wellwelwel/lagune / .claude/skills/ingest
ingest
VerifiedUse before reading any .txt file, whatever its name, and whenever a task builds on GitIngest digests. Checks whether a file is a digest (a whole repository in one file) and surveys, searches, and reads it without loading it whole. Returns only the requested lines, with token estimates and anchors for a reusable synthesis.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.6 KB |
| tools/anchor.ts | script | 696 B |
| tools/commands/anchors.ts | script | 1.6 KB |
| tools/commands/extract.ts | script | 2.6 KB |
| tools/commands/files.ts | script | 1.1 KB |
| tools/commands/is.ts | script | 600 B |
| tools/commands/outline.ts | script | 3.1 KB |
| tools/commands/overview.ts | script | 3.5 KB |
| tools/commands/read.ts | script | 1.6 KB |
| tools/commands/search.ts | script | 3.6 KB |
| tools/commands/tree.ts | script | 2.2 KB |
| tools/digest.ts | script | 4.4 KB |
| tools/fail.ts | script | 81 B |
| tools/format.ts | script | 798 B |
| tools/hidden.ts | script | 474 B |
| tools/ingest.ts | script | 5.8 KB |
| tools/package.json | manifest | 23 B |
| tools/paths.ts | script | 433 B |
| tools/pattern/check.ts | script | 1.8 KB |
| tools/pattern/match.ts | script | 1.3 KB |
| tools/pattern/worker.ts | script | 491 B |
| tools/selection.ts | script | 2.2 KB |
| tools/stats.ts | script | 567 B |
| tools/types.ts | script | 1.7 KB |
tools/commands/overview.ts
View on GitHubimport type { Command, Digest, Entry, Stats } from '../types.ts';
import { posix } from 'node:path';
import { formatCount, omitted, tokens } from '../format.ts';
import { hasHidden } from '../hidden.ts';
import { extensionOf } from '../paths.ts';
import { groupBy, sumStats } from '../stats.ts';
const LANDMARKS = new Set([
'agents.md',
'architecture.md',
'cargo.toml',
'claude.md',
'contributing.md',
'docker-compose.yml',
'dockerfile',
'go.mod',
'makefile',
'package.json',
'pyproject.toml',
'readme.md',
]);
const TOP_ENTRIES = 12;
const groupStats = (
entries: Entry[],
keyOf: (entry: Entry) => string
): [string, Stats][] => {
const groups = groupBy(entries, keyOf);
return [...groups.entries()]
.map(([key, group]): [string, Stats] => [key, sumStats(group)])
.sort(([, left], [, right]) => right.characters - left.characters);
};
const topLevelOf = (entry: Entry): string => {
const slash = entry.path.indexOf('/');
return slash < 0 ? '(root files)' : `${entry.path.slice(0, slash)}/`;
};
const statsLine = (name: string, stats: Stats): string =>
` ${name} ${formatCount(stats.files)} files, ${tokens(stats.characters)}`;
const overviewOf = (digest: Digest): string[] => {
const text = digest.entries.filter((entry) => entry.kind === 'text');
const content = text.filter((entry) => !entry.noise);
const noise = text.filter((entry) => entry.noise);
const hidden = text.filter(hasHidden);
const countOf = (kind: Entry['kind']): number =>
digest.entries.filter((entry) => entry.kind === kind).length;
const landmarks = content.filter(
(entry) =>
entry.path.split('/').length <= 3 &&
LANDMARKS.has(posix.basename(entry.path).toLowerCase())
);
const largest = [...content]
.sort((left, right) => right.characters - left.characters)
.slice(0, TOP_ENTRIES);
const total = sumStats(content);
const noiseTotal = sumStats(noise);
return [
`${digest.root} (${digest.file})`,
` ${formatCount(digest.bytes)} bytes, ${formatCount(digest.entries.length)} entries: ${formatCount(text.length)} text, ${formatCount(countOf('binary'))} binary, ${formatCount(countOf('empty'))} empty, ${formatCount(countOf('symlink'))} symlinks`,
` content: ${formatCount(total.files)} files, ${tokens(total.characters)}`,
` noise: ${formatCount(noiseTotal.files)} files, ${tokens(noiseTotal.characters)} (left out unless --noise)`,
...(hidden.length > 0
? [
` hidden characters (control, zero-width, or bidirectional) in ${formatCount(hidden.length)} files:`,
...hidden.slice(0, TOP_ENTRIES).map((entry) => ` ${entry.path}`),
]
: []),
'',
'Top level',
...groupStats(content, topLevelOf).map(([name, stats]) =>
statsLine(name, stats)
),
'',
'Extensions',
...groupStats(content, (entry) => extensionOf(entry.path))
.slice(0, TOP_ENTRIES)
.map(([name, stats]) => statsLine(name, stats)),
'',
'Landmarks',
...landmarks
.slice(0, TOP_ENTRIES * 2)
.map(
(entry) =>
` ${entry.path} ${formatCount(entry.lines.length)} lines, ${tokens(entry.characters)}`
),
...omitted(
landmarks.length - TOP_ENTRIES * 2,
', list them with files --name'
),
'',
'Largest files',
...largest.map(
(entry) =>
` ${entry.path} ${formatCount(entry.lines.length)} lines, ${tokens(entry.characters)}`
),
];
};
export const overview: Command = async (digests) =>
digests.flatMap((digest, index) => [
...(index > 0 ? [''] : []),
...overviewOf(digest),
]);
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |