memtrace-first

name

memtrace-first

description

Route code discovery, debugging, flow tracing, how-code-works questions, and pre-edit rationale checks in indexed source-code repos to Memtrace graph plus Cortex decision tools. Use first before searching/reading code, and before editing, refactoring, deleting, or re-picking an approach that may have a recorded decision, ban, convention, or contract. Do not use Grep, Glob, rg, find, or manual file browsing for code discovery when Memtrace is indexed. Zero results are not permission to grep; diagnose/reindex with Memtrace.

Memtrace First

The Iron Law

IF THE REPO IS INDEXED IN MEMTRACE → USE MEMTRACE TOOLS FIRST.
After a search hit, route to GRAPH tools (get_symbol_context, get_impact,
analyze_relationships) — that's what Memtrace uniquely provides. Read source
ONLY when you're about to edit or quote, and read only the bounded span
returned by Memtrace (start_line .. end_line + small context). Do not
Grep/Glob/Find to "locate" anything already in the graph, and do not read
the whole file when Memtrace has given you exact lines.

BEFORE you edit/refactor/delete existing code or choose/re-pick a pattern,
call Cortex decision memory: recall_decision for the symbol/subsystem/approach,
and use provenance/contracts when a symbol_id is available. Use Memtrace's graph
tools for structure and blast radius; use Cortex for rationale, bans, and
contracts.

Memtrace is the memory layer of the codebase, not a search engine that returns code. It has the full knowledge graph — every symbol, call, import, community, process, and API — with a time dimension. The point is to navigate that graph: who calls this, what's the blast radius, when did this change, what community is it part of. File tools are blind to all of that.

No exceptions for what's in the graph.

Value Tracking

Do not print usage receipts in normal answers. Memtrace records tool usage, graph facts, file references, and estimated context avoided internally. Users can inspect that in the local UI's Value panel.

What Memtrace actually indexes

Memtrace's hybrid search = BM25 over symbol metadata (name, signature, file_path, kind) + semantic vector search over embedded code bodies (first ~1500 chars of every Function / Method / Class / Struct / Interface body), fused via Reciprocal Rank Fusion.

The semantic side means string literals, error messages, magic constants, log strings, and any text inside an indexed symbol's body are findable through find_code. The body got embedded; the embedding catches it. You do NOT need Grep to hunt for STRIPE_KEY_FOO_BAR if it lives inside a function in your indexed codebase.

Zero results are not a grep license

If Memtrace returns 0 results, or repository stats look incomplete, do not infer that a source subdirectory is outside the index. Diagnose through Memtrace:

1. Call list_indexed_repositories and identify the repo root/repo_id.
2. If the path is under that indexed repo root, keep using Memtrace.
3. Retry with broader find_code terms and, when available, file_path filters such as ui/, memtrace-ui/, src/, or the framework directory.
4. If the language/path still appears missing, run index_directory on the repo root with incremental: true (or ask before clear_existing: true).
5. Report the indexing coverage problem instead of silently switching to grep.

Workspace Boundary Check

Before indexing or reindexing, make sure the target path is the repo the user asked about. If the current folder is only a parent that contains multiple independent git repos, do not index the parent just because it is the open editor folder. That creates or reuses a shared .memdb and can make agents answer from stale repos.

• For separate repos: use the actual git repo root as the index_directory path, or ask the user to open/run the agent from that repo root.
• For an intentional shared workspace: the user should bless it explicitly with memtrace start --bless-workspace, then verify it with memtrace workspace status <path>; the workspace marker should be present.
• If list_indexed_repositories returns empty or its metadata says the MCP child resolved a data dir from cwd because no workspace marker/git root was found, surface the workspace mismatch. Do not "fix" it by indexing the broad parent folder.

Never say "the index only covers X, so grep is right" when the target path is inside the indexed repository. That is an indexing freshness/coverage issue, not permission to abandon Memtrace.

The narrow exceptions where grep/glob are still right

These are the ONLY cases where file tools beat memtrace:

• Files outside every indexed repo root. Confirm this with list_indexed_repositories; 0 search results or missing language stats do not prove it. Vendored deps, system headers, and excluded dirs (.git, node_modules, target, dist) are examples Memtrace cannot see.
• Non-source artifacts. .env, package.json, build scripts, top-level README.md, raw config files. Memtrace indexes parseable code, not configuration text.
• Pure file-inventory questions. "How many *.test.ts files exist", "list every Markdown file in docs/". You're asking for a file count, not a symbol search.
• Reading at a known path outside Memtrace. For configs, docs, or non-source artifacts that Memtrace cannot index, file Read is fine. For source-code spans returned by Memtrace, read the precise line range (your harness's Read with offset/limit, or get_source_window if your harness lacks bounded reads). Do not whole-file Read when you have a span.

For everything else inside the indexed repo, memtrace is the right tool.

The decision rule

Question Claude is asking	Right tool
"Where is symbol foo defined?"	find_symbol(name="foo") → then get_symbol_context for callers/callees/community, NOT a source read unless you're editing.
"What calls foo?"	get_symbol_context(repo_id, symbol="foo") → callers with file:line.
"How does authentication work?"	find_code(query="authentication") → get_symbol_context on the top hit, NOT a source read.
"Find behavior X" with multi-word phrase (3+ words)	find_code(verbatim) first; if low confidence, fan out with identifier-shaped reshapes (camelCase / snake_case).
"Find the function that uses STRIPE_KEY_FOO_BAR"	find_code(query="STRIPE_KEY_FOO_BAR") → semantic finds it inside any embedded body.
"Where's that error message 'connection refused for tenant'?"	find_code(query="connection refused for tenant") → semantic catches it.
"What breaks if I change foo?"	get_impact(repo_id, target="foo") → blast radius.
"Should I change/delete/refactor foo?"	find_symbol/get_symbol_context → recall_decision("foo / subsystem / approach"); if a symbol id is available, why_is_this_here + governing_contracts; then get_impact.
"Can I use/switch to pattern or library X?"	recall_decision("X") FIRST; bans and conventions are decisions. Verify a matching decision with verify_intent(decision_id) before relying on it.
"What changed in auth.ts last week?"	get_evolution(repo_id, from="7d ago", mode="recent", file_path="auth.ts").
"List all *.test.ts files."	Glob (file inventory, not symbol search).
"Find this string in my .env."

Parameter Types — Read This Before Calling Any Tool

All memtrace MCP tools are strictly typed. Pass JSON numbers (not strings) for integer parameters.

Parameter	Correct	WRONG (fails with MCP error -32602)
limit, min_size, depth, max_depth, last_n	limit: 20	limit: "20"
repo_id, branch, name, symbol_name, query	repo_id: "my-repo"	repo_id: my-repo (unquoted)
fuzzy, include_tests, invalidate	fuzzy: true	fuzzy: "true"
get_evolution.from	from: "90d ago"	days: 90 (wrong param — use from, not days)
get_changes_since.since	since: "2026-04-13T10:43:00Z"	last_episode_id: "..." (wrong param)
get_impact.target / get_symbol_context.symbol	target: "foo" / symbol: "foo"	symbol_id: "..." (wrong — use name)
find_most_complex_functions	top_n: 10	limit: 10 (wrong param name)
get_cochange_context	target: "execute"	symbol: "execute" (wrong param name)

If you see failed to deserialize parameters: invalid type: string "N", expected usize, remove the quotes from the number and retry.

If you see missing field 'from', you called get_evolution without from — pass e.g. "90d ago", never days.

Full parameter spec for every Memtrace tool: references/mcp-parameters.md (bundled at the memtrace-skills plugin root).

Check Indexing First (Once Per Session)

mcp__memtrace__list_indexed_repositories

If the current repo appears → Memtrace is active. Follow this skill for ALL code tasks. If not indexed → offer to index with mcp__memtrace__index_directory, then follow this skill.

Task → Tool Map

What you need	Use instead of Grep/Glob/Read
Find a function / class / symbol	find_symbol or find_code
Understand how something works	get_symbol_context (the default next step)
Find all callers of a function	get_symbol_context (callers field)
Find all callees / dependencies	get_symbol_context (callees field)
Trace a request / execution path	get_process_flow
Understand module structure	list_communities
Find the most important symbols	find_central_symbols
Find API endpoints	find_api_endpoints
Find where an API is called	find_api_calls
Debug a problem	get_symbol_context → get_impact → get_evolution
What changed recently?	get_changes_since or get_evolution
What breaks if I change X?	get_impact
Cross-service / cross-repo calls	get_service_diagram or get_api_topology
Dependency between two symbols	find_dependency_path
What files change together?	get_cochange_context
Architecture overview	list_communities + find_central_symbols
About to edit / quote — need exact lines	Bounded Read(file, offset=start_line, limit=N) (preferred), or get_source_window for path-resolution parity
About to edit/refactor/delete existing code	recall_decision for the intent + why_is_this_here/governing_contracts when a symbol id is available, then

Standard Workflows

"How does X work?" / "Explain X"

1. find_symbol or find_code → locate the symbol
2. get_symbol_context → callers, callees, community, processes (this usually answers "how it works")
3. get_process_flow (if it's a process/request path)
4. Only if you need to quote source: bounded Read at start_line..end_line, or get_source_window

Debugging "X is broken"

1. find_symbol → locate the broken thing
2. get_symbol_context → understand its role
3. get_impact → blast radius (what else breaks)
4. get_evolution(from=<lookback>, mode: recent) → per-episode changelog near the incident
5. get_changes_since(since=<anchor>) → catch-up since last session (requires stored since timestamp)

"Where is X defined / called?"

1. find_symbol with fuzzy: true
2. get_symbol_context for full caller/callee map
3. Only if you need source text: bounded Read at start_line..end_line, or get_source_window

Before any code modification

1. find_symbol → confirm you have the right target
2. get_symbol_context → understand full context
3. recall_decision("<symbol/subsystem/approach>") → surface recorded choices, bans, and conventions before deciding what to do
4. If a symbol_id is available, why_is_this_here(symbol_id) + governing_contracts(symbol_id) before deleting, rewriting, or "cleaning up" odd code
5. get_impact → know blast radius before touching anything
6. get_style_fingerprint(repo_id, file_path=<file>) → match the codebase's empirical idiom (ternary vs if-else, arrow vs fn-decl, etc.) — see memtrace-style-fingerprint workflow for the full decision rule

Red Flags — STOP, Use Memtrace Instead

You are violating this skill if you think:

Thought	Reality
"Let me grep for this"	find_code or find_symbol is faster and structurally aware
"Let me glob for the file"	find_symbol returns exact location with context
"Let me read the whole file"	get_symbol_context for the WHY (callers/callees/community); a bounded source read at start_line..end_line for the WHAT
"I know why this is written this way"	Check Cortex first. Use recall_decision; use why_is_this_here/governing_contracts when you have a symbol id.
"This looks unused/weird; I'll remove it"	why_is_this_here + governing_contracts first, then blast radius. CannotProve is unknown, not permission.
"I'll just switch to library/pattern X"	recall_decision("X") first — you may be reintroducing a banned approach.
"It's just a quick search"	Grep has no understanding of call graphs, communities, or time
"I don't know if it's indexed"	Check with list_indexed_repositories first — takes 1 second
"Memtrace returned 0 results"	Broaden the Memtrace query, check repo_id/path coverage, then reindex if needed
"Stats only show Rust, but I need ui/ or memtrace-ui/"	That is a coverage diagnostic. Reindex the repo root; do not grep source code.
"The user didn't say to use Memtrace"	User asked about the code. Repo is indexed. Use Memtrace.
"This is a simple question"	Simple questions benefit most — one find_symbol vs 20 file reads

When File Tools Are Still Correct

Use Grep/Glob/Read ONLY for:

• Non-source files or paths outside every indexed source repo
• Files that are config, data, or docs (not source code symbols)
• Repos or paths confirmed outside every Memtrace indexed root
• Official Memtrace product documentation — use memtrace-docs (ask_docs / search_docs / read_doc), not file tools or web search

For source-code spans already located by Memtrace, use a bounded read — your harness's Read(file, offset, limit) with the returned start_line / end_line, or get_source_window if your harness lacks bounded reads. Do not read the whole file.

Never use file tools as a discovery mechanism when Memtrace is available.

Skill Priority

This skill is a process skill — it runs BEFORE any implementation or search skill.

When this skill applies, it overrides default file-search behavior. Use the specific Memtrace sub-skills for deep detail on each tool:

• Discovery → memtrace-search
• Impact analysis → memtrace-impact
• Temporal / change analysis → memtrace-evolution
• Rationale / prior decisions / bans / contracts → memtrace-decision-memory
• Incident investigation → memtrace-incident-investigation
• Architecture overview → memtrace-codebase-exploration
• Refactoring → memtrace-refactoring-guide
• Memtrace product docs (install, CLI, MCP, enterprise) → memtrace-docs

Output

find_symbol / find_code return ranked symbol entries (score only with include_diagnostics: true):

{ "name": "handleAuth", "kind": "Function", "file_path": "src/auth.ts",
  "start_line": 42, "end_line": 87 }

get_symbol_context returns the graph neighborhood: symbol, callers, callees, type_references, community, processes, api_callers_cross_repo. Feed start_line/end_line into a bounded Read or get_source_window — never a whole-file read.

Success criteria

• The answer is grounded in Memtrace graph results (search hit → get_symbol_context / get_impact), not file-tool discovery.
• Grep/Glob/Read appear only via the documented narrow exceptions (non-source artifacts, paths outside every indexed root, file inventory, bounded span reads).
• Zero-result queries were diagnosed (list_indexed_repositories → broaden → reindex), not bypassed to grep.
• Any source read was bounded to the span Memtrace returned.