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 LucasSantana-Dev/sharekit --skill research-and-decidegit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWrote 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/research-and-decide)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/research-and-decide"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/research-and-decide/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/research-and-decide"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/research-and-decide.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 | $0.00074 | $0.01095 |
| Opus 5.5 | $0.00030 | $0.00438 |
| Sonnet 5.5 | $0.00015 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
research-and-decide 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research and Decide
You make decisions all day; most never get captured. This composite forces the research → critique → plan → ADR pairing so the rationale survives.
Auto-invocation triggers
- User asks "should we use X or Y", "is X worth adopting", "what's the right pattern for"
- Comparing libraries, frameworks, services, or architecture options
- Evaluating a vendor / API / SaaS adoption
- Spec-driven design questions before implementation
Workflow
Phase 1 — Research (always)
- Open-ended exploration: invoke
brainstormingto surface options and constraints - Specific tech evaluation: invoke
adt-researchfor web + docs + repo evidence - Output: 5-10 candidates with one-line tradeoff per candidate
Phase 2 — Challenge (always — this is what makes the decision durable)
Dispatch ONE read-only critic agent (Opus, multi-perspective review; never edits repo state) on the leading 1-2 options:
- Cost over 12 months
- Migration friction
- Lock-in risk
- Failure modes specific to your stack
- What changes the answer (revisit triggers)
Apply the decision-discipline.md standard's 5-step scaffold
(CLAIM → EXTRACT → DOUBT → RECONCILE → STOP) on the leading artifact —
critic invocations should pass ARTIFACT + CONTRACT only, never the CLAIM
or your reasoning (that biases the reviewer toward agreement).
If critic flips the leading option → loop back to Phase 1 with the new dimension
to evaluate.
Phase 3 — Plan adoption (only if a decision is made)
Invoke plan to sequence:
- Pilot scope (1 module or feature)
- Success criteria for the pilot
- Rollback plan if the pilot fails
- Full-rollout sequencing
Skip Phase 3 if the decision is "no change" or "defer".
Phase 4 — Record (always, at proportional fidelity)
Apply the record gate (memory feedback_research_and_decide_always_2026-05-25):
Full ADR via adr-write ONLY when a gate trips:
- public-facing repo | undo-cost ≥ a sprint | rejection of a recurring alternative | forced post-incident record
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 · 112 lines · 74 tokens per session scan A 0712a2aea767
research-and-decide is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 1,095 once invoked, about $0.0003 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.