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/validate-profile)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/validate-profile"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/validate-profile/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/validate-profile"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/validate-profile.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 | $0.00478 |
| Opus 5.5 | $0.00006 | $0.00191 |
| Sonnet 5.5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
validate-profile 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate the user's career profile and turn the findings into an action plan.
Arguments
$ARGUMENTS
Optional path to the profile file; default is career-profile.json in the project root.
Protocol
1. Run the validator
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/validate-profile.py" career-profile.json
(substitute the path from the arguments if one was given). The script is advisory — it always exits 0 and reports findings as a completeness scorecard plus WARN lines. It checks the rules from ${CLAUDE_PLUGIN_ROOT}/skills/resume-updater/references/career-profile-schema.md:
- Required fields (
personal.name,personal.email, at least one experience entry) - Dates in
YYYY-MMformat (education graduation may beYYYY) - Experience in reverse-chronological order
- Maximum 5 target roles
- Every achievement has a non-empty
metric(listed per role when missing)
2. Interpret the results
Don't just paste the output. Summarize:
- The completeness score and what it means
- Blocking issues (missing required fields, malformed dates) — these break resume generation and job matching; fix them first
- Quality issues (achievements without metrics) — these are the difference between a responsibilities list and a resume; for each flagged achievement, show the current statement and ask the user the quantification question from the resume-updater skill ("Can you put a number on that? Percentage? Revenue? Time saved? Scale?")
3. Offer fixes
- For mechanical issues (date formats, ordering, trimming target roles), offer to fix
career-profile.jsondirectly with Edit — show the change before applying. - For missing metrics or empty sections, offer to run the resume-updater skill's interview flow to fill them properly rather than inventing numbers. Never fabricate metrics.
- After any edits, re-run the validator to confirm the score improved. (Edits to
career-profile.jsonalso trigger the plugin's validation hook automatically, so warnings will resurface on save if anything regressed.)
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 · 42 lines · 15 tokens per session scan A 52ea6aaf83e1
validate-profile is a command published in the GitHub repository Aznatkoiny/zAI-Skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 478 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
budget
Manage the token budget for Claude Code sessions. Model-aware — picks the right effective context window and prices per model. The session's REAL model is read from the transcript by the budget hook; config.model is only the fallback. Everything from Sonnet 4.6 up is 1M; Haiku 4.5 is 200K.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
conjure-agent
Creates or updates a Claude Code agent definition (/.claude/agents/ .md or project-local).
conjure
Use when you want to build a new Claude Code skill, agent, hook, or MCP server but aren't sure which — or when you want to describe what you want in plain language. Auto-detects the right artifact type, asks targeted questions, explains the reasoning, then builds it.
conjure-mcp
Create a Claude Code MCP (Model Context Protocol) server. Provide a description of what external system or data source you want Claude to connect to.
conjure-help
Show help for the conjure toolkit — all commands, argument syntax, update modes, and decision guide. Use when you want to know which conjure command to use or how any conjure command works.