Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Aznatkoiny/zAI-Skills/plugin install career-coachWrote 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/commands/aznatkoiny/zai-skills/follow-ups)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/follow-ups"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/follow-ups/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/commands/aznatkoiny/zai-skills/follow-ups"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/follow-ups.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 | $0.00015 | $0.00611 |
| Opus 5 | $0.00008 | $0.00305 |
| Sonnet 5 | $0.00003 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
follow-ups 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the user's application tracker for anything that needs a nudge, and draft the follow-up emails.
Arguments
$ARGUMENTS
This command takes no required arguments — it reads applications.json from the project root. If arguments name a specific company, limit the review to that company's entries.
If applications.json doesn't exist or has no applications, say so and suggest /job-hunt to start populating it.
Protocol
1. Find entries needing attention
Read applications.json and today's date. Flag entries where:
- Stale:
last_updated(ordate_appliedwhenlast_updatedis empty) is more than 14 days ago AND the status is still active (applied,phone_screen,technical,onsite— notsaved,offer,rejected, orwithdrawn) - Due:
next_action_dateis today or in the past, whatever the status
For saved entries older than 14 days, don't draft a follow-up — list them separately as "decide: apply or drop".
2. Report
Show a table:
| Company | Role | Status | Days since update | Next action | Why flagged |
|---|
3. Draft follow-up emails
For each flagged active entry, draft a short follow-up email. Match the tone rules of the user's industry style — read preferences.industry_style from career-profile.json and the corresponding file at ${CLAUDE_PLUGIN_ROOT}/skills/resume-updater/references/industry-styles/<industry_style>.md, applying the same tone and no-generic-phrases rules the /cover-letter command uses.
Email rules:
- 60-120 words; subject line included
- Reference the specific stage ("since our phone screen on…", "since I applied on…") using dates and contacts from the tracker entry
- Add one line of genuine value where the profile supports it (a relevant recent accomplishment, a link to work) — never invented
- Warm, direct close with a clear ask (status check or next step); zero desperation, no guilt-tripping
- Address a named contact from
contactswhen one exists, otherwise the recruiting team
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.
- 9d ago First seen · 49 lines · 15 tokens per session scan A 4b3d518fd688
follow-ups is a command published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 611 once invoked, about $0.0001 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 commands, from other repositories
strip
This is the task-based stripper, not the always-on prior: a deliberate cleanup pass you asked for. Apply the fp-minify doctrine to the target and remove or compress comments that don't earn their place.
conjure-config
Set, view, or remove conjure preferences. Asks questions to understand what you want, then writes plain-language instructions that conjure commands follow automatically.
setup
A command that creates a Korean-language CLAUDE.md project guide from a template. CLAUDE.md is a file containing instructions and project context for the Claude coding assistant.
dock-chat
Dock the full conversation to Telegram — drive Claude from your phone.
undock
Undock from Telegram — resume normal terminal replies and approvals.
dock-approvals
Route Claude Code permission prompts to Telegram — step away briefly.