Borrowing it
Nothing to install: this file belongs to hirurg-lybitel/MCP-Nexus. 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/hirurg-lybitel/MCP-Nexus/main/.agents/skills/solution-shaping/SKILL.mdgit clone --depth 1 https://github.com/hirurg-lybitel/MCP-NexusWrote 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/hirurg-lybitel/mcp-nexus/solution-shaping)<a href="https://agentmods.dev/skills/hirurg-lybitel/mcp-nexus/solution-shaping"><img src="https://agentmods.dev/badge/skills/hirurg-lybitel/mcp-nexus/solution-shaping/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/hirurg-lybitel/mcp-nexus/solution-shaping"><img src="https://agentmods.dev/badge/skills/hirurg-lybitel/mcp-nexus/solution-shaping.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 | $0.00073 | $0.01028 |
| Opus 5.5 | $0.00029 | $0.00411 |
| Sonnet 5.5 | $0.00015 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
solution-shaping 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 2mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solution shaping
Role
Act as a software architect, not only a coder: name tradeoffs, boundaries, dependencies, and failure modes. Prefer clarity and decisions over exhaustive inventory.
Default outcomes
For each solution (capability, subsystem, or vertical slice) under design, produce:
- Architecture plan — what it is for, what it owns, what it depends on, what it explicitly does not do.
- Task breakdown — small, implementable steps (roughly PR-sized), ordered, with explicit dependencies between steps.
- User-facing documentation — short, plain language for a non-specialist reader (product, operations, or “interested user”). Avoid unexplained jargon; define terms once in a glossary if needed.
- Diagrams — when structure or flow matters, include Mermaid diagrams (or ASCII if Mermaid is unsuitable). At least one diagram if there are more than two external touchpoints or non-trivial flow.
Write user-facing documentation in the same language as the user’s request unless they ask otherwise.
When information is missing
Do not invent business facts. Ask targeted clarifying questions (batch them, max ~5–8 at a time), for example:
- Who is the primary user or consumer?
- What must work on day one vs later?
- Hard constraints: performance, security, compliance, offline, browser support, etc.
- Existing systems this must integrate with (APIs, DBs, queues, UI surfaces).
- Success criteria: how will we know it works?
If blocked on answers, state assumptions in one labeled section and continue with a design that can be revised.
Workflow
Copy and use this checklist:
Solution shaping checklist
- [ ] Goal and scope boundary (in / out)
- [ ] Actors and dependencies (who calls whom; data flow)
- [ ] Risks and mitigations (top 3)
- [ ] Task list with order and dependencies
- [ ] User doc: short overview + glossary if needed
- [ ] Diagram(s): context and/or sequence and/or component
- [ ] Open questions (only if still open)
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.
- 2mo ago First seen · 119 lines · 73 tokens per session scan A 7fd6bb9eeab1
solution-shaping is a skill published in the GitHub repository hirurg-lybitel/MCP-Nexus (0 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 1,028 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 2026-08-31.
solution-shaping compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| solution-shapinghirurg-lybitel/MCP-Nexus | Skill | 0 | 4mo ago | MIT | A | 73 | Claude Code, Codex |
| agentcore-investigationawslabs/mcp | Skill | 9.9k | today | Apache-2.0 | A | 52 | Claude Code, Codex |
| amazon aurora dsqlawslabs/mcp | Skill | 9.9k | today | Apache-2.0 | A | 46 | Claude Code |
| redshift-guideawslabs/mcp | Skill | 9.9k | today | Apache-2.0 | A | 258 | Claude Code, Codex |
| mcp-tools-referencedylanroscover/Embody | Skill | 212 | 2d ago | MIT | A | 27 | Claude Code |
| td-api-referencedylanroscover/Embody | Skill | 212 | 2d ago | MIT | A | 48 | Claude Code |
| briefdylanroscover/Embody | Skill | 212 | 2d ago | MIT | A | 49 | Claude Code |