← Back to search

@yawlabs/ctxlint

jeffyaw Scanned 21d ago

Lint your AI agent context files, MCP server configs, and session data against your actual codebase

C
71.2 / 100

Versions

0.18.7latest
Jul 25, 2026
0.18.6
Jul 20, 2026
0.18.5
Jul 20, 2026
0.18.4
Jun 29, 2026
0.18.3
Jun 29, 2026
+ show 52 moreshow less
0.18.2
Jun 27, 2026
0.18.1
Jun 19, 2026
0.18.0
Jun 18, 2026
0.17.0
Jun 18, 2026
0.16.0
Jun 11, 2026
0.15.1
Jun 10, 2026
0.15.0
Jun 10, 2026
0.14.1
Jun 7, 2026
0.14.0
Jun 7, 2026
0.13.3
Jun 7, 2026
0.13.2
Jun 4, 2026
0.13.1
Jun 3, 2026
0.13.0
Jun 3, 2026
0.12.3
May 28, 2026
0.12.2
May 28, 2026
0.12.1
May 19, 2026
0.12.0
May 17, 2026
0.10.2
May 15, 2026
0.10.1
May 14, 2026
0.10.0
May 14, 2026
0.9.20
May 6, 2026
0.9.19
Apr 25, 2026
0.9.18
Apr 23, 2026
0.9.17
Apr 17, 2026
0.9.16
Apr 16, 2026
0.9.15
Apr 16, 2026
0.9.14
Apr 16, 2026
0.9.13
Apr 16, 2026
0.9.12
Apr 16, 2026
0.9.11
Apr 16, 2026
0.9.10
Apr 14, 2026
0.9.9
Apr 14, 2026
0.9.8
Apr 12, 2026
0.9.7
Apr 12, 2026
0.9.6
Apr 12, 2026
0.9.5
Apr 12, 2026
0.9.4
Apr 12, 2026
0.9.3
Apr 12, 2026
0.9.2
Apr 12, 2026
0.9.1
Apr 11, 2026
0.9.0
Apr 10, 2026
0.8.0
Apr 8, 2026
0.7.0
Apr 8, 2026
0.6.0
Apr 8, 2026
0.5.0
Apr 7, 2026
0.4.0
Apr 7, 2026
0.3.0
Apr 7, 2026
0.2.2
Apr 6, 2026
0.2.1
Apr 5, 2026
0.2.0
Apr 5, 2026
0.1.1
Apr 5, 2026
0.1.0
Apr 5, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 7

ctxlint_audit
annotations: none low

Audit AI agent context files (CLAUDE.md, AGENTS.md, etc.) in the project. Checks for stale references, invalid commands, redundant content, contradictions, frontmatter issues, and token waste. Scoped to context-file checks only; MCP-config and session-level checks are exposed as separate tools.

ctxlint_validate_path
annotations: none low

Check if a file path referenced in a context file actually exists in the project. Returns the file status and suggests corrections if the path is invalid.

path string projectPath string
ctxlint_token_report
annotations: none low

Get a token count breakdown for all context files in the project. Shows per-file and aggregate token usage, plus estimated waste from redundant content.

projectPath string
ctxlint_fix
annotations: none low

Run the linter with --fix mode to auto-correct broken file paths in context files using git history and fuzzy matching. Returns a summary of what was fixed. Pass dryRun: true to preview what would be fixed without writing any files.

ctxlint_mcp_audit
annotations: none low

Lint MCP server configuration files in a project. Checks for schema errors, hardcoded secrets, deprecated transports, wrong env var syntax, URL issues, and cross-client inconsistencies.

includeGlobal boolean
ctxlint_session_audit
annotations: none low

Audit AI agent session data for cross-project consistency. Checks for missing GitHub secrets, diverged config files, missing workflows, stale memory entries, and duplicate memories across sibling repositories.

ctxlint_skill_audit
annotations: none low

Audit agent skill and subagent definitions (~/.claude/skills/*/SKILL.md, ~/.claude/agents/*.md). Checks for frontmatter problems, broken file references, trigger collisions, orphaned skill directories, and dead tool restrictions.

Permissions 3

filesystem low
Server uses filesystem capabilities via: fs, fs sync ops, fs.promises
shell high
Server uses shell capabilities via: child_process, spawn(), spawnSync()
env_vars low
Server uses env_vars capabilities via: process.env

Scan Findings 30

medium
Vulnerable dependency: express@4.18.0 (GHSA-qw6h-vgh9-j6wx) dependency_analyzer · 95%
low
Tool 'ctxlint_audit' has no annotations annotation_checker · 100%
low
Tool 'ctxlint_validate_path' has no annotations annotation_checker · 100%
low
Tool 'ctxlint_token_report' has no annotations annotation_checker · 100%
low
Tool 'ctxlint_fix' has no annotations annotation_checker · 100%
low
Tool 'ctxlint_mcp_audit' has no annotations annotation_checker · 100%
low
Tool 'ctxlint_session_audit' has no annotations annotation_checker · 100%
low
Tool 'ctxlint_skill_audit' has no annotations annotation_checker · 100%
medium
OAuth implementation without PKCE auth_checker · 75%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: express@4.18.0 (GHSA-rv95-896h-c2vc) dependency_analyzer · 95%
medium
Vulnerable dependency: vitest@2.0.0 (GHSA-5xrq-8626-4rwp) dependency_analyzer · 95%
medium
Vulnerable dependency: vitest@2.0.0 (GHSA-9crc-q9x8-hgqq) dependency_analyzer · 95%
medium
Hex string literal (>50 chars) in YawLabs-ctxlint-9b72149/src/core/checks/mcp/__tests__/security.test.ts:462 entropy_analyzer · 70%
info
package.json metadata manifest_parser · 100%
info
Tool: ctxlint_audit manifest_parser · 70%
info
Tool: ctxlint_validate_path manifest_parser · 70%
info
Tool: ctxlint_token_report manifest_parser · 70%
info
Tool: ctxlint_fix manifest_parser · 70%
info
Tool: ctxlint_mcp_audit manifest_parser · 70%
info
Tool: ctxlint_session_audit manifest_parser · 70%
info
Tool: ctxlint_skill_audit manifest_parser · 70%
info
Transport: stdio manifest_parser · 90%
info
Required env vars (5) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
low
Permission: filesystem access detected permission_analyzer · 90%
high
Permission: shell access detected permission_analyzer · 95%
low
Permission: env_vars access detected permission_analyzer · 90%
info
SBOM generated: 31 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%