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 code-wikigit 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/code-wiki)<a href="https://agentmods.dev/skills/metaspartan/cybara/code-wiki"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/code-wiki/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/code-wiki"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/code-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00027 | $0.00609 |
| Opus 5.5 | $0.00011 | $0.00244 |
| Sonnet 5.5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
code-wiki 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 1mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Wiki
Use this when the user asks to document a repository, generate architecture diagrams, create a code wiki, or onboard to an unfamiliar codebase.
This is a reference-documentation workflow. It explains what exists and how it fits together; it is not a product strategy or roadmap exercise.
Output Location
Default to ~/.cybara/wikis/<repo-name>/ so active repositories are not modified. Only write under the repo, such as docs/wiki/, when the user explicitly asks for in-repo documentation.
Workflow
- Resolve the target repository.
- If the user gave a local path, use that path.
- If they gave a GitHub URL, clone with
git clone --depth 50 <url> <tmp>/repo. - Record
git rev-parse HEADwhen available.
- Scan the structure with
rg --files, excluding generated and dependency dirs:.git,node_modules,dist,build,target,.next,.expo,coverage,venv,.venv.
- Read the README, manifests, and main entry points:
package.json,bun.lock,Cargo.toml,pyproject.toml,go.mod,Package.swift, app entry files.
- Pick 8-10 modules for the first pass.
- Prioritize entry points, shared/core modules, API boundaries, UI route roots, persistence layers, and integration adapters.
- Write:
README.mdwith purpose, concepts, entry points, and module map.architecture.mdwith a Mermaid flowchart.modules/<module>.mdfor each selected module.diagrams/sequences.mdwith 2-4 key workflows.getting-started.mdwith verified local commands..codewiki-state.jsonwith repo path, commit, generated time, and files reviewed.
Quality Bar
- Every statement should trace to code, config, or docs you read.
- Use relative links for local output; use commit-pinned GitHub links for cloned public repos.
- Keep Mermaid valid and readable. Prefer
flowchart LRfor architecture andsequenceDiagramfor workflows. - Do not document generated bundles or dependency directories.
- Do not claim coverage of the whole repo when you only sampled modules; list gaps explicitly.
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.
- 1mo ago First seen · 55 lines · 27 tokens per session scan A 19977b79533d
code-wiki is a skill published in the GitHub repository metaspartan/cybara (32 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 609 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
awesome-ai-agents-curation
Help founders prepare evidence-backed AI agent project submissions and help maintainers triage project issues and pull requests for the Awesome AI Agents list.
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-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.