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 agentmods add skills/smana/cloud-native-ref/spec-researchnpx skills add Smana/cloud-native-ref --skill spec-researchgit clone --depth 1 https://github.com/Smana/cloud-native-refWhat 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 | $0.00065 | $0.01080 |
| Opus 5 | $0.00032 | $0.00540 |
| Sonnet 5 | $0.00013 | $0.00216 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
spec-research 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 3d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Research Skill (subagent)
Runs in an isolated Explore-agent context. Read-only across the repo + external sources; writes exactly one file: docs/superpowers/specs/<YYYY-MM-DD>-<slug>-research.md.
Your mission
Research $ARGUMENTS to feed a Superpowers design (superpowers:brainstorming). Produce a concise, reusable research artifact the design author can build on.
Research protocol
1. Frame the question
Parse $ARGUMENTS for the topic slug (first token) and the research question (remainder). The design doc need not exist yet — write the research file so the design author can consume it.
2. Map the local landscape first
Before going external, exhaust the repo:
- Existing compositions in the sibling
Smana/crossplane-configurationrepo, underapis/<api>/kcl/— grep for analogous patterns (e.g., if researching cache, look atapp/,sqlinstance/). - Constitution (
docs/platform-constitution.md) — which rules apply to this topic? - ADRs (
docs/decisions/) — any prior decision constrains this? - Prior designs (
docs/superpowers/specs/) and archived specs (docs/specs/done/) — reuse patterns rather than reinvent. - Runtime examples:
infrastructure/aws-0/,security/aws-0/, etc.
3. External sources (in priority order)
- Context7 via
mcp__context7__resolve-library-idthenmcp__context7__query-docs— up-to-date docs for any named library or operator. - Official operator/vendor docs via WebFetch.
- Superpowers skills (the installed plugin's
skills/directory) when the research is meta — about the workflow, not the tech. - WebSearch only if the above three yielded nothing — lowest signal, easiest to misquote.
4. Write research.md
Emit exactly this structure at docs/superpowers/specs/<YYYY-MM-DD>-<slug>-research.md:
# Research: <one-line question>
**Topic**: <slug>
**Conducted**: <YYYY-MM-DD>
**Researcher**: Claude (spec-research subagent)
---
## TL;DR
<3–5 bullet points: the decisions the researcher would recommend and why>
## Standard stack
<Operators, libraries, images we should use. Pin to specific versions when docs list an LTS.>
| Component | Pick | Version | Source |
|-----------|------|---------|--------|
## Local patterns worth reusing
<File paths + 1-line note on what each shows. Copy existing patterns over invention.>
- `<path>`: <why it matters>
## Don't hand-roll
<Things the ecosystem already solves. Saves the spec author from designing these.>
## Common pitfalls
<Sharp edges from ecosystem docs / community. Especially: KCL mutation (#285),
Cilium bug #43493 for prefix delegation, anything that broke in this repo before.>
## Open questions surfaced
<Items to raise as open questions during brainstorming>
- [ ] <question>
- [ ] <question>
## References
- Context7: `<library-id>` <brief excerpt>
- <Vendor doc URL>
- Local files: `<path>`, `<path>`
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.
- 3d ago First seen · 110 lines · 65 tokens per session scan A 0e134566aafc
spec-research is a skill published in the GitHub repository Smana/cloud-native-ref (99 stars, last pushed 3d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,080 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 2026-08-30.
Other skills, from other repositories
database-schema-designer
Design robust, scalable database schemas for SQL and NoSQL databases. Provides normalization guidelines, indexing strategies, migration patterns, constraint design, and performance optimization. Ensures data integrity, query performance, and maintainable data models.
gepetto
Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
gnhf
Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.
gen-test
Generate idiomatic tests for Go packages and handlers in the Meshery project.
superplane-dashboard-and-widgets
Implements and configures SuperPlane canvas consoles (markdown, node, table, board, chart, number, scorecard panels), widget data sources, CEL/templates, table row trigger actions, and console YAML. Use when editing console UI, panelTypes, useWidgetData, WidgetTable, WidgetBoard, canvasconsoleyml…
superplane-changelog
When generating a SuperPlane changelog from merged commits. Use for "what's new" summaries with new integrations, new components/triggers, improvements, security updates, and bug fixes. Output is user-focused markdown in tmp/.