Borrowing it
Nothing to install: this file belongs to suraj-davariya/ai-job-search. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suraj-davariya/ai-job-search/main/.claude/commands/expand.mdgit clone --depth 1 https://github.com/suraj-davariya/ai-job-searchWrote 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/suraj-davariya/ai-job-search/expand)<a href="https://agentmods.dev/commands/suraj-davariya/ai-job-search/expand"><img src="https://agentmods.dev/badge/commands/suraj-davariya/ai-job-search/expand/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/suraj-davariya/ai-job-search/expand"><img src="https://agentmods.dev/badge/commands/suraj-davariya/ai-job-search/expand.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 | $0.00026 | $0.01936 |
| Opus 5.5 | $0.00010 | $0.00774 |
| Sonnet 5.5 | $0.00005 | $0.00387 |
| Haiku 4.5 | $0.00003 | $0.00194 |
Grade A, and why
expand 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 2mo 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/expand — Competency Expansion
Spec:
docs/requirements/functional-requirements-onboarding.md(REQ-0050–0055) Architecture: ARCH-0010 (Profile Manager → Competency Expander) Merge rules:docs/requirements/business-rules-and-validation.md(§7.1 additive, §7.3 idempotency)
You are running the CareerForge competency-expansion workflow. Your job is to discover skills, domains, methods, and behavioral signals the candidate genuinely has but hasn't captured yet — from their documents, code, and the web — and add them to the profile. This is a prompt-as-code command (ARCH-0001): the profile lives in Markdown (file-as-DB, ARCH-0004); you read those files, build a competency map, and append to them.
/expand is the Profile Manager's Competency Expander. It shares /setup's profile files
but, unlike /setup, it only ever adds — it is not an editor.
Hard Invariants (apply to every step, every write)
- Additive-only (REQ-0054). Never modify or remove existing content.
/expandonly appends. If something is already in the profile in any form, it is not proposed again. - Read-before-write. Read the target profile files first — their current content is the idempotency baseline.
- Idempotency via source annotations (REQ-0054, business-rules §7.3). Every addition
carries a source annotation, e.g.
*(Coursera — Deep Learning Specialisation)*. The annotation is the idempotency key: a competency already present with its annotation is never re-added on a future run. - No fabrication (ARCH-0007). Every competency traces to a real source or is clearly labeled an inference. Never invent a skill, course, certification, or repository. Flag anything you cannot read rather than guessing its content.
- No writes without confirmation (REQ-0053). Present the full competency map and get explicit approval before writing any file.
- Human-in-the-loop (ARCH-0006). You draft and execute; the user reviews and approves.
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.
- 2mo ago First seen · 177 lines · 26 tokens per session scan A 62e88303a00a
expand is a command published in the GitHub repository suraj-davariya/ai-job-search (24 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 1,936 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 2026-08-30.
expand compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| expandsuraj-davariya/ai-job-search | Command | 24 | 4mo ago | MIT | A | 26 | Claude Code |
| cost-optimizewshobson/agents | Command | 42k | yesterday | MIT | A | 26 | Claude Code |
| refactor-cleanwshobson/agents | Command | 42k | yesterday | MIT | A | 26 | Claude Code |
| deps-auditwshobson/agents | Command | 42k | yesterday | MIT | A | 23 | Claude Code |
| export-closedloop-learningsclosedloop-ai/claude-plugins | Command | 123 | today | Apache-2.0 | A | 13 | Claude Code |
| research-verifydrobins25/craft | Command | 73 | yesterday | MIT | A | 28 | Claude Code |
| spreadsheet-auditintellegix/intellegix-code-agent-toolkit | Command | 57 | 4d ago | MIT | A | 0 | Claude Code |