Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/LucasSantana-Dev/sharekitnpx agentmods add skills/lucassantana-dev/sharekit/decide-nowWrote 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/lucassantana-dev/sharekit/decide-now)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/decide-now"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/decide-now/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/skills/lucassantana-dev/sharekit/decide-now"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/decide-now.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 | $0.00101 | $0.00969 |
| Opus 5.5 | $0.00040 | $0.00388 |
| Sonnet 5.5 | $0.00020 | $0.00194 |
| Haiku 4.5 | $0.00010 | $0.00097 |
Grade A, and why
decide-now 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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
decide-now
Make the right call faster by grounding the decision in what's actually happening — not in generic best practices.
decide-now vs /decide
| decide-now | /decide | |
|---|---|---|
| When | Answer depends on current context | One-time architectural bet |
| Speed | Fast (minutes) | Thorough (research phase) |
| Output | Chat verdict | ADR file |
| Examples | "merge now or wait?", "fix or defer?", "A or B for this task?" | "which ORM?", "which deploy target?" |
Rule of thumb: if the answer would change depending on what's in memory / git / plans / PRs right now → decide-now. If future agents need to know the decision was made → /decide.
Workflow
1. Load relevant context
Don't read everything — scan for what the question actually needs. Common sources:
| Question type | What to load |
|---|---|
| Merge / PR readiness | gh pr view <N> CI status, open review threads, CodeRabbit state |
| Prioritization | Memory index, open issues, active plans, recent commits |
| Approach selection | Recent ADRs, CLAUDE.md constraints, active plans, memory |
| Bug fix vs defer | CI state, PR stack, issue severity, what's in flight |
| Dependency on external state | Handoff at ~/.claude/handoffs/<project>/latest.md |
Always check: CLAUDE.md hard rules — a rule there can override everything else. When checking reviewer-comment rules: CodeRabbit, dependabot, renovate, and other configured bots are explicitly NOT "another person" — they don't block merges per CLAUDE.md bot-exemption.
2. Synthesize
Before forming a recommendation, ask:
- Does any CLAUDE.md rule constrain the options?
- What would be consistent with the current trajectory of work?
- Does memory record a similar decision and its outcome?
- Are there blockers or dependencies that change the calculus?
- What's the cost of being wrong? (reversible → bias toward action; irreversible → bias toward caution)
3. Output — always this shape
Decision: <one-line verdict — the actual choice, not "it depends">
Why: <2-3 sentences grounded in the loaded context; cite specifics (PR #N, memory note X, ADR slug, plan phase)>
Tradeoff: <what you're giving up with this choice — one sentence>
Next step: <the smallest concrete action to execute on this decision>
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.
- 1mo ago First seen · 92 lines · 101 tokens per session scan A d67b066b4497
decide-now is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 3d ago), licensed MIT. It adds 101 tokens to every session and 969 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
loongsuite-pilot-insight
A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.