Not in the top 1,000 by GitHub stars
nikolai-vysotskyi/trace-mcp
Framework-aware code intelligence MCP server — 91 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
integrations/bb/skills/trace-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
e4e645c7e5e3 → adac3f7d216a
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e4e645c7e5e3
No earlier version was observed for comparison.
skills/trace-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
e4e645c7e5e3 → adac3f7d216a
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e4e645c7e5e3
No earlier version was observed for comparison.
skills/trace-mcp-codemod/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
e4e645c7e5e3 → adac3f7d216a
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e4e645c7e5e3
No earlier version was observed for comparison.
skills/trace-mcp-pre-commit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
e4e645c7e5e3 → adac3f7d216a
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e4e645c7e5e3
No earlier version was observed for comparison.
skills/trace-mcp-refactoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
e4e645c7e5e3 → adac3f7d216a
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e4e645c7e5e3
No earlier version was observed for comparison.
Verified commit adac3f7d216a1d0f06353597a823cc65f13dc42b
git clone --filter=blob:none --no-checkout https://github.com/nikolai-vysotskyi/trace-mcp.git .hotskills/nikolai-vysotskyi-trace-mcp && git -C .hotskills/nikolai-vysotskyi-trace-mcp checkout --detach adac3f7d216a1d0f06353597a823cc65f13dc42b
# Copy each selected skill directory from .hotskills/nikolai-vysotskyi-trace-mcp into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/nikolai-vysotskyi/trace-mcp.git .hotskills/nikolai-vysotskyi-trace-mcp && git -C .hotskills/nikolai-vysotskyi-trace-mcp checkout --detach adac3f7d216a1d0f06353597a823cc65f13dc42b
# Copy each selected skill directory from .hotskills/nikolai-vysotskyi-trace-mcp into .agents/skills/<skill-name>/Heat
3.9- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- trace-mcp
integrations/bb/skills/trace-mcp - trace-mcp
skills/trace-mcp - trace-mcp-codemod
skills/trace-mcp-codemod - trace-mcp-pre-commit
skills/trace-mcp-pre-commit - trace-mcp-refactoring
skills/trace-mcp-refactoring
How it works
trace-mcp
When your agent uses it
Use trace-mcp through bb to search indexed code and recall project decisions with compact context.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
297 tokensWhen the skill is activated
Reference documents
492 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../../../.claude-plugin/.mcp.jsonasset48 bytes../../../../.claude-plugin/README.mddoc2,023 bytes../../../../.claude-plugin/hooks/hooks.jsonasset689 bytes../../../../.claude-plugin/hooks/hooks.jsonasset689 bytes../../../../.claude-plugin/hooks/hooks.jsonasset689 bytes../../../../.claude-plugin/hooks/hooks.jsonasset689 bytes../../../../.claude-plugin/marketplace.jsonasset493 bytes../../../../.claude-plugin/plugin.jsonasset878 bytes../../../../.codex-plugin/hooks/hooks.jsonasset516 bytes../../../../.codex-plugin/hooks/hooks.jsonasset516 bytes../../../../.codex-plugin/hooks/hooks.jsonasset516 bytesSKILL.mdcore1,413 bytes
Read SKILL.md
Use `trace_get_index_health` to check the index, then `trace_search` to find symbols before reading whole files. Use `trace_get_symbol` for an exact definition and `trace_get_outline` for file structure. Use `trace_get_project_memo` at the start of a task when prior decisions matter, `trace_query_decisions` for a focused recall query, and `trace_remember_decision` to record an explicit English-language decision with the current bb thread as its session ID. Automatic decision capture rejects non-English text; for a manually entered decision in another language use the panel or `bb trace remember`. For other capabilities, search the catalog with `trace_tools` and pass the selected tool name and arguments to `trace_call`.
The thread's **Trace context** panel shows index health, saved decisions, and the provider's context-window usage. The same data and explicit writes are available through `bb trace status`, `bb trace decisions`, `bb trace remember`, and `bb trace index`; pass `--thread <id>` outside a bb thread.
The plugin runs trace-mcp in the bb environment's repository on its host machine. A thread needs an environment with a path. On first use, indexing may take time. Tool results are capped; narrow or page a query when a result says it was shortened.View the complete source on GitHubtrace-mcp
When your agent uses it
Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
1,588 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Start-of-Session Checklist
- Decision Matrix
- Environment Variables (Safe Path)
- Token-Efficiency Rules
- After Editing a File
- Before Creating New Symbols
- Health Checks (Once Per Session)
- Related Skills
Files
SKILL.mdcore6,305 bytesSKILL.mdcore6,305 bytes
Read SKILL.md
# trace-mcp — Code Intelligence Routing
trace-mcp is a framework-aware code intelligence MCP server. It exposes 182 tools that return semantic, structured results over a cross-language dependency graph. When trace-mcp is available, it is almost always cheaper and more accurate than native file tools.
## When to Use
Activate this skill whenever you need to:
- Find a function, class, method, route, component, or any symbol
- Understand a file, module, or feature before editing
- Determine what breaks if you change something
- Trace a request flow, call graph, or data flow
- Audit architecture, dead code, tests, or security
**Do not use** `Read`, `Grep`, `Glob`, or shell `ls`/`find`/`cat`/`head`/`tail` for exploring source code (`.ts`, `.js`, `.py`, `.php`, `.go`, `.rb`, `.java`, etc.). Use trace-mcp tools instead. Native tools stay allowed only for non-code files (`.md`, `.json`, `.yaml`, configs) or immediately before an `Edit` on a known file.View the complete source on GitHubtrace-mcp-codemod
When your agent uses it
Use trace-mcp apply_codemod for any bulk mechanical change instead of repeated Edit calls. Activate whenever the same edit pattern would be applied 2+ times, across one file or many.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
753 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use — HARD RULE
- Standard Workflow
- Planning Larger Changes
- Anti-Patterns to Avoid
Files
SKILL.mdcore2,934 bytes
Read SKILL.md
# trace-mcp — Codemod Workflow
`apply_codemod` is the correct tool for any repeated mechanical change. Using `Edit` for the same pattern twice or more is a waste of tokens and is error-prone.
## When to Use — HARD RULE
If you are about to make the **same kind of change 2 or more times** — whether in one file or across many — stop and use `apply_codemod`. This includes:
- Adding `async`/`await` to a set of functions
- Updating a function signature everywhere it is called
- Fixing import paths after a move
- Adding or removing keywords/decorators
- Wrapping calls in a logger, try/catch, or feature flag
- Replacing a deprecated API usageView the complete source on GitHubtrace-mcp-pre-commit
When your agent uses it
Run trace-mcp security, quality-gate, and antipattern checks before committing or opening a PR. Activate when the agent is about to create a commit or pull request in a project indexed by trace-mcp.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
514 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Checklist
- Fix or Escalate
- After Commit
Files
SKILL.mdcore2,259 bytes
Read SKILL.md
# trace-mcp — Pre-Commit & Pre-PR Checks
Before creating a commit or opening a pull request, run the trace-mcp validation suite. Fix any critical or high findings before committing.
## When to Use
- The user asks to commit, stage, or push changes
- The user asks to open a PR
- The agent has finished implementing a feature or fix and is about to hand off
## Checklist
### 1. Security scan
View the complete source on GitHubtrace-mcp-refactoring
When your agent uses it
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
652 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Refactoring Workflow
- Renaming a Symbol — MANDATORY Flow
- Extracting a Function
- After the Refactor
Files
SKILL.mdcore2,695 bytes
Read SKILL.md
# trace-mcp — Refactoring Workflow
Use this skill whenever you are about to rename, restructure, extract, or otherwise refactor code in a project indexed by trace-mcp. The goal is to never break cross-file references and never guess at what is affected.
## When to Use
- Renaming a class, function, method, variable, or file
- Extracting a function or method
- Restructuring a module or splitting a file
- Changing a function signature
- Any change that touches more than one call site
## Refactoring Workflow
View the complete source on GitHubSkills included
- trace-mcp
- trace-mcp
- trace-mcp-codemod
- trace-mcp-pre-commit
- trace-mcp-refactoring
Repository facts
- License
- MIT
- Created
- Apr 3, 2026
- Last pushed
- Nov 7, 2026
- Forks
- 24
- Open issues
- 0
- Project activity
- Active
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 9 notes
.claude-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed.codex-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed.codex-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/trace-mcp/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notes
- No broad tool permissions
- No dangerous shell commands
- 9 network referencesin 2 files: .claude-plugin/plugin.json:5 .claude-plugin/marketplace.json:3
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 6 references to secretsin 1 file: trace-mcp/SKILL.md:49
- No requests to vote in Hot
Show all 15 signals by file
.claude-plugin/marketplace.json
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "Nikolai Vysotskyi", "url": "https://github.com/nikolai-vysotskyi" - Network accessline 6
"name": "Nikolai Vysotskyi", "url": "https://github.com/nikolai-vysotskyi" }, - Network accessline 7
"url": "https://github.com/nikolai-vysotskyi" - Network accessline 29
"memory" ], "repository": "https://github.com/nikolai-vysotskyi/trace-mcp" - Network accessline 30
], "repository": "https://github.com/nikolai-vysotskyi/trace-mcp" } - Network accessline 31
"repository": "https://github.com/nikolai-vysotskyi/trace-mcp"
skills/trace-mcp/SKILL.md
- Access to secretsline 49
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted] - Access to secretsline 63
[Credential-related source omitted] - Access to secretsline 64
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Access to secretsline 66
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 6 facts
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuetrace-mcp/SKILL.md:49Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuetrace-mcp/SKILL.md:56Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuetrace-mcp/SKILL.md:63Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuetrace-mcp/SKILL.md:64Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuetrace-mcp/SKILL.md:65Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuetrace-mcp/SKILL.md:66Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md integrations/bb/skills/trace-mcp/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md integrations/bb/skills/trace-mcp/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md integrations/bb/skills/trace-mcp/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md integrations/bb/skills/trace-mcp/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.