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 jeremylongworth-source/AgentSkills --skill reply-draftinggit clone --depth 1 https://github.com/jeremylongworth-source/AgentSkillsWrote 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/jeremylongworth-source/agentskills/reply-drafting)<a href="https://agentmods.dev/skills/jeremylongworth-source/agentskills/reply-drafting"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/reply-drafting/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/jeremylongworth-source/agentskills/reply-drafting"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/reply-drafting.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 | $0.00054 | $0.00403 |
| Opus 5.5 | $0.00022 | $0.00161 |
| Sonnet 5.5 | $0.00011 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
reply-drafting 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.
What it actually says
Reply Drafting
Core Workflow
- Read the customer issue, triage notes, support policy, product glossary, and any approved troubleshooting facts.
- Decide the reply goal: acknowledge, clarify, troubleshoot, resolve, escalate, set expectations, or summarize next steps.
- Draft in customer-facing language that is specific, calm, accurate, and easy to act on.
- Separate the customer reply from internal notes, assumptions, missing facts, and approval needs.
- Ask only necessary follow-up questions and explain why they matter.
- State what is known, what is being checked, and what the customer can do now.
Safety Rules
- Never send the reply automatically.
- Do not invent product behavior, policies, refunds, credits, timelines, SLAs, legal positions, security status, or incident conclusions.
- Do not include internal-only notes, private data, hidden assumptions, or speculative root cause in the customer-facing draft.
- Do not ask customers to send passwords, secrets, tokens, full payment data, or unredacted sensitive logs. Ask for redacted evidence or an approved secure channel instead.
- Require approval before commitments involving money, access, data, legal, security, incidents, or roadmap promises.
Deliverable Shape
For support replies, provide:
- Customer-facing draft
- Internal notes
- Assumptions and missing facts
- Policy or product facts used
- Approval required before sending
- Optional shorter variant when useful
References
- Read
references/reply-drafting-checklist.mdwhen drafting or reviewing a customer support reply.
What ships with it
2 files 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.
- 1mo ago First seen · 50 lines · 54 tokens per session scan A f0a0b1c52755
reply-drafting is a skill published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 17d ago), licensed MIT. It adds 54 tokens to every session and 403 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 2026-09-03.
Other skills, from other repositories
reuse-before-you-write
Use before writing any new function, helper, component or module - find what the repository, the standard library and the installed dependencies already provide, and use an established library instead of hand-rolled code for a non-trivial problem.
local-project-context
The local task workspace, the build/test commands the hand-off gate runs, and the file and exploration tools. Use when starting work in a task workspace or before running any build, test or verification command.
mcp-media-inbox-triage
Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.
ap-terminal
Open a real PTY terminal session through agentproto to drive interactive TUIs (vim, htop, an interactive CLI wizard, a nested claude TUI) with live keystrokes and byte-buffered output. Trigger phrases include "open a terminal", "start a PTY session", "type into the interactive prompt", "attach a terminal panel", "send…
pb-new-agent-session
Spawn one worker agent on the agentproto daemon, drive it with a brief and follow-ups to a verified result, then tear it down cleanly. Trigger when delegating a single task - 'spawn an agent', 'delegate this to a worker', 'run an agent to completion', 'drive an agent session'.
operator-profile
Create a compact operator preference profile that tunes safe workflow defaults without overriding task contracts, repository instructions, safety boundaries, or required verification.