why

Files (7)

• SKILL.md
• epistemics.md · references/
• investigator-prompt.md · references/
• source-playbook.md · references/
• code-archaeology.md · references/sources/
• incident-postmortem.md · references/sources/
• synthesizer-prompt.md · references/

SKILL.md (first lines)

# Why

Investigate the motivation and intent behind code.

Companion to the `how` skill. `how` answers what the code does and how it works. `why` answers what forces led to its shape.

Spawn investigators with `subagent_type: why-investigator` (Claude Code: `Agent` tool; OpenCode: `task` tool). Models come from that agent definition; never pass `model`. Subagents cannot spawn subagents, so run this skill from the primary agent. If a `why-synthesizer` agent is installed, spawn it to merge the reports. If it is not installed, synthesize in this session.

## Operating Posture

Operate as a **careful, cautious, and precise investigator**. Be honest about what you know vs what you're inferring. Read `references/epistemics.md` for the full confidence framework and phrasing guide. The synthesizer must follow it.

## Step 1. Understand the Target and the Question

Parse what the user is asking. The **target** is usually a chunk of code, a pattern, a feature, or a named design decision. The **question** is usually a design rationale, a tradeoff, a motivating edge case, an external constraint, dead code, or a broad history sweep.

If the target is vague ("why do we do it this way?" with no clear referent), make your best guess from conversation context (open files, recent edits, selection, what was just discussed). State your interpretation briefly so the user can redirect if you're off, then proceed.

## Step 2. Establish the Code Anchor

Before spawning investigators, anchor the investigation in concrete code. You need:

- The relevant file path(s) and line range(s)
- The key symbols (function names, class names, constants)
- An initial commit list. The last few commits touching the target.
- PR numbers from merge commits (pattern `(#1234)` in the subject line)

Build this inline. If you cannot run shell commands (e.g. OpenCode conductor has bash denied), spawn one `why-investigator` for source control first to build the code anchor, then fan out.

```bash
# Blame target lines for last-touch commits
git blame -L <start>,<end> <file>

# Full file history, with patches, through renames
git log --follow -p -- <file>

# Last N commits touching the file, PR numbers visible
git log --oneline -20 -- <file>

# Extract PR numbers from a commit message
git log -1 --format=%B <commit>
```

Pull PR bodies and discussion via `gh` for any substantive commits:

```bash
gh pr view <number> --json title,body,author,createdAt,mergedAt,labels,closingIssuesReferences,comments,reviews
```

Capture this as seed context (file paths, symbols, commits, PR numbers, linked ticket IDs). Pass it to the investigators.

## Step 3. Spawn Parallel Investigators (default posture)

**Default to the full parallel investigation.**

### Discovery

Before spawning investigators, list the MCP tools available in this session.

Map each available MCP to one evidence category:

1. Source control history

Source control is always available through git and `gh`. For any other MCP, classify using the MCP name, server instructions, tool names, and resource descriptors. If an MCP could fit more than one category, choose the one matching its primary evidence. Record ambiguous cases in the coverage map. Any other MCP found in the session that holds historical evidence (tickets, docs, telemetry) may still be investigated as its own category.

Aim for a complete **coverage map**, not a minimal one. Document the null, don't skip the search.

Launch all matching investigators in a single message so they run concurrently. Don't ask one agent to cover multiple MCPs.

Spawn each with `subagent_type: why-investigator`. Investigators **MUST NOT** write anything.

Each investigator gets:

1. The base prompt from `references/investigator-prompt.md`
2. The category playbook `references/sources/<source>.md` for the selected MCP, adapted from the examples in `references/source-playbook.md`
3. The cross-cutting `references/sources/incident-postmortem.md` **if the target code looks defensive** (null checks, retry logic, timeout handling, rate limiting, feature flags, egress guards, OOM handlers)
4. The code anchor from Step 2 (file paths, symbols, commit hashes, PR numbers, ticket IDs)
5. The user's original question

### Investigator roster. One per available evidence category

Spawn one investigator per category that has a matching MCP. Each owns exactly one tool or MCP.

Each entry names the category and the kind of "why" it uniquely surfaces. Use it to know what to expect back, how to name a gap when a category returns empty, and (only in the rare provably-irrelevant case) to justify a skip.

1. **Source control investigator**. Git history, `gh` for PRs, code comments, tests. Always spawn. The only guaranteed source. Best at surfacing _implementation-time rationale captured during review_.

### When to skip an investigator

Only skip with an **explicit, written justification** that goes in the final "Sources Consulted" section. Two valid reasons:

- **No MCP is available for that category** in this environment. Flag this as a gap, not a choice. Example: "Ticket tracker skipped. No matching MCP available, so the ticket history was not searchable."
- **The source is provably irrelevant**, not just "probably irrelevant." A high bar. Example: "Error / exception tracking skipped. Target is a build-time script with no runtime code path."

If your scope assessment suggests a single-commit trivial target where the PR description already contains the complete answer, you may answer inline **only after** confirming the other category searches would be redundant. Say so explicitly. This should be rare.

## Step 4. Synthesize

If a `why-synthesizer` agent is installed, spawn it with `subagent_type: why-synthesizer`. If that agent is not installed, write the synthesis in this session. Do not invent a synthesizer subagent. Either way, use `references/synthesizer-prompt.md` and give the synthesis:

1. The investigator findings, including any null results and any categories skipped with justification
2. The code anchor from Step 2 (file paths, symbols, commit hashes, PR numbers, ticket IDs)
3. The user's original question
4. The epistemics framework from `references/epistemics.md`
5. The synthesizer prompt template from `references/synthesizer-prompt.md`

## Step 5. Present

Present that synthesis to the user. You may lightly edit for clarity or add context from the conversation, but **do not rewrite the confidence language**.

## Output Format

The output structure is the one in `references/synthesizer-prompt.md`: The Question, The Code in Question, What We Found, What We Can Reasonably Infer, Competing Hypotheses, What We Don't Know, Sources Consulted, Confidence Summary. Adapt as needed, but keep the confidence separation intact, and keep Sources Consulted as one line per investigator, including the ones that returned nothing or were skipped, with the reason.

After the Sources Consulted block, if the user's `why` question is a prelude to actually changing this code, convert the lineage findings into a Preserve / Change / Avoid / Risk constraint set suitable for planning the change.

## Common Failure Modes to Avoid

- **Recency bias**. Assuming the most recent commit is authoritative. The current shape is often the accretion of many earlier decisions. Trace back.

From fmflurry/settings-opencode, MIT.

More from fmflurry/settings-opencode