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 terrylica/cc-skills --skill draft-messagegit clone --depth 1 https://github.com/terrylica/cc-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/terrylica/cc-skills/draft-message)<a href="https://agentmods.dev/skills/terrylica/cc-skills/draft-message"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/draft-message/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/terrylica/cc-skills/draft-message"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/draft-message.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 127 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00038 | $0.01828 |
| Opus 5.5 | $0.00015 | $0.00731 |
| Sonnet 5.5 | $0.00008 | $0.00366 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
draft-message 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 1mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft a Telegram Message (via Saved Messages)
Send a message to the user's Saved Messages so the user can review it, optionally edit it, then copy-paste it into the target chat's compose area before sending. Saved Messages is every Telegram account's built-in private chat with itself — it syncs across all clients automatically.
Why Saved Messages, not MTProto cloud drafts? The official Telegram clients have a known unfixed race condition (tdesktop#29111, closed "not planned") where the local empty-draft state silently overwrites cloud drafts pushed via
SaveDraftRequestfrom another authorization. We observed this in practice: the server confirmed the draft, but the user's compose area stayed empty. Saved Messages bypasses this entirely — full HTML formatting is preserved, and Telegram's native copy-paste between compose areas preserves rich text across iOS, Android, Desktop, and Web.
Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
When To Use Draft vs. Send
| Situation | Use |
|---|---|
| Long or multi-paragraph message an agent composed autonomously | Draft — let the human eyeball it before it lands |
| Message carries sensitive wording (hiring, firing, contract terms) | Draft — one typo or wrong name is expensive |
| Reply where tone matters (addressing a peer or an external party) | Draft — AI-generated tone can be subtly off |
| Short confirmations, status updates, routine responses | Send — friction of drafting exceeds value |
| Automated notifications, alerts, scheduled pings | Send — no human-in-the-loop needed |
| Time-critical message where draft→review→send round-trip is too slow | Send — accept the risk |
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.
- 1mo ago Changed · +5 tokens per session 59d6ee6ce9ae
- 1mo ago First seen · 128 lines · 33 tokens per session scan A cb339664f883
draft-message is a skill published in the GitHub repository terrylica/cc-skills (0 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,828 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
low-code-platforms
Low-code and internal tool platforms including Retool, Supabase, Appsmith, Tooljet, n8n, and Zapier. Use when building admin panels, internal tools, workflow automations, or integrating low-code platforms with custom code.
host-ssh
Run PowerShell on Windows hosts or a POSIX shell on macOS/Linux hosts over SSH, via the machine registry in the guide Environment (GASSHMACHINES). Use when the user needs host OS tasks — drives, dotnet, Playwright, processes, SSH into their laptop or desktop — not file I/O on paths already visible in the workspace…
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.
agentic-orchestration
Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems. Use when designing how multiple agents coordinate — splitting up tasks, defining handoffs, or choosing an orchestration topology.
social-media-strategy
Platform-specific tactics, content optimization, audience growth, and analytics-driven social media strategy. Use when planning a social strategy, optimizing posts for a specific platform, or growing and measuring an audience.
book-publishing
Multi-book content, voice, and production workflows for nonfiction authoring. Use when planning a book, maintaining consistent voice across chapters, structuring a manuscript, or running an end-to-end publishing pipeline.