ktg-plugin-marketplace

open/ktg-plugin-marketplace

Fork 0

Commit graph

Author	SHA1	Message	Date
Kjell Tore Guttormsen	ce7c42f517	fix(config-audit): MCP token callers use 'mcp' kind (v5 F2) Two MCP enumeration paths in readActiveMcpServers now pass kind='mcp' to estimateTokens with optional toolCount derived from def.tools array (populated when callers cache MCP discovery — Step 14 wires that up). Hook callers keep kind='item' (no schema overhead). Visible effect: every active MCP server jumps from estimatedTokens=15 to >= 500 (or higher when toolCount is known). The whats-active output and TOK hotspots now reflect actual MCP cost. Tests: assert mcpServers[].estimatedTokens >= 500 in fixture.	2026-05-01 06:22:54 +02:00
Kjell Tore Guttormsen	48d560a209	feat(config-audit): add 'mcp' kind to estimateTokens (v5 F2) Differentiate MCP servers from generic 'item' (flat 15) — they actually cost 500+ tokens per turn for protocol metadata and tool schemas. estimateTokens(bytes, 'mcp', {toolCount}) returns max of: - 500 token floor (base overhead) - ceil(bytes / 3.5) (json-rate when bytes known) - 500 + toolCount * 200 (when tool count is detected; Step 14 wires this) Caller-side migration in next commit (Step 5). Tests: +4 cases for mcp kind.	2026-05-01 06:21:30 +02:00
Kjell Tore Guttormsen	4f1cc7e0b7	feat(config-audit): v3.1.0 — /config-audit whats-active inventory command New read-only command that shows everything Claude Code actually loads for a given repo — plugins, skills, MCP servers, hooks, CLAUDE.md cascade — with source attribution (user/project/plugin) and rough token estimates. Helps identify candidates for disabling without guessing. Added: - scanners/lib/active-config-reader.mjs — pure async helper: readActiveConfig, detectGitRoot, walkClaudeMdCascade, readClaudeJsonProjectSlice (longest-prefix matching for .claude.json projects), enumeratePlugins, enumerateSkills, readActiveHooks, readActiveMcpServers, estimateTokens (markdown 4 c/tok, json 3.5 c/tok, frontmatter cap 150 tokens, item flat 15) - scanners/whats-active.mjs — thin CLI shim: --json, --output-file, --verbose, --suggest-disables - commands/whats-active.md — renders tables via Read tool; honors UX rules - tests/lib/active-config-reader.test.mjs — 36 tests, all green (integration fixture built in tmpdir with fake HOME, .claude.json prefix matching, plugin discovery, hook/MCP merge from all scopes) Verified: - Performance budget: <2s wall-clock (smoke test: 102ms on real repo) - Token estimates within ±20% of hand-computed values - Read-only: no writeFile/mkdir/unlink in production code - Self-audit: Plugin Health scanner reports 0 findings (Grade A) - Full test suite: 522 tests, 512 pass (10 pre-existing conflict-detector failures on main — unrelated to this change, reproducible on clean HEAD) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-14 21:50:20 +02:00

Author

SHA1

Message

Date

Kjell Tore Guttormsen

ce7c42f517

fix(config-audit): MCP token callers use 'mcp' kind (v5 F2)

Two MCP enumeration paths in readActiveMcpServers now pass kind='mcp'
to estimateTokens with optional toolCount derived from def.tools array
(populated when callers cache MCP discovery — Step 14 wires that up).

Hook callers keep kind='item' (no schema overhead).

Visible effect: every active MCP server jumps from estimatedTokens=15
to >= 500 (or higher when toolCount is known). The whats-active output
and TOK hotspots now reflect actual MCP cost.

Tests: assert mcpServers[].estimatedTokens >= 500 in fixture.

2026-05-01 06:22:54 +02:00

Kjell Tore Guttormsen

48d560a209

feat(config-audit): add 'mcp' kind to estimateTokens (v5 F2)

Differentiate MCP servers from generic 'item' (flat 15) — they actually
cost 500+ tokens per turn for protocol metadata and tool schemas.

estimateTokens(bytes, 'mcp', {toolCount}) returns max of:
- 500 token floor (base overhead)
- ceil(bytes / 3.5) (json-rate when bytes known)
- 500 + toolCount * 200 (when tool count is detected; Step 14 wires this)

Caller-side migration in next commit (Step 5).

Tests: +4 cases for mcp kind.

2026-05-01 06:21:30 +02:00

Kjell Tore Guttormsen

4f1cc7e0b7

feat(config-audit): v3.1.0 — /config-audit whats-active inventory command

New read-only command that shows everything Claude Code actually loads for a
given repo — plugins, skills, MCP servers, hooks, CLAUDE.md cascade — with
source attribution (user/project/plugin) and rough token estimates. Helps
identify candidates for disabling without guessing.

Added:
- scanners/lib/active-config-reader.mjs — pure async helper: readActiveConfig,
  detectGitRoot, walkClaudeMdCascade, readClaudeJsonProjectSlice (longest-prefix
  matching for .claude.json projects), enumeratePlugins, enumerateSkills,
  readActiveHooks, readActiveMcpServers, estimateTokens (markdown 4 c/tok,
  json 3.5 c/tok, frontmatter cap 150 tokens, item flat 15)
- scanners/whats-active.mjs — thin CLI shim: --json, --output-file, --verbose,
  --suggest-disables
- commands/whats-active.md — renders tables via Read tool; honors UX rules
- tests/lib/active-config-reader.test.mjs — 36 tests, all green (integration
  fixture built in tmpdir with fake HOME, .claude.json prefix matching,
  plugin discovery, hook/MCP merge from all scopes)

Verified:
- Performance budget: <2s wall-clock (smoke test: 102ms on real repo)
- Token estimates within ±20% of hand-computed values
- Read-only: no writeFile/mkdir/unlink in production code
- Self-audit: Plugin Health scanner reports 0 findings (Grade A)
- Full test suite: 522 tests, 512 pass (10 pre-existing conflict-detector
  failures on main — unrelated to this change, reproducible on clean HEAD)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-04-14 21:50:20 +02:00

3 commits