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 Sprintra-io/sprintra-mcp --skill sprintra-decidegit clone --depth 1 https://github.com/Sprintra-io/sprintra-mcpWrote 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/sprintra-io/sprintra-mcp/sprintra-decide)<a href="https://agentmods.dev/skills/sprintra-io/sprintra-mcp/sprintra-decide"><img src="https://agentmods.dev/badge/skills/sprintra-io/sprintra-mcp/sprintra-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/sprintra-io/sprintra-mcp/sprintra-decide"><img src="https://agentmods.dev/badge/skills/sprintra-io/sprintra-mcp/sprintra-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 | $0.00053 | $0.00534 |
| Opus 5 | $0.00026 | $0.00267 |
| Sonnet 5 | $0.00011 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
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 11d 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.
What it actually says
Record Decision (ADR)
Capture a technical or architecture decision into Sprintra as an Architecture Decision Record.
Input
Decision topic: $ARGUMENTS
Process
Step 1: Understand the Decision
If the user already stated the decision clearly (e.g., "let's use PostgreSQL"), proceed to Step 2.
If it's a question ("should we use X or Y?"), briefly discuss tradeoffs (3-4 bullet points per option max), then ask: "Which way do you want to go?" Once decided, proceed.
Step 2: Record the ADR
Call:
decisions(method: "add",
title: "[concise decision title]",
context: "[why this decision was needed — 2-3 sentences]",
decision: "[what was decided and how it will be implemented — 2-3 sentences]",
consequences: "[positive and negative consequences — brief]",
category: "architecture|technology|design|infrastructure|process",
status: "accepted"
)
Rules:
- Title: Past tense action — "Use PostgreSQL for primary database", "Adopt REST over GraphQL"
- Context: The problem or question that prompted this decision
- Decision: The chosen approach with enough detail to understand WHY
- Consequences: Both positive AND negative. Be honest about tradeoffs.
- Category:
architecture(system structure),technology(tool/library choice),design(UI/UX),infrastructure(deploy/ops),process(workflow/team)
Step 3: Check for Conflicts
Call decisions(method: "get_conflicts") to see if this contradicts any existing decisions. If conflicts found, flag them.
Step 4: Confirm
Decision recorded: [title] (dec-xxxxx)
Category: [category]
Status: accepted
Important
- Keep it concise. ADRs are reference docs, not essays.
- If the user is just thinking out loud ("maybe we should..."), don't record it. Only record actual decisions.
- One decision per invocation. If multiple decisions were made, tell the user to run
/decideagain for each.
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.
- 11d ago First seen · 61 lines · 53 tokens per session scan A dc8ffee5d037
decide is a skill published in the GitHub repository Sprintra-io/sprintra-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 534 once invoked, about $0.0003 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
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
post-mortem
Diagnose instruction defects and optionally submit Rosetta GitHub issue.
solr-extending
To build Solr plugins: SearchComponent, QParser, URP, DocTransformer.
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
help-flow
Help about Rosetta: explains capabilities and usage.
init-workspace-flow
Workflow for initializing or upgrading a workspace: context, discovery, documentation, etc.