Why

Investigate the motivation and intent behind code. Why was it built this way? What edge cases were considered? What product, business, or operational constraints shaped the design? What alternatives were rejected, and why?

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

How this skill works

Historical context spreads across seven evidence categories: source control history, issue or ticket tracking, long-form documents, real-time team chat, infrastructure observability, error or exception tracking, and product analytics warehouses. You cannot predict from the question alone which one holds the answer, so the skill enumerates available MCPs at run time, maps each to a category, queries all seven in parallel, then synthesizes with explicit confidence calibration. Null results from searched categories are first-class evidence about how the decision was made; report them alongside positive findings. The default is coverage, not minimalism.

Operating Posture

Operate as a careful, cautious, precise investigator. Think like a detective piecing together a historical case from fragmentary records. When the record is thin, say so.

Concretely:

• Evidence before narrative. Collect the pieces first, then see what story they support. Never pick a story and recruit the evidence that fits it.
• Precision over polish. Prefer the exact quote and citation over a smooth paraphrase. A reader should be able to follow any claim back to its source and verify it in under a minute.
• Consider what you haven't seen. The evidence you find is a sample, not the whole truth. Before concluding, ask what you would expect to see if an alternative explanation were true, and whether you looked for it.
• Name the gaps. If a thread goes cold, a source isn't searchable, or a question has no answer, document the gap. Don't paper it over with an authoritative-sounding guess.
• Hedge on purpose. When evidence is indirect, your language should signal it ("appears to", "likely", "suggests"). Confidence-matching phrasing is a feature of the output, not a stylistic choice the synthesizer may override.
• No shortcut by code-reading. The code tells you what it does, rarely why it exists. Resist inferring intent from code shape.

This posture is the working method, not a disclaimer.

Core Epistemics

This skill builds a patchwork understanding from fragmented historical evidence. Tickets go stale. Chat threads get deleted. Commit messages lie. People change their minds between the PR description and the implementation. The original author may have left the company.

Be ruthlessly honest about what you know versus what you're inferring. The goal is not a satisfying story; it is to surface evidence, calibrate confidence, and let the user decide.

Principles:

• Cite everything. Every claim about intent should reference a specific commit hash, PR number, ticket ID, doc URL, chat permalink, or code comment. If you can't cite it, it's inference, not fact, and must be labeled as such.
• Prefer "appears to" over "because". Hedge when evidence is indirect. Reserve confident language for direct, explicit evidence.
• Surface contradictions. If two sources disagree, show both. Don't quietly pick the one that fits your narrative.
• Acknowledge gaps. If a question has no answer in any source you searched, say so. An honest "we couldn't find out why" beats a confident guess.
• Multiple hypotheses are valid. When the evidence fits several stories, present them all with the evidence for each. Let the user triangulate.
• Beware rationalization. Code that makes sense today may have been written for reasons that no longer apply, or for no good reason at all. Don't retrofit intent.

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 one of:

• "Why was X designed this way?" Design rationale.
• "Why do we do X instead of Y?" Tradeoff or alternatives.
• "What edge cases motivated this?" Defensive reasoning.
• "What business or product constraint led to this?" External forcing function.
• "Why does this code still exist?" Dead-code territory.
• "What's the history of X?" Broad archaeological 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, the code location under discussion, and 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 running the investigations, anchor them 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. It is cheap, and every repository specialist and MCP query needs it.

# 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:

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). Include it in delegated tasks and MCP queries so each search starts from the same anchor.

Step 3. Run Parallel Investigations (default posture)

Default to broad evidence coverage. Each category lives in a different system, and the question alone does not reveal which source contains the rationale. Search every available category independently and run unrelated searches concurrently.

Discover Atomic agents and MCP servers

Before delegation, list executable Atomic specialists. Do not invent an agent or pin a model:

subagent({ action: "list" })

Keep each listed agent's declared model and fallback policy unless the user explicitly requests an available override.

Inspect Atomic's MCP status, then list or search its lazily discovered tool metadata:

mcp({})
mcp({ server: "<server-name>" })
mcp({ search: "issue ticket docs chat observability errors analytics" })

Use mcp({ connect: "<server-name>" }) only when metadata is stale or the server must authenticate/connect before use. Use mcp({ describe: "<tool-name>" }) to inspect a tool's schema, then call it with a JSON string:

mcp({ tool: "<tool-name>", args: "{\"query\":\"<target symbols, commits, PRs, and dates>\"}" })

Map each available MCP server or tool to one evidence category:

1. Source control history
2. Issue / ticket tracker
3. Long-form documents
4. Real-time team chat
5. Infrastructure observability
6. Error / exception tracking
7. Product analytics warehouse

Source control is always available through git and gh. Classify configured MCPs using server names, tool descriptions, and resource schemas. If one server fits several categories, run a separate query per category and record the overlap in the coverage map.

Aim for a complete coverage map, not a minimal one. A null result from a searched source is evidence about the decision record; document it rather than skipping the search.

Delegate repository exploration with Atomic specialists

Use Atomic's focused exploration agents for repository evidence:

subagent({
  tasks: [
    { agent: "codebase-analyzer", task: "Investigate the source-control rationale for <question>. Use the supplied code anchor; inspect git blame/log, commits, PR metadata available through gh, comments, and tests. Return exact citations and null results. Do not edit." },
    { agent: "codebase-research-locator", task: "Find local research, specs, ADRs, and decision records relevant to <question> and the supplied code anchor. Return ranked paths, dates, and supersession notes. Do not edit." }
  ],
  concurrency: 2,
  context: "fresh"
})

If the locator finds relevant documents, follow with codebase-research-analyzer to extract current decisions, constraints, contradictions, and exact file citations. Use codebase-online-researcher only when public web evidence is part of the question. Use only agents returned by subagent({ action: "list" }).

Query MCP-backed categories from the parent

Atomic's built-in repository specialists do not automatically receive every configured MCP tool. Query each matching MCP category from the parent with mcp({ tool, args }), issuing independent calls concurrently when possible. Build each query from:

1. The base method in references/investigator-prompt.md
2. The category playbook in references/sources/<source>.md, adapted through references/source-playbook.md
3. references/sources/incident-postmortem.md when the target looks defensive
4. The code anchor from Step 2
5. The user's original question

If subagent({ action: "list" }) shows a project-specific investigator that explicitly has the required MCP access, it may own that category instead. Otherwise keep the MCP call in the parent; do not invent an agent, a tool name, or a model.

Investigation roster. One independent search per available evidence category

Run one independent investigation per category that has a matching source. Keep each query scoped to one evidence system so its vocabulary, result shape, and null result remain auditable.

Each entry lists what the category physically contains 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. Every category overlaps, but each owns a kind of evidence the others cannot recover.

1. Source control investigation. Git history, gh for PRs, code comments, tests. Always run it, normally with codebase-analyzer; it is the only guaranteed source. Best at surfacing implementation-time rationale captured during review. PR descriptions stating the problem, review threads debating alternatives, inline comments encoding non-obvious constraints, test names that encode motivating edge cases, and commit messages linking tickets or incidents. Most trustworthy because it ties directly to the diff that shipped.

2. Issue / ticket tracker investigator (e.g. Linear, Jira, GitHub Issues, Plane, Shortcut MCP). Tickets, project docs, status updates, spec attachments. Best at surfacing the product or business forcing function. Customer requests ("Acme needs X for their SOC2 audit"), compliance deadlines, parent-initiative framing ("Q3 enterprise readiness"), ticket-level scope changes, and labels that categorize the motivation (customer:*, incident-followup, compliance, perf-regression). Strongest when the why is external to engineering.

3. Long-form documents investigator (e.g. Notion, Confluence, Google Docs, Coda MCP). PRDs, specs, RFCs, design docs, ADRs, postmortems, team pages, meeting notes. Best at surfacing long-form design rationale. Problem statements, explicit "alternatives considered" and "rejected approaches" sections, strategy documents that set priorities, ADRs with finalized decisions, and postmortem action items that tie directly to code. Where the why is written out before it becomes code.

4. Real-time team chat investigator (e.g. Slack, Discord, Microsoft Teams, Mattermost MCP). Feature-name and symbol searches, PR URL mentions, incident channels (#sev-*, #incident-*), author-handle activity around the ship date. Best at surfacing real-time deliberation that never reached a doc. Fire-drill decisions during incidents, Q&A between the PR author and reviewers, casual "we decided X because Y" threads, and rationale for small changes that didn't warrant a PRD. Especially important when the source control, ticket, and doc paper trail is thin.

5. Infrastructure observability investigator (e.g. Datadog, New Relic, Honeycomb, Grafana, Splunk MCP). Metrics, monitors, dashboards, logs, APM traces, formal incidents. Infra/runtime view. Best at surfacing infrastructure and runtime reality that motivated the code. Monitor thresholds whose numbers match code constants, metric spikes in the window right before a PR merge, dashboards created as postmortem action items, incident timelines that reference the target. Strongest when the target reacts to an infra signal (timeouts, retries, rate limits, circuit breakers).

6. Error / exception tracking investigator (e.g. Sentry, Rollbar, Bugsnag, Airbrake MCP). Issues, events, stack traces, releases. Best at surfacing the specific exceptions and error trajectories that motivated defensive or corrective code. Stack traces that pass through the target function, issues whose first-seen/last-seen windows bracket the PR ship date, release correlations that show an error stopping at a specific version. Strongest for catch blocks, null guards, type checks, retries, and other defenses.

7. Product analytics warehouse investigator (e.g. Databricks, Snowflake, BigQuery, ClickHouse, dbt, Redshift MCP). Product-analytics events, experiment and feature-flag exposure tables, usage and billing events, query history, warehouse telemetry. Product/data view. Complements infrastructure observability by covering user behavior and data reality around the ship date rather than infra metrics. Best at surfacing product and data reality that shaped the code. Feature-usage trajectories (a step-function ramp from zero is strong evidence that this PR launched it), experiment/flag exposure data tied to ship decisions, pre-ship distributions that reveal where a threshold constant came from (e.g., limit = 128 * 1024 matching the p99 of an upload-size column), and data-pipeline scale evidence for migrations/backfills. Strongest for flag-gated code, experiment-driven ships, data migrations, and "where did this number come from" questions.

When to skip an investigation

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: "Real-time team chat skipped. No matching MCP available, so the conversational record 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." Not "probably not in error tracking, it's a feature not an error."

"It's pure feature code, error tracking won't have anything" is not sufficient, and neither is "I doubt long-form docs would have this." Run the search; let the null result speak. An empty query is cheap. Missing a design record that exists produces a wrong answer.

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 all seven available category searches would be redundant. Say so explicitly. This should be rare.

Step 4. Synthesize

Synthesize the collected evidence in the parent session. The parent retains orchestration and final-answer authority, so no generic synthesizer agent is needed.

Use:

1. The repository-specialist findings and MCP results, including null results and justified skips
2. The code anchor from Step 2
3. The user's original question
4. The epistemics framework from references/epistemics.md
5. The structure and checks from references/synthesizer-prompt.md

Produce a confidence-weighted, evidence-cited narrative with clearly separated direct evidence and inference, plus honest acknowledgment of gaps and null-result sources. Spot-verify critical citations yourself with the relevant repository or MCP tool before presenting them.

Step 5. Present

Present the parent synthesis to the user. You may lightly edit for clarity or add context from the conversation, but do not rewrite the confidence language. The epistemic framing is the product. Dropping the hedges to sound more authoritative is the exact failure mode this skill exists to prevent.

Output Format

The final output uses this structure. Adapt as needed, but keep the confidence separation intact.

The Question. Restate what the user asked, concisely.

The Code in Question. File paths, line ranges, and key symbols. One or two lines so the reader is anchored.

What We Found (direct evidence). Claims with explicit citations (PR #, ticket ID, doc URL, chat permalink, commit hash, code comment with file:line). Each bullet is a thing we have textual evidence for. Use present tense and quote or paraphrase the source.

What We Can Reasonably Infer. Claims well-supported by indirect evidence or combinations of signals, but not explicitly stated anywhere. Each bullet must explain the inference chain: "Given A and B, it's likely that C." Use hedged language ("appears to", "likely", "suggests").

Competing Hypotheses. If the evidence fits multiple stories, list them. For each, give the hypothesis, the evidence for it, and the evidence against it. Don't force a winner when the record doesn't support one. (Skip this section if there's a clear answer.)

What We Don't Know. Explicit gaps. Questions the user asked that the evidence didn't answer. Sources we searched and came up empty. Be specific. "We searched the issue tracker for 'rate limit' and found no ticket discussing this specific threshold" is more useful than "we don't know why."

Sources Consulted. One line per independent source search, including those that returned nothing. The reader should see at a glance (a) which MCPs or repository sources were queried, (b) which came back empty, and (c) which were skipped and why. This coverage map lets the user judge breadth and redirect if something obvious was missed.

Format each line as: - <Source>: <what was searched>. <what was found, or "no relevant results," or "skipped. reason">.

Example:

• Source control (git/gh): git log --follow backend/retry.ts, PRs #49074, #47812. Found PR #49074 introduced exponential backoff and linked ENG-4421.
• Issue tracker (Linear): searched for "retry" and ENG-4421. Found ENG-4421 parent issue but no discussion of backoff parameters.
• Long-form docs (Notion): searched for "retry policy," "backend retries," "ENG-4421." No relevant results.
• Real-time team chat (Slack): skipped. No matching MCP available in this environment. Gap: conversational record not searched.
• Infrastructure observability (Datadog): searched for retry_count metric and monitors around 2024-08-14. Found monitor "Upstream 5xx rate > 1%" created same day as PR #49074.
• Error / exception tracking (Sentry): searched for issues first-seen in Aug 2024 with stack through retry.ts. Found issue SENTRY-3821 spiking in the week before the PR.
• Product analytics warehouse (Databricks): queried <your_analytics_db>.<schema>.stg_backend_upstream_retry for the 30-day window around 2024-08-14. Daily failure-classified event count fell from ~1.2k/day pre-PR to <50/day post-PR. Also checked system.query.history for relevant migration queries. None found.

After the Sources Consulted block, if the user's why question is a precursor 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

• Confident storytelling. A plausible narrative built from thin evidence. A bullet with no citation goes in "inferred" or "hypotheses," not "what we found."
• Citing the code as evidence for its own intent. "Handles the null case because it checks for null" is mechanics, not motivation. Motivation comes from an external source (PR discussion, ticket, comment, conversation) or is labeled as inference.
• Recency bias. Assuming the most recent commit is authoritative. The current shape is often the accretion of many earlier decisions. Trace back.
• Sycophantic agreement. If the user suggests a reason ("I assume this is for performance?"), treat it as a hypothesis and check the evidence independently, don't just confirm it.
• Skipping the gaps section. An honest accounting of what you couldn't find out is part of the value.
• Skipping investigations by anticipation. Deciding up front that "long-form docs probably don't have this" or "this isn't an error tracking thing" without searching. The default-to-all-seven posture prevents this. A null result is a data point; a skipped search is a blind spot.
• Collapsing all searches into one vague task. Each evidence system has its own query vocabulary, result shape, and pitfalls. Keep one independent query per category, using Atomic repository specialists for local evidence and parent-side mcp(...) calls for configured external systems.

Reference Files

• references/epistemics.md. Confidence tiers and phrasing guide. The parent synthesis must follow it.
• references/investigator-prompt.md. Base query method for independent evidence investigations.
• references/source-playbook.md. Index pointing at the category playbooks below.
• references/sources/*.md. One self-contained example playbook per category, plus cross-cutting incident-postmortem.md. Apply the matching file to that category's Atomic specialist task or parent-side MCP query.
• references/synthesizer-prompt.md. Prompt template and quality checks for the parent synthesis.