@matheuskrumenauer/tanya 0.2.0-beta.0 → 0.4.0-beta.0

package/README.md

@@ -38,6 +38,16 @@ npm install -g @matheuskrumenauer/tanya
 
 The unscoped `tanya` name is taken on npm, so the package publishes under the `@matheuskrumenauer` scope.
 
+Docker/container installs that cannot infer platform metadata may need npm
+platform flags for Tanya's image tooling dependency:
+
+```bash
+npm install -g --os=linux --cpu=arm64 --libc=glibc @matheuskrumenauer/tanya
+```
+
+Use `--cpu=amd64` on x64 containers. Tracking issue:
+https://github.com/matheusjkweber/tanya/issues/9.
+
 ## Contributing
 
 Start with [CONTRIBUTING.md](./CONTRIBUTING.md) for local setup, tool and
@@ -130,6 +140,27 @@ tanya providers test          # provider smoke test
 tanya doctor                  # local environment check
 ```
 
+## Slash commands
+
+Interactive chat accepts built-in slash commands without sending them to the
+model:
+
+```text
+/clear            # reset only the active conversation history
+/skills           # list matched skill packs and token cost
+/verify           # print the deterministic verifier report for the cwd
+/cost             # show persisted token usage and estimated cost
+/memory --limit 5 # list recent golden-task memory
+```
+
+Project-local commands live in `.tania/commands/*.{js,ts,sh}` and appear in
+`/help` with a `project:` prefix, for example `/project:say-hi`. Shell commands
+run directly; JavaScript and TypeScript commands export a default
+`CommandDefinition`.
+
+Project-local commands are arbitrary code execution. TODO(M3): gate them
+through the permission engine before treating them as safe extension points.
+
 `--verify` adds required verification commands to the run context. Tanya must run and report each exact command before finishing the coding task.
 
 `tanya benchmark run --all` currently exercises 26 executable low-to-medium regression fixtures: targeted edits, new files, dependency/lockfile updates, framework-style migrations, failing-test repair, frontend smoke checks, artifact/context reuse, streaming long-tool execution, run-history logging, dirty worktrees, report repair, and the CosmoHQ mobile/backend smoke profiles.