Borrowing it
Nothing to install: this file belongs to mtarcure/claude-vibe-squad. 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/mtarcure/claude-vibe-squad/main/.claude/skills/mode-selection/SKILL.mdgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/mode-selection)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/mode-selection"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/mode-selection.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00919 |
| Opus 5 | $0.00020 | $0.00460 |
| Sonnet 5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
mode-selection 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mode Selection
House procedure for choosing a dispatch mode before authoring the packet. The mode is a separate operator decision from the work itself, and the wrong mode silently changes the wall, the verification contract, and the gates a lane runs under. Verify every claim here against the current scripts — do not trust this doc over the code.
Name the mode and get approval — it is its own consent
chrono/CLAUDE.mdDispatch step 1 requires opening the chosen file undershared/modes/, stating which mode the work will run under, and waiting for the operator to agree. Hard Rule 1 forbids a mode starting without explicit consent.- Approving the work is not approving the mode. Measured 2026-08-21: an operator approved a
bounty campaign and 34 of 38 lanes dispatched as
mode: project— nobody was told. Say the mode word out loud; never infer it from "yes, go".
Both dispatch paths preserve an explicit choice
- Generated packets use
scripts/send-task.sh ... --mode project|bounty. The wrapper rejects an omitted or invalid value, writes the exact choice into frontmatter, and never supplies a default. - Prepared packets carry
mode: project|bountyin frontmatter and dispatch withbin/send-task.sh <packet-file>, which carries the packet's ownmodeinto the compiled contract (MODE_VALUE->"mode"). - The wrapper survives because it still assembles standard frontmatter, resolves lanes and review metadata, and routes through the hardened dispatcher. Retire it only if those conveniences move elsewhere; do not retain or reintroduce a mode default as its reason to exist.
Verify the mode that LANDED, never the one you intended
- The dispatch context carries the landed mode as a real field. Read it from the exact attempt you
dispatched, never from a glob — attempt ids are UUIDs, so glob order is not chronological and
head -1can hand you a previous attempt's mode after a retry:python3 -c 'import json,sys; a=json.load(open(sys.argv[1]))["authority"]; \ p=a.get("mode_profile"); m=(a.get("memory_context") or {}).get("mode"); \ print(p if p==m else f"MISMATCH profile={p} memory={m}")' <context_path>mode_profileandmemory_context.modemust agree; if they disagree, stop — do not pick one. - A wrapper
--dry-runechoesPacket mode: <mode>and derives that mode's contract. It proves the generated packet's choice but not a landed attempt; a green prepared-packet dry-run likewise does not replace the exact-attempt check. - If the landed mode differs from what the operator approved, stop and say so before the lane works.
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 · 59 lines · 41 tokens per session scan A 84bc7ebff2d0
mode-selection is a skill published in the GitHub repository mtarcure/claude-vibe-squad (109 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 919 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
skill-installer
Install, update, trust, or inspect Codewhale skills from GitHub or local skill folders. Use when the user asks for available skills or wants a community skill installed.