agentmods.dev

draft-reply

draft-reply is a skill for Claude Code from jain777/jobclaw-skills. It costs 72 tokens per session (1,500 once invoked), scanned A, original, MIT.

An email-reply drafting tool for recruiting conversations, covering scheduling, accepting or declining, asking questions, sharing information, and following up.

In plain words
What is it for?
Use it to turn a recruiter email or thread into one focused reply with suitable times, answers, questions, or next steps.
Why use it?
It removes the need to decide how to respond while preserving the thread's tone, dates, links, and the user's preferred signature. It drafts messages but does not send them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the jobclaw-skills plugin — 20 skills shipped together

not rated 5repo 3mo ago A scan 72 tokens original MIT

Good fit Use it to turn a recruiter email or thread into one focused reply with suitable times, answers, questions, or next steps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jain777/jobclaw-skills/draft-reply
View source ↗ jain777/jobclaw-skills
Install

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.

Any agent
npx skills add jain777/jobclaw-skills --skill draft-reply
Clone the repo
git clone --depth 1 https://github.com/jain777/jobclaw-skills

Made for: Claude Code.

Or install jobclaw-skills, the plugin that ships this one along with the rest of its 20 skills.

Wrote 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.

agentmods badge for draft-reply

README.md
[![agentmods](https://agentmods.dev/badge/skills/jain777/jobclaw-skills/draft-reply/github.svg)](https://agentmods.dev/skills/jain777/jobclaw-skills/draft-reply)
Your own site
<a href="https://agentmods.dev/skills/jain777/jobclaw-skills/draft-reply"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/draft-reply/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.

agentmods 80×15 button for draft-reply

Your own site · 80×15
<a href="https://agentmods.dev/skills/jain777/jobclaw-skills/draft-reply"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/draft-reply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.01500
Opus 5 $0.00036 $0.00750
Sonnet 5 $0.00014 $0.00300
Haiku 4.5 $0.00007 $0.00150

Measured 9d ago against content hash 98c1c8c1492b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

draft-reply 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 9d 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.

skills/draft-reply/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

draft-reply

One reply, one intent, no auto-send. Hard rules: ../_shared/RULES.md. Use Communication / Leadership verbs from ../tailor-resume/reference/action-verbs.md. All reply-intent labels come from ../../knowledge/status/taxonomy.md.

Inputs

  1. Thread — the inbound email plus any prior thread (paste or --in inbox/<thread-id>.json).
  2. Intent — one of reply-schedule | reply-accept | reply-decline | reply-ask | reply-info | follow-up.
    • For reply-accept, also pass accept_kind ∈ {schedule, assessment, offer} (templates diverge).
  3. Triage extraction (optional) — { dates[], links[], asks[], deadline, ... } from inbox/triage-<date>.json. If absent, the skill runs a thin in-line classify to recover the minimum (don't write a triage record back — that's triage-inbox's job).
  4. Profile — profile/master-profile.md for signature, timezone, voice, and (if intent is reply-info) the preferences.* data the recruiter is asking for.
  5. Specifics:
    • reply-schedule → 2–3 candidate windows the user offers (in the user's tz, with the recruiter's tz noted).
    • reply-accept (offer) → do not write an acceptance email here. Output a deliberately conservative acknowledgement that buys time and points the user to /coach-negotiation. Emit a warning in the rationale.
    • reply-decline → reason category (accepted-elsewhere | not-aligned | timing | other); the skill phrases gracefully.
    • reply-ask → exactly one question to ask.
    • reply-info → which preferences.* fields the recruiter asked for.
    • follow-up → days since last contact (drives tone — gentle at 7d, firm at 21d).

Method

  1. Region note. Read the target region pack — tone defaults (US: direct, IN: warmer with explicit thanks); spelling variant; date format used in the body.

  2. Mirror the inbound. Match salutation style (Hi <First> vs Dear <Last>), formality, length expectations. Don't out-formal the recruiter; don't be sloppier either.

Read the full file on GitHub · 84 lines

Changes

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.

  1. 9d ago First seen · 84 lines · 72 tokens per session scan A 98c1c8c1492b

Subscribe to this mod's changes

draft-reply is a skill published in the GitHub repository jain777/jobclaw-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 1,500 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.

Writing and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens