Tldrcrew
Decision guide for delegating to tldr-style subagents. Tells the main thread WHEN to spawn `tldrcrew-investigator` (locate code), `tldrcrew-builder` (1-2 file edit), or `tldrcrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is tldr-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use tldrcrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".From its SKILL.md
npx -y skills add 0p9b/TLDR --skill tldrcrewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 22 stars22 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.8 KB, as published. Nobody here has run it
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.
When to use tldrcrew vs alternatives
| 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.
Why this exists (the real win)
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.
Output contracts
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.
Chaining patterns
Locate → fix → verify (most common):
tldrcrew-investigatorreturns site list.- Main thread picks 1-2 sites, hands paths to
tldrcrew-builder. tldrcrew-revieweraudits 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.
What NOT to do
- Don't use
tldrcrew-builderwhen you don't already know the file. Spawn investigator first or main thread will eat tokens passing context. - Don't chain
tldrcrew-investigator → tldrcrew-builderfor a 5-file refactor. Builder will returntoo-big.and you'll have wasted a turn. - Don't ask
tldrcrew-reviewerfor "general feedback" — it returns findings only, no architecture opinions. UseCode Reviewerfor that. - Don't expect prose. tldrcrew output is structured, sometimes terse to the point of cryptic. If a human will read it directly, paraphrase.
Auto-clarity (inherited)
Subagents drop TLDR → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume TLDR after.