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 ychampion/cskill-agents --skill preview-first-large-output-messagesgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/preview-first-large-output-messages)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/preview-first-large-output-messages"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/preview-first-large-output-messages/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/ychampion/cskill-agents/preview-first-large-output-messages"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/preview-first-large-output-messages.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 | $0.00033 | $0.00414 |
| Opus 5 | $0.00016 | $0.00207 |
| Sonnet 5 | $0.00007 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
preview-first-large-output-messages 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 7d 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.
What it actually says
SKILL: Preview-First Large Output Messages
Domain: messaging
Trigger: Apply whenever a persisted tool result response must include a preview so the model sees the start of the output along with the saved artifact reference.
Source Pattern: Distilled from reviewed large-result persistence and preview UX implementations.
Core Method
When tool output is too large to show inline, persist the full artifact first and then render a response that leads with the saved-file reference plus a short preview from the beginning of the content. Build the preview from the stored artifact rather than regenerating it from a second formatting path, so what the user sees matches what was actually saved. Include enough metadata to show that the preview is partial and that the full artifact remains available for later reading.
Key Rules
- Always begin the visible message with the persisted-file reference and the preview block so readers know the full output was preserved.
- Generate the preview from the saved content so the preview equals the displayed portion; don’t replay the original stream twice.
- Include an explicit partial-output marker when the original content exceeded the preview length so downstream renderers know the preview is incomplete.
- Persisted metadata should note whether the content is JSON so future reads interpret the file correctly.
Example Application
When a tool returns a 200 KB JSON dump, store it as tool-results/<id>.json, then emit a message that points to that file and shows the first couple kilobytes as a preview so the user immediately understands what was returned.
Anti-Patterns (What NOT to do)
- Don’t reinject the entire persisted file into the preview; keep the preview length bound to the configured slice.
- Don’t omit the persisted-file reference; without it, the preview becomes a dead end instead of a usable large-output contract.
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.
- 7d ago First seen · 29 lines · 33 tokens per session scan A 3d2c8df4ad42
preview-first-large-output-messages is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 414 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.
dream
Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.