Skip to content

CowboyLogic/ai-dev / skills/client-config-claudecode

client-config-claudecode

Flagged

Manage and maintain Claude Code configuration files and settings. Use this skill whenever the user wants to view, edit, add, remove, or understand any Claude Code settings — permissions, hooks, MCP servers, environment variables, model settings, sandbox, auto mode, or any other configuration field. Trigger on: "add permission", "allow tool", "deny tool", "configure hook", "add MCP server", "change model", "update settings", "show my settings", "what settings do I have", or "set default mode".

FileKindSize
CHANGELOG.mdmarkdown18.3 KB
README.mdmarkdown3.2 KB
SKILL.mdskill md8.5 KB
assets/sources.jsonconfig3.2 KB
evals/evals.jsonconfig10.2 KB
references/hooks.mdmarkdown28.0 KB
references/mcp.mdmarkdown16.1 KB
references/permissions.mdmarkdown21.6 KB
references/settings-schema.mdmarkdown39.2 KB
scripts/show-settings.pyscript8.6 KB
scripts/update-references.pyscript5.4 KB
scripts/validate-settings.pyscript35.9 KB
# Claude Code Configuration Manager

Evaluation results for the `client-config-claudecode` skill. The skill itself is
[SKILL.md](SKILL.md), and its history is in [CHANGELOG.md](CHANGELOG.md).

> [!NOTE]
> **Claude Code version:** verified against [Claude Code 2.1.325](https://github.com/anthropics/claude-code/releases/tag/v2.1.325)
> (published to npm 2026-11-13; the npm `latest` and `next` tags on 2026-11-15, with `stable` at 2.1.311).
> References come from the `code.claude.com/docs` pages listed in
> [assets/sources.json](assets/sources.json), checked against the changelog through 2.1.325.
> Where only the changelog supports a claim, the reference says so. Last re-verified
> 2026-11-15. Re-verify when Claude Code ships a new release.

## Evaluation results

Benchmark run: **2026-04-26 · iteration 1** · 3 scenarios · 6 total runs

These results predate the 2026-09-24 v2.0 refresh, the 2026-10-11 v2.1 update, the
2026-10-13 v2.2 update, the 2026-10-14 v2.3 update, and the 2026-10-18 v2.4 update, the 2026-11-01 v2.5 update, the 2026-11-08 v2.6 update, and the 2026-11-15 v2.7 update.
[evals/evals.json](evals/evals.json) holds the eval cases; it also includes five cases that
this run did not cover: `default-mode-scope` (added in v2.0), `hook-fail-closed` (added in
v2.1), `stop-hook-loop-cap` (added in v2.2), `idle-compaction` (added in v2.3), and
`mcp-server-name-with-double-underscore` (added in v2.4). The v2.5 update added no eval cases.

### Overall

| | With skill | Baseline (no skill) | Delta |
|---|---|---|---|
| Assertions passed | 15 / 15 | 12 / 15 | — |
| Pass rate | **100%** | **80%** | **+20 pp** |

### By scenario

| Scenario | With skill | Baseline | Delta | Notes |
|---|---|---|---|---|
| Lint hook on file edit/write (`PostToolUse`, `Edit\|Write`, `$CLAUDE_PROJECT_DIR`) | 5 / 5 | 5 / 5 | 0% | Well-established; both answered correctly |
| Git read-allow / destructive-deny (`Bash()` rule syntax, deny precedence) | 5 / 5 | 5 / 5 | 0% | Baseline has accurate permissions knowledge |
| Voice dictation + model (`voice` object, tap mode, `autoSubmit`) | 5 / 5 | 2 / 5 | +60% | Baseline used deprecated `voiceEnabled: true`; stated `voice.mode` and `voice.autoSubmit` do not exist |

> [!NOTE]
> This skill has marginal but measurable value when used with Claude models. For well-established
> configuration areas (hooks, permissions), the baseline is already reliable. Value increases for
> settings that postdate the model's training cutoff.

### Key takeaway

For Claude Code's established configuration surface (hooks structure, `Bash()` permission
rules), the baseline model is already reliable — the skill reinforces rather than corrects.
The gap opens on settings that have changed since training: the baseline defaults to the
deprecated `voiceEnabled: true` boolean, asserts the `voice` object sub-fields don't exist,
and confidently gives the user a configuration that will behave differently than expected.
The skill closes this gap entirely.

> [!TIP]
> **When does this skill matter most?** Any time a user asks about voice dictation
> settings, or any other Claude Code feature that postdates the model's training cutoff.
> The skill reference reflects the current schema; the baseline cannot.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall