investigate-first
Diagnose ambiguous failures before editing.
Skill by JuliusBrussee
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/juliusbrussee-investigate-first
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, debugging
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/investigate-first
What's inside
- Skill name
investigate-first- Description
- Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
- License
- Apache-2.0
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Investigate first Gather evidence before changing product code. - Separate observed symptom from inferred cause. - Trace inputs, state transitions, ownership boundaries, and failure output. - Rank hypotheses by evidence and cheap falsification value. - Do not edit until one credible mechanism explains evidence. - Stop exploration when evidence is sufficient to name cause or exact blocker. Report cause and proof. Make no fix unless task authorizes implementation.
From JuliusBrussee/caveman, Apache-2.0.
More from JuliusBrussee/caveman
- 0.888score
caveman-compress
JuliusBrussee
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-learn
JuliusBrussee
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-manage
JuliusBrussee
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-optimize
JuliusBrussee
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-evidence-review
JuliusBrussee
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
cavecrew
JuliusBrussee
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline…
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
megacave
JuliusBrussee
Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-commit
JuliusBrussee
Write a Conventional Commits message compressed to intent only.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-review
JuliusBrussee
Compressed code review - one line per finding with location, problem and fix.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-setup
JuliusBrussee
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-explore
JuliusBrussee
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-discover
JuliusBrussee
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket.
SkillAFreshness: A★ 114.8KClaude Code +9
Signals
- Stars
- 114,786
- Forks
- 6,616
- Open issues
- 64
- Last commit (this folder)
- Aug 11, 2026 (2 months ago)
- Last release
- Oct 13, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/JuliusBrussee/caveman
- Website
- docs.caveman.so/caveman
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.331score
investigate-first
striges88-bit
Diagnose ambiguous failures before editing.
SkillAFreshness: AClaude Code +9 - 0.310score
investigate-first
quyenanh198
Diagnose ambiguous failures before editing.
SkillBFreshness: BClaude Code +9 - 0.307score
investigate-first
matinz03
Diagnose ambiguous failures before editing.
SkillBFreshness: BClaude Code +9 - 0.307score
investigate-first
veronoicc
Diagnose ambiguous failures before editing.
SkillBFreshness: BClaude Code +9
More from JuliusBrussee
- 0.888score
caveman-compress
JuliusBrussee
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-learn
JuliusBrussee
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-manage
JuliusBrussee
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-optimize
JuliusBrussee
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-evidence-review
JuliusBrussee
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
cavecrew
JuliusBrussee
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline…
SkillAFreshness: A★ 114.8KClaude Code +9
Cite this page
investigate-first skill. Agent Mart. https://agentmart.dev/skills/juliusbrussee-investigate-first (last updated 2026-10-24)