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 skills/thoughtbot/rails-consultant/offboardnpx skills add thoughtbot/rails-consultant --skill offboardgit clone --depth 1 https://github.com/thoughtbot/rails-consultantWrote 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/thoughtbot/rails-consultant/offboard)<a href="https://agentmods.dev/skills/thoughtbot/rails-consultant/offboard"><img src="https://agentmods.dev/badge/skills/thoughtbot/rails-consultant/offboard.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00816 |
| Opus 5 | $0.00014 | $0.00408 |
| Sonnet 5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
offboard 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 4d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior
Walk through each wrap-up item below as a conversation. Go one item at a time. For each item:
- Explain what needs to happen and why.
- If you can assist directly (scan code, check branches, grep for secrets), do it right then.
- Ask whether the item applies, whether it's done, or whether they need help.
- Move on when they confirm.
Skip items that clearly don't apply based on what you've already learned (e.g., skip Figma items if there's no design work). If you're unsure, ask.
Checklist
1. Transfer codebase ownership to the client
Check who owns the repo. Ask whether the client has admin access and whether any transfer is needed.
2. Upload files to client-accessible storage
Ask whether all project files (documents, assets, exports) have been uploaded to Basecamp, Drive, or whatever file storage the client uses.
3. Figma file transfer
Ask whether this engagement involved design work. If yes:
- Have Figma files been transferred to the client's organization, or exported as
.figfiles and sent? - Does your team have a copy of the files?
- Have client members been removed as editors from your Figma team? (Viewers are fine — they don't count toward billing.)
If no design work, skip this entirely.
4. Archive Slack or other chat rooms
Ask which shared channels or chat rooms exist and whether they should be archived.
5. Clean up project management tools
Ask about Trello, Switchboard, or other project management tools. Should boards be archived or closed?
6. Transfer password manager entries
Ask whether any credentials are stored in your team's password manager that need to be transferred to the client's vault.
7. Delete sensitive user data from machines
Scan the local project directory for potential sensitive data:
- Grep for common patterns: API keys, tokens, passwords,
.envfiles, credential files, database dumps, SSH keys. - Check for
.env,.env.local,.env.production, or similar files. - Check for any database dumps or seed files with real user data.
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.
- 4d ago First seen · 99 lines · 28 tokens per session scan A 0b32103ef691
offboard is a skill published in the GitHub repository thoughtbot/rails-consultant (23 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 816 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 skills, from other repositories
recursive-decomposition
Handle tasks that exceed the context window by decomposing them: size and filter the input, chunk it, run recursive sub-agents on independent parts, verify on small windows, and synthesise programmatically, following the Recursive Language Models (RLM) research by Zhang, Kraska and Khattab (2025). Use when a task…
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
brainstorm
Guided game concept ideation — from zero idea to a structured game concept document. Uses professional studio ideation techniques, player psychology frameworks, and structured creative exploration.
balance-check
Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.
adherencia-reglas
Mide qué fracción de las reglas propias del proyecto se cumple de verdad, contándolo sobre el historial de sesiones que Claude Code ya guarda en disco. Se activa al preguntar si una norma, protocolo o convención se está aplicando, al revisar si un CLAUDE.md sirve de algo, al decidir si una regla debe pasar a ser hook…
remove-ai-slop
Review and clean AI-slop from writing: filler and marketing adverbs, empty openers, overused jargon, hedging, false agency, structural tells, future tense for current behavior, and em-dash overuse. Use when asked to remove AI-sounding phrasing, tighten prose, de-AI text, edit out "simply/just/easily", flag or strip…