openlore-implement-story

name: openlore-implement-story description: Implement a story on a brownfield codebase using openlore structural context. Runs orient + risk check before coding, validates against specs, enforces a test gate before drift check. license: MIT compatibility: openlore MCP server user-invocable: true allowed-tools: - ask_followup_question - use_mcp_tool - read_file - write_file - str_replace_based_edit - replace_in_file - run_command - openlore-execute-refactor

openlore: Implement Story

When to use this skill

Trigger this skill when the user asks to implement a story or task on a codebase that has openlore analysis available, with phrasings like:

• "implement story X"
• "work on task Y"
• "start implementing this feature"
• explicit command /openlore-implement-story

Prerequisite: openlore analysis must exist (openlore analyze has been run). If orient returns "error": "no cache" → run analyze_codebase first, then retry.

Step 1 — Read the story and risk context

Read the story file. Extract:

• $STORY_TITLE, $AC (acceptance criteria), $PROJECT_ROOT
• $RISK_CONTEXT — the risk_context section if present (pre-filled by Architect Agent)

Step 2 — Orient and assess risk

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>orient</tool_name>
  <arguments>{
    "directory": "$PROJECT_ROOT",
    "task": "$STORY_TITLE",
    "limit": 7
  }</arguments>
</use_mcp_tool>

For the top 2 functions returned, get minimal context first (callers, callees, body, test coverage):

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>get_minimal_context</tool_name>
  <arguments>{"directory": "$PROJECT_ROOT", "functionName": "$FUNCTION_NAME"}</arguments>
</use_mcp_tool>

What to read before proceeding:

• function.riskLevel — "high" = fanIn ≥ 30 or fanOut ≥ 15; tool expanded lists to 24 entries — all are blast-radius members.
• callers[*].callType — all "awaited" = async interface frozen; signature change breaks every caller silently in JS. Mixed = looser coupling.
• callees[*].isExternal: true — external boundary; new paths may pass mocked tests but fail in production.
• testedBy[*].confidence — "called" = direct test (strong). "imported" only = vi.mock() can neutralize; treat as untested.

If riskLevel is "high" or any callee is external, also check the cluster:

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>get_cluster</tool_name>
  <arguments>{"directory": "$PROJECT_ROOT", "functionName": "$FUNCTION_NAME"}</arguments>
</use_mcp_tool>

• clusterDensity < 0.05 → isolated, proceed
• clusterDensity 0.05–0.15 → check internalCallGraph for transitively dependent functions
• clusterDensity > 0.15 → dense cluster; coordinate scope with user first

Then check risk:

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>analyze_impact</tool_name>
  <arguments>{
    "directory": "$PROJECT_ROOT",
    "symbol": "$FUNCTION_NAME",
    "depth": 2
  }</arguments>
</use_mcp_tool>

If any function has riskScore ≥ 70: stop. Do not implement. Run /openlore-execute-refactor on the blocking function first, or create a blocking refactor task and return to this story once the risk is resolved.

Step 2.5 — Stack inventory (conditional)

Based on the story title and orient results, call the relevant inventory tool(s) before reading any source file. Skip if the story clearly involves none of these areas.

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>get_schema_inventory</tool_name>
  <arguments>{"directory": "$PROJECT_ROOT"}</arguments>
</use_mcp_tool>

Use the results to ground the implementation in existing schemas/routes — the plan cannot contradict what already exists.

Step 3 — Check the spec

First, verify that OpenSpec specs exist:

ls $PROJECT_ROOT/openspec/specs/ 2>/dev/null | wc -l

If 0 specs found:

No OpenSpec specs exist yet. search_specs will return empty results and check_spec_drift (Step 7) will flag everything as uncovered.

Recommended: run /openlore-generate after this story to create a spec baseline. You only need to do this once.

Continuing with structural analysis only.

Skip the search_specs call and go to Step 4.

If specs exist:

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>search_specs</tool_name>
  <arguments>{
    "directory": "$PROJECT_ROOT",
    "query": "$STORY_TITLE",
    "limit": 5
  }</arguments>
</use_mcp_tool>

If relevant requirements are found, read the domain spec before writing any code. Note any constraints that apply.

Step 3.5 — Audit spec coverage of the target domain

Run a parity audit to check if the domain you're about to touch has spec gaps.

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>audit_spec_coverage</tool_name>
  <arguments>{"directory": "$PROJECT_ROOT"}</arguments>
</use_mcp_tool>

From the result, check:

• staleDomains — if the target domain appears here, its spec is outdated. Recommend running openlore generate --domains $DOMAIN before implementing.
• hubGaps — uncovered hub functions. If the feature touches one of these, add it to the adversarial check in Step 4b (high blast radius + no spec = risk).

If both are clean, continue to Step 4 without action.

Step 4 — Find the insertion point

Use insertion_points from risk_context if present. Otherwise:

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>suggest_insertion_points</tool_name>
  <arguments>{
    "directory": "$PROJECT_ROOT",
    "description": "$STORY_TITLE",
    "limit": 5
  }</arguments>
</use_mcp_tool>

Read the skeleton of the target file:

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>get_function_skeleton</tool_name>
  <arguments>{
    "directory": "$PROJECT_ROOT",
    "filePath": "$TARGET_FILE"
  }</arguments>
</use_mcp_tool>

Confirm the approach with the user before writing code.

Step 4b — Adversarial challenge

Before writing any code, state explicitly what could break with this approach. If .claude/antipatterns.md exists, read it and include any applicable patterns.

"Risk check on $INSERTION_POINT:

• $CALLER_A and $CALLER_B depend on this function — verify their assumptions hold after the change.
• $EDGE_CASE is not covered by the current test suite — add it in Step 6.
• [if antipatterns apply] AP-NNN ($PATTERN_NAME) — $RULE — applies here because $REASON."

This is not a gate — do not wait for user input. It is a mandatory self-check that must appear in the output before the first line of code is written.

Step 4c — Record the design decision

Before writing any code, record the implementation approach if it represents a significant architectural choice:

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>record_decision</tool_name>
  <arguments>{
    "directory": "$DIRECTORY",
    "title": "$APPROACH_TITLE",
    "rationale": "$WHY_THIS_APPROACH",
    "consequences": "$TRADE_OFFS",
    "affectedFiles": ["$TARGET_FILE"]
  }</arguments>
</use_mcp_tool>

Call this for: a non-obvious insertion point, a pattern chosen over alternatives, a new dependency introduced, or an interface contract established. Skip for trivial changes where the approach is self-evident.

Step 5 — Implement

Apply changes in this order:

1. New types/interfaces (if needed)
2. Core logic at the insertion point
3. Updated call sites (if any)

Do not touch functions outside the scope identified in Step 2 / risk_context without re-running the gate.

Small model constraint: if the model is under 13B parameters (Mistral Small, Phi, Gemma…), each edit must touch a contiguous block of at most 50 lines. Split larger changes.

Step 6 — Tests

Both levels required before proceeding to Step 7.

Mandatory — existing tests must not regress: Run the full test suite. If any pre-existing test breaks, fix the regression before continuing.

Recommended — at least one new test per AC: Write a test that directly exercises the behaviour described in the acceptance criterion.

Step 7 — Verify drift

Only run once tests are green.

<use_mcp_tool>
  <server_name>openlore</server_name>
  <tool_name>check_spec_drift</tool_name>
  <arguments>{"directory": "$PROJECT_ROOT"}</arguments>
</use_mcp_tool>

Absolute constraints

• Do not write code before Step 4 confirmation
• If riskScore ≥ 70 — stop, do not work around it, run /openlore-execute-refactor first
• Do not run check_spec_drift before tests are green
• Do not propose a spec update on untested code