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/sandeco/reversa/reversa-codingnpx skills add sandeco/reversa --skill reversa-codinggit clone --depth 1 https://github.com/sandeco/reversaWhat 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 | $0.00064 | $0.02451 |
| Opus 5 | $0.00032 | $0.01226 |
| Sonnet 5 | $0.00013 | $0.00490 |
| Haiku 4.5 | $0.00006 | $0.00245 |
Grade A, and why
reversa-coding 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 yesterday.
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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o executor. Sua missão é transformar actions.md em código real, fase por fase, respeitando paralelismo e dependências. Ao terminar, deixar dois rastros para auditoria futura: legacy-impact.md (o que foi mexido no legado) e regression-watch.md (o que precisa continuar verdadeiro nas próximas extrações).
Antes de começar
- Leia
.reversa/state.jsonpara resolveroutput_foldereforward_folder - Use os valores reais nos lugares onde o texto mencionar
_reversa_sdd/ou_reversa_forward/
Âncora de contexto: legado ou greenfield
Esse skill EXIGE uma âncora de contexto em _reversa_sdd/, senão os dois artefatos centrais (legacy-impact.md e regression-watch.md) perdem o valor e o ciclo forward vira um framework genérico qualquer. Duas âncoras são válidas:
- Legado:
_reversa_sdd/contémarchitecture.mdEdomain.md(extração do Time de Descoberta via/reversa). Comportamento clássico. - Greenfield:
_reversa_sdd/contémprd.mdE pelo menos uma spec em_reversa_sdd/sdd/(artefatos do/reversa-new). Projeto novo é caso válido, o pipeline não bloqueia por ausência da extração. Os artefatos do skill se adaptam conforme descrito nas seções de geração.
Se existirem as duas âncoras (projeto que rodou /reversa e /reversa-new), use a de legado como principal e as specs SDD como complemento.
A verificação continua estrita quando NENHUMA âncora existe: o skill aborta com mensagem clara, NÃO oferece opção de prosseguir mesmo assim, NÃO escreve nada em disco.
Verificações Iniciais
- Leia
.reversa/active-requirements.json1.1. Se ausente, aborte com mensagem apontando/reversa-requirements - Verifique a existência de
feature-dir/actions.md2.1. Se ausente, aborte com mensagem apontando/reversa-to-do - Verifique a âncora de contexto:
3.1. Âncora de legado:
_reversa_sdd/existe E contémarchitecture.mdEdomain.md. Se satisfeita, registre internamente o cenário como legado e siga para o passo 4. 3.2. Âncora greenfield:_reversa_sdd/existe E contémprd.mdE pelo menos um arquivo.mdem_reversa_sdd/sdd/. Se satisfeita (e a de legado não), registre o cenário como greenfield, informe ao usuário ("Sem extração de legado, vou ancorar nos artefatos do/reversa-new:prd.mde specs SDD.") e siga para o passo 4. 3.3. Se NENHUMA das duas âncoras estiver satisfeita, aborte com a mensagem:
What ships with it
1 file 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.
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.
- yesterday Changed c419a9432904
- 3d ago First seen · 152 lines · 64 tokens per session scan A 414a907eeb58
reversa-coding is a skill published in the GitHub repository sandeco/reversa (1,544 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 2,451 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…