investigate

A bug-investigation workflow that explores several possible causes at the same time using separate agents.

In plain words
What is it for?
It helps gather context from a written problem, Slack messages, or Linear issues, test three to five hypotheses, and report which explanations were supported or rejected.
Why use it?
It reduces the chance of focusing too early on one suspected cause and helps compare competing explanations for a problem.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/rilldata/rill/investigate
Any agent
npx skills add rilldata/rill --skill investigate
Clone the repo
git clone --depth 1 https://github.com/rilldata/rill

Made for: Claude Code, Codex.

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00302
Opus 5 $0.00005 $0.00151
Sonnet 5 $0.00002 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 2d ago against content hash 9f1321dfb4e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

investigate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/investigate/SKILL.md · 33 lines

What it actually says

Investigate a bug by gathering context, then spawning parallel Task agents to test multiple hypotheses simultaneously.

Input: $ARGUMENTS

Instructions

1. Gather Context

Parse the input for links and fetch context:

  • Slack link (contains slack.com/archives): Fetch the message and thread replies via Slack MCP tools
  • Linear issue (ID like ENG-1234 or URL): Fetch via mcp__linear__get_issue, including comments and attachments
  • Free text: Use directly as the problem statement

User-provided hunches should be prioritized when forming hypotheses.

2. Investigate in Parallel

Generate 3-5 hypotheses, then use the Task tool to spawn one agent per hypothesis in a single message (parallel, not sequential). For each agent:

  • subagent_type: "Explore", model: "sonnet"
  • A focused prompt with the hypothesis, what to look for, and what would confirm or refute it

3. Synthesize

After all agents complete, report: which hypotheses were confirmed, refuted, or inconclusive, and recommend next steps.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 33 lines · 11 tokens per session scan A 9f1321dfb4e5

Subscribe to this mod's changes

investigate is a skill published in the GitHub repository rilldata/rill (2,859 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 302 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

hardwood-pr-git

Rebase, rewrite, squash, reword and push Hardwood PR history — including contributor PRs whose author and committer identity must survive the rewrite. Use whenever the user asks to "rebase", "rebase onto main", "fix the commit message", "prefix with the issue key", "squash the commits", "force push (with lease)"…

hardwood-hq/hardwood · 163 tokens

hardwood-cli

Inspect, debug, and convert Apache Parquet files with the hardwood CLI. Use whenever a user is debugging code that reads or writes Parquet (Arrow / Spark / Flink / Java / Python) and the data file itself may be the cause — to check the schema, physical and logical types, repetition, or a row sample. Use it to diagnose…

hardwood-hq/hardwood · 216 tokens

hardwood-review

Review a Hardwood PR, local branch, or staged diff against the project's CLAUDE.md conventions and recurring failure modes. Use whenever the user asks to "review", "look over", "check", "audit", or "assess" a PR number, a branch, or pending changes in the hardwood-hq/hardwood repo. Also use when the user pastes a PR…

hardwood-hq/hardwood · 102 tokens

hardwood-address-review

Work through a reviews/pr- -review.md findings file against a Hardwood PR — check out the PR branch, make the fixes, surface each Decision with its options + recommendation for the maintainer to pick, tick off addressed items in the review file, and commit (do not push). Use whenever the user says "address review for.

hardwood-hq/hardwood · 75 tokens

parquet-dev-ml

Search the Apache parquet-dev mailing list by downloading the raw monthly mbox archives from lists.apache.org and grepping them locally. Use whenever the user wants to find, read, or quote a thread on the Parquet dev list ([email protected]) — e.g. "search the parquet-dev ML", "find the thread about X on the…

hardwood-hq/hardwood · 117 tokens

exasol-import-export

Exasol IMPORT and EXPORT SQL statements: syntax, file formats (CSV, FBV, Parquet), cloud storage (S3, Azure, GCS), connection objects, error handling, and ETL staging patterns.

exasol/mcp-server · 49 tokens