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 YG3-ai/quill --skill mosaicgit clone --depth 1 https://github.com/YG3-ai/quillWrote 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/yg3-ai/quill/mosaic)<a href="https://agentmods.dev/skills/yg3-ai/quill/mosaic"><img src="https://agentmods.dev/badge/skills/yg3-ai/quill/mosaic/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/yg3-ai/quill/mosaic"><img src="https://agentmods.dev/badge/skills/yg3-ai/quill/mosaic.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 | $0.00060 | $0.01173 |
| Opus 5 | $0.00030 | $0.00587 |
| Sonnet 5 | $0.00012 | $0.00235 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
mosaic scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import json, urllib.request, sys How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The developer just typed /quill:mosaic — they want a mosaic response
to a multi-aspect task. Their task description: "$ARGUMENTS"
Mosaic mode is different from consult/perspective/assumptions. Those relay one-shot perspectives. Mosaic produces structured work: 2-4 slices written by different agents in their native voices, cross- reviewed for consistency, assembled with the seams visible on purpose.
The thesis: two heads are better than one. The mosaic IS the value — preserved texture diversity is the feature, not a bug.
When mosaic mode fits
- Multi-aspect tasks: code + docs + UX + tests, or backend + frontend + migration plan, or methodology + findings + caveats
- Work where you want both a precise voice AND a humanistic voice contributing, not one blending them
- Tasks where the seams between aspects matter (e.g. does the doc match the implementation? does the test cover the UX claim?)
When to NOT reach for mosaic mode
- Single-aspect tasks (just code, just docs, just a yes/no question) —
use the doer agent directly or
/quill:consult - Quick questions — mosaic mode takes 60-180 seconds
- Anything where uniform voice is actually what the developer wants
If you suspect the developer's task is single-aspect, tell them so and
suggest they re-issue without /quill:mosaic (or use /quill:consult
for a thinking-partner reframe).
Step 1 — Pass the task to mosaic mode
Use this command, substituting the developer's task description for
<DEVELOPER TASK>:
python3 -c "
import json, urllib.request, sys
msg = sys.argv[1]
payload = json.dumps({'task': msg}).encode()
req = urllib.request.Request('http://127.0.0.1:9000/mosaic', data=payload, headers={'Content-Type': 'application/json'})
try:
with urllib.request.urlopen(req, timeout=240) as r:
data = json.loads(r.read())
if data.get('error'):
print(f'MOSAIC ERROR: {data[\"error\"]}')
else:
print(data.get('assembled_response', '(no response)'))
print()
print('---VOICE MAP---')
for slc, voice in (data.get('voice_map') or {}).items():
print(f' {slc}: {voice}')
flags = data.get('cross_review_flags') or []
if flags:
print()
print(f'---{len(flags)} CROSS-REVIEW FLAG(S)---')
except Exception as e:
print(f'BRIDGE UNAVAILABLE: {e}')
" "<DEVELOPER TASK>"
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.
- 12d ago First seen · 115 lines · 60 tokens per session scan A 30d264abaa5b
mosaic is a skill published in the GitHub repository YG3-ai/quill (1 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,173 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
codex-delegate
Delegates implementation-heavy or repetitive coding work (batch edits, boilerplate, multi-file refactors with clear patterns, test scaffolding) from Claude to OpenAI Codex CLI. Use when token cost outweighs judgment cost. Trigger phrases include "delegate to codex", "let codex do this", "batch refactor across files"…
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
output-standards
Use this skill when defining or enforcing output formatting standards for agent responses in WrongStack. Triggers: user says "next steps format", "output standard", "response format", "final message format", "standardize next steps".