transitive-bullshit/skills / skills/claude
claude
VerifiedUse Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude. Supports selecting `--model` and thinking/effort level with defaults of the current `opus` alias and `high`.
Claude
Claude Code is an independent agent on PATH (claude), sharing this working
tree and already authenticated. Use it as a second opinion or delegated worker,
not as ground truth: verify its claims, own any changes, and keep its task
contract narrow.
Defaults
Use claude -p --model opus --effort high unless the user or task calls for a
different model or thinking level. Keep opus as an alias so Claude Code
resolves the current Opus release; do not pin a dated model ID in this skill.
- Model: prefer aliases such as
opus,sonnet, orfable, which follow the current Claude releases. Accept a full model name only when the user or task requires that specific model, and verify it is current first. Defaultopus. - Thinking level: pass Claude Code's
--effortflag. Valid levels arelow,medium,high,xhigh, andmax. Defaulthigh. - Cost guard: for exploratory asks, add
--max-budget-usd <amount>when the user gives a budget or the task is likely to sprawl.
Example:
claude -p --model opus --effort high "<prompt>"
Prompting Claude
Prompt Claude like an operator: compact, block-structured, and explicit about the artifact you need. A sharper contract beats higher effort.
- One task per run. Split review, implementation, and docs into separate prompts.
- Name installed repo skills when relevant. Claude can read repo files; say "follow codebase-design for module boundaries" or "follow write-skills for the skill" instead of pasting those skills into the prompt.
- Blocks, added only where useful:
<task>— the concrete job, context, and expected end state.<output_contract>— exact response shape, highest-value first.<default_follow_through>— take low-risk interpretations and continue; stop only when a missing detail changes correctness, safety, or an irreversible action.<verification_loop>— inspect the result against requirements and revise before finalizing.<grounding>— ground every claim in code or tool output; label inferences.<action_safety>— keep the diff tightly scoped; no drive-by refactors.
- Anti-patterns: vague prompts, mixed jobs, no output contract, asking it to "think harder" instead of tightening the task, and accepting its answer without checking the evidence.
Consultation
Use Claude for consultation when the user asks for Claude's view or when a second-agent read from Claude is already authorized. Keep it read-oriented unless the user explicitly asks it to edit.
- Ask for evidence, not vibes: require file paths, observed behavior, command output, or labelled inferences.
- Prefer a read-only tool surface for reviews:
--tools "Read,Grep,Glob" --permission-mode dontAsk. - Never grant fewer tools than your output contract requires. Read your own prompt and ask which tool produces each claim you demanded. A judge that cannot run a command will still answer a question posed in numbers — with numbers, self-consistent and measured from nothing, and with the artifacts it says it wrote. Trimming the tool surface does not make the answer cautious; it makes the fabrication harder to spot. Either grant the tool or stop asking for the claim. Add command execution only within the authorized scope and the host’s normal approval controls; otherwise narrow the contract.
- Require the receipt with the number: any quantity in the response must arrive with the command that produced it and that command's output. Findings that fail this are struck, not discounted.
- Triage every finding against the code before acting. Report what Claude flagged, what you accepted, and what you dismissed.
Implementation — explicit ask only
Delegate implementation to Claude only when the user names Claude for the task. Keep delegation within the authorized task. In-scope follow-ups retain that authorization; ask again only when the proposed delegation expands its scope.
- Slice the task sharply: goal, constraints, allowed scope, and verification. An underspecified task stays with you until a fresh agent could not misread it.
- Start from a clean tree or record the baseline commit so Claude's diff is separable from yours. Tell Claude to keep scratch files (probes, dumps, notes) out of the tree — its diff must contain only the deliverable.
- Choose permissions by what the task must do:
- Read/review:
--tools "Read,Grep,Glob" --permission-mode dontAsk. - Narrow edits: add edit tools and keep the prompt's allowed paths explicit.
- Broader work: use a dedicated worktree and the host’s normal approval controls. If a required action is blocked, request the scoped permission through the host; do not bypass permission checks to complete the task.
- Read/review:
- Capture the response with
--output-format textby default. Use--output-format jsononly when the caller needs structured metadata. - You own the result: inspect the diff, run the relevant tests, and only then report it. "Claude says it's done" is not done.
Liveness
claude -p is a networked, authenticated non-interactive run. If it fails,
classify the failure before retrying.
- Auth failure: do not repair credentials unless the user asks; report the
blocker. If sandboxed
claude -psaysNot logged in, retry once with the required approval because local auth can depend on keychain/session access. - Sandbox/network failure: rerun with the required approval if the command is important to the task.
- Long run: prefer
--max-budget-usdor a narrower prompt before raising effort. - Workspace trust:
-pskips the interactive trust dialog, so run it only from a repo or worktree you intentionally trust.
Rules
- Use
claude -p --model opus --effort highas the default invocation; keep the alias unversioned so it follows the current Opus release. - Let the user override model and effort in plain language; translate that to
--modeland--effort. - Keep Claude's writes out of the working tree unless delegation was explicit.
- Do not touch the same working tree while Claude is making edits.
- Treat Claude output as evidence to verify, not authority to relay.
- Match the tool surface to the output contract; a claim shape you granted no tool for comes back invented.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |