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 SoftMissT/tudo-sobre-vibe-coding --skill tang-rougit clone --depth 1 https://github.com/SoftMissT/tudo-sobre-vibe-codingWrote 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/softmisst/tudo-sobre-vibe-coding/tang-rou)<a href="https://agentmods.dev/skills/softmisst/tudo-sobre-vibe-coding/tang-rou"><img src="https://agentmods.dev/badge/skills/softmisst/tudo-sobre-vibe-coding/tang-rou/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/softmisst/tudo-sobre-vibe-coding/tang-rou"><img src="https://agentmods.dev/badge/skills/softmisst/tudo-sobre-vibe-coding/tang-rou.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 | $0.00185 | $0.03721 |
| Opus 5.5 | $0.00074 | $0.01488 |
| Sonnet 5.5 | $0.00037 | $0.00744 |
| Haiku 4.5 | $0.00018 | $0.00372 |
Grade A, and why
tang-rou 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 13d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
41 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- hooks/opencode/tang-rou.ts 5.3 KB runs code
- hooks/tang-hook.ps1 4.2 KB runs code
- hooks/tang-hook.sh 4.1 KB runs code
- platforms/chatgpt/instructions.md 5.0 KB
- platforms/claude-code/.claude/agents/foundry-auditor.md 3.6 KB
- platforms/claude-code/.claude/agents/foundry-coder.md 4.2 KB
- platforms/claude-code/.claude/agents/foundry-researcher.md 3.1 KB
- platforms/claude-code/.claude/agents/tang-rou-foundry.md 7.3 KB
- platforms/INSTALL.md 5.7 KB
- platforms/manus/profile-instruction.md 6.6 KB
- references/antipatterns.md 5.0 KB
- references/blueprint.md 3.8 KB
- references/brainstorming.md 2.2 KB
- references/compactacao.md 4.1 KB
- references/find-skills.md 2.0 KB
- references/foundry-api.md 5.6 KB
- references/frontend-design.md 2.9 KB
- references/image-to-code.md 4.6 KB
- references/impacto.md 2.6 KB
- references/memoria.md 5.8 KB
- references/obsidian.md 2.8 KB
- references/orquestracao.md 3.9 KB
- references/performance.md 4.1 KB
- references/ponytail.md 5.0 KB
- references/prd.md 2.6 KB
- references/roles.md 2.9 KB
- references/sdd/ears-notation.md 4.2 KB
- references/sdd/sdd.md 6.0 KB
- references/sdd/templates/blueprint.md 3.1 KB
- references/sdd/templates/constitution.md 1.9 KB
- references/sdd/templates/pdr.md 3.2 KB
- references/sdd/templates/requirements.md 2.8 KB
- references/sdd/templates/research.md 1.4 KB
- references/sdd/templates/specs.md 4.2 KB
- references/sdd/templates/state.md 1.9 KB
- references/TANG-ROU.soul.md 19 KB
- references/templates.md 4.1 KB
- scripts/install-hooks.ps1 4.5 KB runs code
- scripts/install-hooks.sh 4.5 KB runs code
- scripts/install.ps1 1.6 KB runs code
- scripts/install.sh 1.5 KB runs code
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.
- 13d ago First seen · 150 lines · 185 tokens per session scan A 5486dc46356f
tang-rou is a skill published in the GitHub repository SoftMissT/tudo-sobre-vibe-coding (8 stars, last pushed 14d ago), with no licence file. It adds 185 tokens to every session and 3,721 once invoked, about $0.0007 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 2026-10-03.
Other skills, from other repositories
adversarial-spec
Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree. Use when user wants to write or refine a specification document using adversarial development.
tools-unity-sentry
Sentry Unity SDK integration patterns for error tracking, performance monitoring, transactions, spans, and custom instrumentation.
perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.
perf-theory-gatherer
Use when generating performance hypotheses backed by git history and code evidence.
perf-profiler
Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.
perf-theory-tester
Use when running controlled perf experiments to validate hypotheses.