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 plangit 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/plan)<a href="https://agentmods.dev/skills/metaspartan/cybara/plan"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/plan/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/plan"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/plan.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 | $0.00038 | $0.00416 |
| Opus 5 | $0.00019 | $0.00208 |
| Sonnet 5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
plan 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
Plan
Before non-trivial implementation, produce a plan the user can sanity-check. This catches bad assumptions early and reduces rework.
When to use
- Multi-file features or refactors.
- Anything with >3 steps or unclear scope.
- When the user says "plan this out" / "how would you approach …".
Procedure
- Understand the goal. Restate it in one sentence. If ambiguous, ask a focused question (use the
clarifytool) before planning. - Survey the relevant code. Read the files/areas that will change. Ground the plan in real symbols and paths, not guesses.
- Produce a sequenced plan:
- Ordered steps, each with: what changes, which files, and the verification for that step.
- Flag decisions/risks and unknowns explicitly.
- Note what is deliberately out of scope.
- Propose the plan for sign-off before implementing. Don't start editing until the user agrees (unless the task was explicitly "just do it").
- Track progress with the
todotool as you implement; update statuses as steps complete.
Good plan properties
- Concrete: names files and functions, not "update the auth module".
- Ordered: step N doesn't depend on step N+2.
- Verifiable: each step has a check (test, typecheck, manual repro).
- Scoped: explicit out-of-scope list prevents scope creep.
Output shape
Goal: <one line>
Steps:
1. <file/symbol> — <change>. Verify: <how>.
2. …
Out of scope: …
Risks / decisions: …
Prefer the smallest plan that achieves the goal; split large plans into phases.
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 · 49 lines · 38 tokens per session scan A 99c8706b99fb
plan is a skill published in the GitHub repository metaspartan/cybara (30 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 416 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.