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 agentmods add skills/jtsternberg/claude-plugins/replyingnpx skills add jtsternberg/claude-plugins --skill replyinggit clone --depth 1 https://github.com/jtsternberg/claude-pluginsWrote 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/jtsternberg/claude-plugins/replying)<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/replying"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/replying.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.01315 |
| Opus 5 | $0.00042 | $0.00658 |
| Sonnet 5 | $0.00017 | $0.00263 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
replying 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 3d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Replying
Answering mail is the one place in this plugin where being slow is correct. Email cannot be recalled and this CLI has no send idempotency, so there is no undo and no safe retry.
Read the reference before you send
Every mechanic — verb choice, the reply-all headcount, drafts, threading, body flags,
what to do when a send fails — lives in one file, because relay-work-order and
check-mail need the same rules and a second copy would drift from this one.
Codex: substitute the installed plugin directory for the path below.
${CLAUDE_PLUGIN_ROOT}/references/replying.md
Read it before your first send in a session. What follows here is only the part you must not get wrong even if you read nothing else.
The four rules
1. Show, then send. Put the exact to/cc/bcc, the subject, and the full body in
front of the user and get explicit confirmation. One confirmation covers one send, not a
session. Sends are deliberately absent from allowed-tools so the harness prompts too —
that prompt is the feature, and broadening to Bash(agentmail *) would remove the only
harness-level guard on an irreversible action.
2. Count before reply-all. inboxes:messages reply-all takes no --to/--cc/--bcc —
the API forbids explicit recipients there — so the blast radius is whatever is already on
the thread and you cannot trim it at send time. Read the thread, tell the user the number,
then send. Cap is 50 across to+cc+bcc.
3. Draft anything the user did not dictate. A draft is a reviewable artifact instead of
a claim about what you were about to write, --client-id makes creating it idempotent, and
it is AgentMail's own human-in-the-loop recommendation. Show drafts get output, then
drafts send after approval.
4. Never retry a failed send. Timeout, 5xx, killed process, unclear error — do not re-run it. Check whether it landed:
agentmail inboxes:messages list --inbox-id <id> --limit 5 --format json > /tmp/am-check.json
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.
- 3d ago First seen · 108 lines · 83 tokens per session scan A e567a469fad2
replying is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 1,315 once invoked, about $0.0004 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
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.