From tldr
Decides when to use tldrcrew subagents (investigator, builder, reviewer) for compressed TLDR output, saving ~60% context tokens per delegation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tldr:tldrcrewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
tldrcrew = three subagent presets that emit TLDR output. Same job as Anthropic defaults (`Explore`, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation.
tldrcrew = three subagent presets that emit TLDR output. Same job as Anthropic defaults (Explore, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation.
| Task | Use |
|---|---|
| "Where is X defined / what calls Y / list uses of Z" | tldrcrew-investigator |
| Same but you also want suggestions/architecture commentary | Explore (vanilla) |
| Surgical edit, ≤2 files, scope obvious | tldrcrew-builder |
| New feature / 3+ files / cross-cutting refactor | Main thread or feature-dev:code-architect |
| Review diff, branch, or file for bugs | tldrcrew-reviewer |
| Deep code review with rationale + alternatives | Code Reviewer (vanilla) |
| One-line answer you already know | Main thread, no subagent |
Rule of thumb: if you'd want the subagent's output in 1/3 the tokens, pick tldrcrew. If you'd want prose, pick vanilla.
Subagent tool results get injected into main context verbatim. A vanilla Explore that returns 2k tokens of prose costs 2k tokens of main-context budget every time. The same finding from tldrcrew-investigator returns ~700 tokens. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task.
What main thread can rely on per agent:
tldrcrew-investigator
<Header>:
- path:line — `symbol` — short note
totals: <counts>.
Or No match. Always file-path-first, line-number-attached, backticked symbols. Safe to grep with path:\d+.
tldrcrew-builder
<path:line-range> — <change ≤10 words>.
verified: <re-read OK | mismatch @ path:line>.
Or one of: too-big. / needs-confirm. / ambiguous. / regressed. (terminal first token).
tldrcrew-reviewer
path:line: <emoji> <severity>: <problem>. <fix>.
totals: N🔴 N🟡 N🔵 N❓
Or No issues. Findings sorted file → line ascending.
Locate → fix → verify (most common):
tldrcrew-investigator returns site list.tldrcrew-builder.tldrcrew-reviewer audits the diff.Parallel scout (when investigation is broad):
Spawn 2-3 tldrcrew-investigator calls in one message (different angles: defs vs callers vs tests). Aggregate in main thread.
Single-shot edit (when site is already known):
Skip investigator. Hand exact path:line to tldrcrew-builder directly.
tldrcrew-builder when you don't already know the file. Spawn investigator first or main thread will eat tokens passing context.tldrcrew-investigator → tldrcrew-builder for a 5-file refactor. Builder will return too-big. and you'll have wasted a turn.tldrcrew-reviewer for "general feedback" — it returns findings only, no architecture opinions. Use Code Reviewer for that.Subagents drop TLDR → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume TLDR after.
npx claudepluginhub jqbit/tldr --plugin tldrDelegates tasks to compressed-output subagents (investigator, builder, reviewer) that save ~60% main-context tokens per delegation. Use instead of vanilla Explore/edit agents when context budget is tight.
Guides delegation to genshijin subagents (investigator for code locations, builder for 1-2 file edits, reviewer for diffs) instead of inline or vanilla Explore to compress outputs and save context tokens.
Runs cross-model code reviews using the external Codex CLI tool from a Claude session. Catches bugs that single-model self-review would miss by leveraging a different reviewer architecture.