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-commentsgit 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-comments)<a href="https://agentmods.dev/skills/brsbl/moss-skills/moss-comments"><img src="https://agentmods.dev/badge/skills/brsbl/moss-skills/moss-comments.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.01834 |
| Opus 5 | $0.00016 | $0.00917 |
| Sonnet 5 | $0.00006 | $0.00367 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
moss-comments 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 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.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moss Comments
Use comments for explicit questions, decisions, approvals, or review points that need attention on exact evidence. Fix ordinary wording, duplication, and scannability issues directly instead of leaving editorial comments, except when annotating your own edits to an existing large note.
A root comment has body markers plus a matching comments.json entry. Replies exist only in the sidecar and connect through parentId.
Execution Context
Use these attribution values:
| Writer | source / resolvedBy |
|---|---|
| Human using Moss UI | user |
| Moss's in-app agent | agent |
| Agent or tool editing files outside Moss | external |
Do not write user for agent-authored content. Preserve missing attribution as legacy/unknown instead of backfilling it.
Body Markers
Wrap the exact annotated range:
The %%m:c1:start%%current layout%%m:c1:end%% needs review.
- IDs may contain letters, digits,
_, and-. - Generate an ID that does not already exist in the body or sidecar; no particular prefix is required.
- Start and end markers are both required and use the same comma-separated IDs.
- Multiple roots may share a range:
%%m:a,b:start%%text%%m:a,b:end%%. - Only root IDs appear in body markers.
Wrap an entire inline pill rather than placing markers inside it. Put block markers on standalone lines around the whole image, chart, HTML block, code fence, or other block node. Never place markers inside wiki links, formulas, color pills, fenced payloads, or raw HTML comments.
Sidecar Schema
comments.json is a JSON object keyed by comment ID. Required fields use Unix timestamps in seconds.
| Field | Required | Contract |
|---|---|---|
text |
Yes | Comment or reply text. |
createdAt |
Yes | Finite Unix timestamp in seconds; do not change after creation. |
updatedAt |
Yes | Finite Unix timestamp in seconds; update when the entry changes. |
source |
New entries | user, agent, or external. |
parentId |
Replies only | Existing root or reply ID; no cycles or dangling targets. |
imageUrls |
No | Note-relative paths under assets/. |
resolvedAt |
Resolved thread | Finite Unix timestamp in seconds. |
resolvedBy |
When known | user, agent, or external. |
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 First seen · 132 lines · 32 tokens per session scan A cd5dd50eec32
moss-comments is a skill published in the GitHub repository brsbl/moss-skills (11 stars, last pushed 13d ago), licensed MIT. It adds 32 tokens to every session and 1,834 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
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…
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.
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.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).