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 brsbl/moss-skills --skill moss-writing-guidelinesgit 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-writing-guidelines)<a href="https://agentmods.dev/skills/brsbl/moss-skills/moss-writing-guidelines"><img src="https://agentmods.dev/badge/skills/brsbl/moss-skills/moss-writing-guidelines/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/brsbl/moss-skills/moss-writing-guidelines"><img src="https://agentmods.dev/badge/skills/brsbl/moss-skills/moss-writing-guidelines.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 | $0.00047 | $0.03164 |
| Opus 5 | $0.00023 | $0.01582 |
| Sonnet 5 | $0.00009 | $0.00633 |
| Haiku 4.5 | $0.00005 | $0.00316 |
Grade A, and why
moss-writing-guidelines 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 11d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moss Writing Guidelines
Write every Moss note for a reader who skims first and reads second. This skill owns note structure and composition; moss-notes owns file layout, node selection, and persisted syntax.
Summary First
Frontmatter and the single H1 title come first when present. The first body paragraph after the H1 should state the answer, decision, status, or takeaway without requiring background from later sections.
- Open with the answer, decision, or takeaway — not background or process.
- State conclusions before evidence; put caveats and supporting detail after.
Progressive Disclosure
- Order sections most- to least-important. Front-load what most readers need.
- Use H2 for major sections, H3/H4 for subsections. Never add a second H1.
- Keep paragraphs short (2-4 sentences). Layer content from overview to detail to appendix — scannable does not mean shorter, so keep the useful detail.
- Push deep detail, derivations, or side caveats into later sections, callouts, or comments.
- Keep normal document conventions. Scannability comes from structure, headings, section openings, and node choice — not from artificial framing like "60-second read."
Choose And Compose Nodes
Before choosing a node, classify each content unit from its meaning and structure. This is a reasoning step, not keyword matching: infer what the reader must understand or do even when the author has not named the content type.
- Reader job: Is it explaining one idea, enumerating steps, comparing alternatives, showing a sequence or state, revealing a trend, demonstrating behavior, warning about a risk, or collecting a decision?
- Information shape: Is it connective prose, grouped points, repeated attributes, peer views, a flow, spatial relationships, quantitative change, or a visual artifact?
- Audience and altitude: Who must understand or act on it, and what is the highest level of detail that preserves their decision?
- Reading behavior: Must readers compare everything at once, inspect one slice at a time, interact with it, or respond to it?
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.
- 11d ago First seen · 140 lines · 47 tokens per session scan A eabb0659e594
moss-writing-guidelines is a skill published in the GitHub repository brsbl/moss-skills (11 stars, last pushed 16d ago), licensed MIT. It adds 47 tokens to every session and 3,164 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.