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 jain777/jobclaw-skills --skill write-outreachgit clone --depth 1 https://github.com/jain777/jobclaw-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/jain777/jobclaw-skills/write-outreach)<a href="https://agentmods.dev/skills/jain777/jobclaw-skills/write-outreach"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/write-outreach/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/jain777/jobclaw-skills/write-outreach"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/write-outreach.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 | $0.00041 | $0.00964 |
| Opus 5 | $0.00020 | $0.00482 |
| Sonnet 5 | $0.00008 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
write-outreach 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 11d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-outreach
Compose a short outreach message that earns a reply. Hard rules: see ../_shared/RULES.md — non-negotiable. Use the Communication verbs in ../tailor-resume/reference/action-verbs.md.
Inputs
- Profile: read
profile/master-profile.md(esp.Notes / voice,target.tracks, and thecontext:block for direction only — never echo). - Recipient:
{ name, role, company }. Optional: known mutual, a recent post/work they did, prior touch. - Platform:
linkedin(≤ 120 words, no subject) oremail(≤ 180 words, with subject). - Goal:
intro(be known) ·referral(ask for an internal referral) ·info(informational chat) ·follow-up(post-application / post-interview / post-event).
If recipient / platform / goal is missing, ask once, batched.
Method
-
Region note. Read the target region pack — outreach norms differ slightly (US: direct; IN: referrals matter more, lead with mutuals/track when possible).
-
Pick the hook. One verifiable, profile-grounded fact connecting candidate → company / role / recipient. Examples that work: same OSS project, alum overlap, identifiable recent work overlap, shared track. Examples that don't: generic "I admire your mission", company-name flattery in the opener.
-
One CTA only. Schedule 15 min · share a referral · answer a specific question · introduce a third party. No multi-CTA messages — they get ignored.
-
Draft.
- LinkedIn — ≤ 120 words. No "Dear", no "Hope this finds you well." Open with the hook in ≤ 1 sentence. One CTA. Sign with first name.
- Email — ≤ 180 words. Subject = 4–8 specific words ("Quick question on Mercury API roadmap", not "Quick question"). Body = 2 short paragraphs (hook+credential → CTA). Sign with full name + 1-line current credential.
-
Self-check against the anti-patterns and rubric before output.
Output
- Console: the message (and subject if email).
- Write
outreach/<company-slug>-<role-slug>-<platform>.md(createoutreach/if needed). Include the subject as the H1 for email. - 2-line rationale: what hook you chose · what CTA you set. Helps the user judge before sending.
- Region tip when relevant (e.g., IN: "open with the mutual / IIT-batch line — converts far harder than the cold version").
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.
- 11d ago First seen · 65 lines · 41 tokens per session scan A 595dcf7f6477
write-outreach is a skill published in the GitHub repository jain777/jobclaw-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 964 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…