token-goat 2.6.8 → 2.6.9

package/README.md

@@ -97,9 +97,13 @@ The fastest way to reduce AI token costs is fixing these five, not writing short
 | CSV/JSON/JSONL/log file re-read when only structure changed | Pre-Read hint for structured files (CSV headers, JSON keys, log format), ~70% smaller than full read |
 | Index-only files (lockfiles, source maps, bundles) read on every session | Pre-Read suppression for read-only files (package-lock.json, *.map, dist/), skipped unless explicitly edited |
 | Large markdown file read in full (README.md, CHANGELOG.md, CLAUDE.md ≥8 KB) | Heading tree intercepted instead — H1–H3 with `#2`/`#3` disambiguation; `token-goat section` shortcuts listed for well-known files; post-edit injects a re-read suggestion rather than the full file |
-| PDF or Office binary (.docx, .xlsx, .pptx, .odt) opened via Read | Full read denied; PDF shows page count and outline (`token-goat pdf-extract` pulls the actual text, optionally paged/sliced, when the outline isn't enough); Office binaries redirect to `pandoc` or `docx2txt` for text extraction |
+| PDF opened via Read | Full read denied; PDF shows page count and outline (`token-goat pdf-extract` pulls the actual text, optionally paged/sliced, when the outline isn't enough) |
+| Excel/PowerPoint/Word file (.xlsx/.pptx/.docx) opened via Read | Full read denied; redirects to the matching narrow-slice command family (`xlsx-sheets`/`xlsx-head`/`xlsx-range`/`xlsx-query`, `pptx-outline`/`pptx-slide`/`pptx-notes`/`pptx-text`, `docx-outline`/`docx-text`) instead of extracting the whole document as text |
+| Other Office binary (.odt, .ods, .ott, .odp) opened via Read | Full read denied; redirects to `pandoc` for text extraction (no dedicated reader for these formats yet) |
 | Large CSV or TSV file (≥10 KB) read in full | Column headers, row count, and 3 sample rows shown; `token-goat csv-query` projects columns and/or filters rows instead of a full read; `duckdb` query suggestion for very large tabular data |
 | WebFetch returns a page's full raw HTML | HTML-to-text extraction strips markup/scripts/styles before the model ever sees it — readable prose instead of a wall of tags |
+| Large WebVTT/SRT transcript (≥10 KB) read in full | Duration, cue count, and detected speakers shown; `token-goat transcript-outline` gives a skimmable speaker/time overview and `token-goat transcript` slices by speaker/time range/pattern instead of a full read |
+
 | Large TXT or log file (≥20 KB) read in full | Line count + first/last 5 lines shown; `.log`/`.out` files bias toward `--tail 100 --grep`; general catch-all for any file ≥100 KB |
 | Subagent reads a 47–86 KB recon dump (or greps a 73 KB transcript) and overflows its window | `pre_read` denies a full Read at or above `large_read_redirect_bytes` (512 KB base, tightened by context pressure to as low as ~92 KB once the session is nearly full — the case that matters most for an already-strained subagent), and a `content`-mode Grep over one oversized file, redirecting both to surgical reads or a windowed `offset`/`limit` |
 | Subagent overflows at "hello" with no idea why | `token-goat baseline` attributes the fixed environmental floor — other plugins' hook dumps, both CLAUDE.md files, MEMORY.md, MCP servers — by owner, suggested fix, and fixed-vs-variable cost |
@@ -426,8 +430,31 @@ To upgrade cleanly:
 | `token-goat resume <session_id>` | Emit a single post-compact recovery packet — top skills, last two Bash outputs, top edited-file diffs, and `git diff --stat`, capped at ~2000 tokens. Replaces 5-10 round-trips. |
 | `token-goat config list / get / set / validate` | Inspect or edit `config.toml` from the CLI. `validate` reports unknown keys with did-you-mean suggestions. |
 | `token-goat config-get <file> <key>` | Look up one key from a config-shaped file (TOML/INI `key = value`, or YAML) without reading the whole thing. On a `.md` file, a leading `---`-fenced YAML frontmatter block (Jekyll/Hugo/SKILL.md style) is checked first and takes precedence over the TOML/INI fallback; a `.md` file with no frontmatter, or an unclosed fence, falls through to the normal lookup unchanged. |
-| `token-goat pdf-extract <file>` | Extract plain text from a PDF instead of a raw Read. `--pages <spec>` narrows to a page range (e.g. `1-5` or `3`); `--head`/`--tail`/`--grep`/`--max-matches`/`--section` slice the extracted text the same way `bash-output`/`web-output` do. |
-| `token-goat csv-query <file>` | Project columns and/or filter rows from a CSV instead of a raw Read. `--columns <cols>` selects a comma-separated subset; `--where col=value` applies an equality filter; `--head <n>` caps rows; `--json` emits rows as a JSON array of objects instead of a formatted table. |
+| `token-goat pdf-extract <file>` | Extract plain text from a PDF instead of a raw Read. `--pages <spec>` narrows to a page range (e.g. `1-5` or `3`); `--head`/`--tail`/`--grep`/`--max-matches`/`--section` slice the extracted text the same way `bash-output`/`web-output` do. `--layout` heuristically reconstructs column-aware reading order from text-item coordinates instead of raw content-stream order (imperfect on rotated/overlapping text). |
+| `token-goat pdf-outline <file>` | List a PDF's bookmark/outline tree with page numbers instead of a raw Read. |
+| `token-goat pdf-meta <file>` | Page count, title/author, and whether a PDF has an extractable text layer (so you know before extracting whether it's scanned/image-only). |
+
+| `token-goat csv-query <file>` | Project columns and/or filter rows from a CSV instead of a raw Read. `--columns <cols>` selects a comma-separated subset; `--where <spec>` is repeatable and ANDed, supporting `col=value`, `col!=value`, `col>value`, `col<value`, and `col~=regex`; `--head <n>` caps rows; `--json` emits rows as a JSON array of objects instead of a formatted table; `--delimiter <char>` and `--no-header` handle non-comma or headerless files. |
+| `token-goat csv-profile <file>` | Per-column type inference (number/date/string), null/distinct counts, and min/max or top values for low-cardinality columns, instead of a raw Read. Same `--delimiter`/`--no-header` flags as `csv-query`. |
+| `token-goat sharepoint-resolve <shareUrl>` | Best-effort resolve a SharePoint/OneDrive sharing URL to a local synced file path, purely from the local filesystem and `OneDrive`/`OneDriveCommercial` env vars -- no network call, no Graph API, no credentials. Prints the resolved path (feed it to `xlsx-sheets`/`pptx-outline`/etc.) or an honest "could not resolve" with the paths it tried. |
+| `token-goat video-chapters <file>` | Lists a video's embedded chapter markers (timestamps + titles) and subtitle/caption streams via `ffprobe`, instead of downloading/transcoding the file to inspect it. Requires ffmpeg on PATH; degrades with a clear message when it's missing. |
+
+
+
+| `token-goat xlsx-sheets <file>` | List sheet names, used range, and dimensions in an Excel workbook instead of a raw Read. |
+| `token-goat xlsx-head <file> --sheet <name>` | Preview the header + first N rows of one sheet (`--rows`, default 20) instead of a raw Read. |
+| `token-goat xlsx-range <file> --sheet <name> --range <a1>` | Extract one cell range (e.g. `A1:D50`) from a sheet; `--formulas` shows formulas instead of computed values. |
+| `token-goat xlsx-query <file> --sheet <name>` | Project columns / filter rows from one sheet instead of a raw Read (same `--columns`/`--where`/`--head` shape as `csv-query`, via the sheet's CSV projection). |
+| `token-goat pptx-outline <file>` | Per-slide title, body size, and speaker-notes flag instead of a raw Read. |
+| `token-goat pptx-slide <file> --slide <n>` | Full text of one slide; `--notes` appends that slide's speaker notes. |
+| `token-goat pptx-notes <file>` | Speaker notes for one slide (`--slide <n>`) or all slides, instead of a raw Read. |
+| `token-goat pptx-text <file> --grep <pattern>` | Find slides whose text matches a pattern instead of a raw Read. |
+| `token-goat docx-outline <file>` | Heading tree of a Word document instead of a raw Read. |
+| `token-goat docx-text <file>` | Full body text of a Word document instead of a raw Read; `--head`/`--tail`/`--grep`/`--section`/`--max-matches` slice it the same way `pdf-extract` does. |
+| `token-goat transcript-outline <file>` | Speaker list, duration, and time-bucketed markers for a WebVTT/SRT transcript instead of a raw Read. |
+| `token-goat transcript <file>` | Slice a WebVTT/SRT transcript by `--speaker <name>`, `--from`/`--to <hh:mm:ss>`, and/or `--grep <pattern>` instead of a raw Read. |
+
+
 | `token-goat screenshot <url> <destPath>` | Capture a local headless-browser screenshot, shrunk the same way local image reads are (image-shrink pipeline). `--executable-path` overrides the Chrome/Chromium binary; `--width`/`--height` set the viewport (default 1280x800); `--full-page` captures the full scrollable page. |
 | `token-goat clean-cache` | Prune on-disk caches to their configured floor without waiting for the worker. |
 | `token-goat prune-cache` | Manually trigger LRU eviction across all cache directories (images, bash, web, skills). |