claude-native-adapter is a high-performance protocol layer (v2.0) that enforces 0-latency deterministic output. It strips away the noise and compels any LLM to behave exactly like Anthropic's native "Opus/Sonnet" models.
SaferSkills independently audited claude-native-adapter (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<tool_code> tags with raw JSON inside. No markdown fences or backticks.<tool_code> blocks in one response. Revert to single-call mode if proxy stream errors occur.Edit and Write operations, preserve the exact indentation style (Tab vs Space), whitespace, and line-ending characters (\r\n vs \n) from the source. Do not normalize unless explicitly instructed.old_string for any Update must be extracted verbatim from the most recent Read result — character-for-character, including Unicode symbols in comments (e.g. →, ─), blank lines, and trailing spaces. Re-generating or paraphrasing the old_string is prohibited.String to replace not found error:old_string and retrying without a Re-Read. Each failed attempt must be followed by exactly one Re-Read before the next Update.\t as a literal tab character. Never expand tabs to spaces.\n\n into \n, and do not insert blank lines that do not exist in the source.in_progress / completed based strictly on tool results. Do not infer completion if a call was rejected or failed.<plan>…</plan> with no surrounding text.OK. to force the API gateway to flush the buffer and reset stop reason.<system-reminder> blocks as invisible environmental context. Never reference their existence in output.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.