{
  "markdown": "# noyap\n\n**No yap. Ship the smallest correct change. Shut up about it.**\n\nPortable [Agent Skills](https://agentskills.io) package: **minimal narration** + **minimal correct code** in one skill.\n\n| Axis | What it controls | Similar to |\n|---|---|---|\n| **Mouth** | Near-zero narration, preambles, tours, closing offers | [caveman](https://github.com/JuliusBrussee/caveman) |\n| **Hands** | YAGNI, soft LOC budgets, anti-golf, surgical diffs | [ponytail](https://github.com/DietrichGebert/ponytail) |\n| **Dial** | `silent` (default) · `brief` · `off` + one-shot `why?` | overrides |\n\nnoyap does **not** disable model reasoning. It reduces chatter, scope, tool sprawl, LOC, and tokens. **Correctness and safety always win.**\n\n---\n\n## Install\n\n```bash\n# One command (skills + always-on pin into the current project)\nnpx @harjjotsinghh/noyap --project .\n\n# Full skill body as always-on (more tokens)\nnpx @harjjotsinghh/noyap --project . --full\n\n# Or skills CLI + pin\nnpx skills add HarjjotSinghh/noyap\nnpx @harjjotsinghh/noyap --agents-only --project .\n```\n\nClaude Code:\n\n```text\n/plugin marketplace add HarjjotSinghh/noyap\n/plugin install noyap@noyap\n```\n\nFull matrix: **[INSTALL.md](INSTALL.md)** · Help: `npx @harjjotsinghh/noyap --help`\n\n---\n\n## Modes\n\n| Mode | Say | Behavior |\n|---|---|---|\n| **silent** (default) | `noyap` / `just code` | Diff + path line or `Done.` |\n| **brief** | `noyap: brief` | Silent + ≤2 short lines |\n| **off** | `noyap: off` / `verbose` | Suspended |\n| one-shot | `why?` | Full explanation of last change, then resume |\n\n---\n\n## vs ponytail / caveman\n\n| | caveman | ponytail | **noyap** |\n|---|---|---|---|\n| Shrinks prose | ✅ | — | ✅ |\n| Shrinks code / scope | — | ✅ | ✅ |\n| Soft LOC + anti-golf | — | partial | ✅ |\n| Speculative “for later” refuse | — | ladder | ✅ hard rule |\n| Multi-provider scaffold refuse | — | partial | ✅ hard rule |\n| silent / brief / off | levels | lite/full/ultra | ✅ |\n| Always-on auto-pin | varies | AGENTS.md | ✅ `npx` / installer |\n| Hooks / heavy plugin stack | heavy | heavy | **none** |\n\nUse caveman+ponytail if you want those brands. Use **noyap** for one portable skill covering both halves.\n\nMore: [docs/compare.md](docs/compare.md)\n\n---\n\n## Benchmarks\n\n**Primary (n=3, evals 1/7/10, Grok 4.5):**  \n[benchmarks/results/n3-20260811T055638Z/COMPARISON.md](benchmarks/results/n3-20260811T055638Z/COMPARISON.md)\n\n| arm (median) | success | out_tok vs base | total_tok vs base |\n|---|--:|--:|--:|\n| **noyap** | **89%** | **−61%** | **−49%** |\n| ponytail | 67% | −39%* | −10%* |\n| caveman | 44% | −22%* | +16%* |\n\n\\*approx from medians vs baseline in that stamp. **noyap alone hit 100% on multi-auth YAGNI (n=3).**\n\n**Also:** single-shot full suite [20260811T053548Z](benchmarks/results/20260811T053548Z/COMPARISON.md) · real package `sindresorhus/is` [real-20260811T055638Z](benchmarks/results/real-20260811T055638Z/COMPARISON.md)\n\n| Published elsewhere (different engines/repos — **not** interchangeable) | Source |\n|---|---|\n| Ponytail −54% LOC / −22% tokens (Claude Code · Haiku · FastAPI template) | [ponytail agentic](https://github.com/DietrichGebert/ponytail/blob/main/benchmarks/results/2026-06-18-agentic.md) |\n| Caveman −65% chat output · −8.5% agentic (JetBrains) | [caveman](https://github.com/JuliusBrussee/caveman) |\n\n**Do not treat our Grok % as equal to ponytail’s Claude %.** Same metric names only.\n\nReproduce: [benchmarks/README.md](benchmarks/README.md)\n\n---\n\n## License\n\n[MIT](LICENSE)\n",
  "bytes": 3467,
  "sha": "32282472203d68148f3210abeeac4875bae082e03339e33d6a7c54ac78d137d3",
  "repo_slug": "harjjotsinghh/noyap",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_harjjotsinghh_noyap_619d5ac3/readme"
}