5a767abb
moss-notes is a skill published in the GitHub repository brsbl/moss-skills (11 stars, last pushed 12d ago), licensed MIT. It adds 41 tokens to every session and 1,784 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.