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 agentmods add commands/fighter90/career-ops-ui/codebase-tourgit clone --depth 1 https://github.com/Fighter90/career-ops-uiWhat 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 | $0.00020 | $0.00261 |
| Opus 5 | $0.00010 | $0.00130 |
| Sonnet 5 | $0.00004 | $0.00052 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
codebase-tour 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 2d 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.
What it actually says
Walk through the repo in this order, ONE sentence per item:
- Stack — Node 18+, Express 4, vanilla SPA, no build step, no TS.
- Server entry —
server/index.mjs(createApp factory + ~50 routes). - Server lib — list
server/lib/*.mjswith a one-line purpose each. - Client entry —
public/index.html→public/js/app.js→public/js/router.js. - Views —
public/js/views/*.js, one per route. - Tests —
node --test tests/*.test.mjs, in-process viacreateApp(). - Parent integration —
paths.mjs::resolveProjectRoot()finds the parent career-ops; this UI reads/writes viaPATHS.*. - Streaming —
/api/stream/*endpoints emit SSE for long-running scans / PDF generation. - Hard rules — never edit outside
web-ui/, never log secrets, never relax CSP. - Where to start —
docs/architecture/OVERVIEW.md.
Output as a numbered list. Under 250 words.
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.
- 2d ago First seen · 19 lines · 20 tokens per session scan A 22e091e02ed0
codebase-tour is a command published in the GitHub repository Fighter90/career-ops-ui (58 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 261 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 2026-08-30.
Other commands, from other repositories
triage
Triage a GitHub issue and present findings on validity, code locations, and optionally create a failing test or resolution plan.
audit-config
Quick Claude Code config audit — counts per surface (user vs project) and totals.
memory
List the file-based memory store grouped by project (auto-memory) plus the CLAUDE.md files.
burn-rate
Compute the recent 7-day spend trend (burn rate) from daily sessions and per-session cost.
cost-today
Quick total cost plus a per-model one-liner from the dashboard pricing engine.
inventory
One-screen inventory of skills, agents, commands, MCP servers, and hooks counts.