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 skills add AGoldian/claudenv --skill vibe-decisionsgit clone --depth 1 https://github.com/AGoldian/claudenvWrote 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/agoldian/claudenv/vibe-decisions)<a href="https://agentmods.dev/skills/agoldian/claudenv/vibe-decisions"><img src="https://agentmods.dev/badge/skills/agoldian/claudenv/vibe-decisions.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 5.1 | $0.00131 | $0.01372 |
| Opus 5 | $0.00066 | $0.00686 |
| Sonnet 5 | $0.00026 | $0.00274 |
| Haiku 4.5 | $0.00013 | $0.00137 |
Grade A, and why
vibe-decisions 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 8d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe decisions
Mode detection (FIRST step every time)
Check the system prompt for the marker Vibe-decisions mode (loop).
- Marker present → AUTO-LOG mode. Pick the approach, write the decision file, continue. NEVER pause. NEVER ask "делать так?". This is
claudenv loopand pause violates autonomy=law. - Marker absent → INTERACTIVE mode. Output brief overview, wait for user confirmation or
/deeper.
Both modes share the same trigger criteria, file format, and slash-command behavior. Only output shape and pause behavior differ.
Trigger criteria
Trigger if the decision involves:
- choosing a library or framework from 2+ viable options
- choosing an algorithm or data structure with meaningful trade-offs
- architecture pattern (sync/async, push/pull, where state lives, monolith/services)
- correctness vs performance vs simplicity trade-off
- anything where reasonable engineers would disagree
DO NOT trigger for:
- syntax-level choices in a single language (for vs map, ternary vs if)
- obvious choices (JSON for a config file, regex for simple pattern)
- pure refactoring within established patterns
- when the user typed
/just-codein the previous turn
Step 1 — Check memory before deciding
Before writing brief or auto-log, read related precedents:
view/memories/decisions/— list files; if any topic looks related, read it- Mention the precedent briefly: "Раньше для X выбирали Y (см. )"
Step 2A — AUTO-LOG mode output (inside claudenv loop)
Output exactly this shape in the user's language, then continue with code in the same turn:
**Выбрано:** <approach>
**Почему:** <one sentence>
**Альтернативы:** <A> — <terse trade-off>; <B> — <terse trade-off>
**Лог:** /memories/decisions/<YYYY-MM-DD>-<topic-slug>.md (scope: <global|project>)
Immediately after the block, use the Write tool to create the decision file (see Step 4 for format). Then proceed with the actual code. Do NOT pause.
Step 2B — INTERACTIVE mode output (no loop)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 128 lines · 131 tokens per session scan A c21c5049d778
vibe-decisions is a skill published in the GitHub repository AGoldian/claudenv (10 stars, last pushed 3mo ago), licensed MIT. It adds 131 tokens to every session and 1,372 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
submit-a-plugin
Prepare and submit a BB plugin to the Community marketplace when publication or a marketplace PR is requested.
memory
Retrieve relevant durable BB memories or save verified knowledge useful to future threads.
workflows
Author or run durable BB workflows when the user requests workflow execution or multi-agent orchestration.
secrets
Request user-supplied credentials securely into a dotenv file without exposing their values to the agent.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".