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 metaspartan/cybara --skill spikegit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/spike)<a href="https://agentmods.dev/skills/metaspartan/cybara/spike"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/spike/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/metaspartan/cybara/spike"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/spike.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00402 |
| Opus 5 | $0.00020 | $0.00201 |
| Sonnet 5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
spike 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 9d 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
Spike
A spike is a time-boxed, throwaway investigation. Its output is a decision, not production code.
When to use
- "Will approach X even work?" / "Can we do Y with Z?"
- Comparing 2+ approaches and needing empirical data, not opinion.
- De-risking an unknown (an API, a library, a perf claim) before building the real thing.
Procedure
- State the question precisely. What must be true for the approach to be viable? ("Can library X parse a 1GB file in <2s without OOM?")
- Set a time/effort box. Spikes are short — if it's taking long, narrow the question.
- Write the minimum code to answer the question. Use
exec/writein an isolated scratch path (e.g.spike/). Don't worry about quality. - Measure the actual thing. Run it; capture timing/output/errors. Don't extrapolate.
- Report a verdict:
- Verdict: VIABLE / NOT VIABLE / NEEDS-MORE-INFO
- Evidence: concrete numbers, snippet, or the failure mode observed.
- Recommendation: proceed with X / avoid X because / next probe needed.
- Clean up the scratch code (or move it aside) unless it's promoted to real code.
Anti-patterns
- Spending a spike polishing code instead of answering the question.
- Reporting "it should work" without measuring.
- Letting a spike silently become production code without a review pass.
Keep spikes honest: a "no, this won't work" verdict with evidence is a successful spike.
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.
- 9d ago First seen · 35 lines · 40 tokens per session scan A 26daab3652df
spike is a skill published in the GitHub repository metaspartan/cybara (30 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 402 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
kodama-verification
Define measurable success criteria and collect targeted test, build, lint, type-check, or smoke-test evidence before claiming work is complete.
kodama-behavior
Classify requests, assess unfamiliar codebases, delegate work safely, and recover from failed attempts. Use for multi-step, ambiguous, or parallelizable work.
kodama-constraints
Enforce non-negotiable safety, scope, security, and quality constraints for implementation and review work.
project-release-check
Validate this example project's release readiness. Use before publishing a release candidate.
slop-taste
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
slop-hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.