calibrate-settings

calibrate-settings is a skill for Claude Code from odere-pro/claude-calibration. It costs 197 tokens per session (1,186 once invoked), scanned C, original, MIT.

A settings auditor for Claude Code configuration files at user, project, local, and plugin levels. It checks settings files for problems such as invalid JSON, committed secrets, and unsafe permission options.

In plain words
What is it for?
Use it to enumerate and lint settings.json files, then review security and configuration findings.
Why use it?
It helps find risky or broken configuration spread across the different places Claude Code can read.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

Part of the claude-calibration plugin — 20 skills, 6 agents, 2 hooks shipped together

Good fit Use it to enumerate and lint settings.json files, then review security and configuration findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/odere-pro/claude-calibration/calibrate-settings
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add odere-pro/claude-calibration --skill calibrate-settings
Clone the repo
git clone --depth 1 https://github.com/odere-pro/claude-calibration

Made for: Claude Code.

Or install claude-calibration, the plugin that ships this one along with the rest of its 20 skills, 6 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for calibrate-settings

README.md
[![agentmods](https://agentmods.dev/badge/skills/odere-pro/claude-calibration/calibrate-settings/github.svg)](https://agentmods.dev/skills/odere-pro/claude-calibration/calibrate-settings)
Your own site
<a href="https://agentmods.dev/skills/odere-pro/claude-calibration/calibrate-settings"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-calibration/calibrate-settings/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for calibrate-settings

Your own site · 80×15
<a href="https://agentmods.dev/skills/odere-pro/claude-calibration/calibrate-settings"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-calibration/calibrate-settings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,186 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00197 $0.01186
Opus 5 $0.00098 $0.00593
Sonnet 5 $0.00039 $0.00237
Haiku 4.5 $0.00020 $0.00119

Measured 10d ago against content hash 58d1dc7e93c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

calibrate-settings scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/enumerate.sh, scripts/lint.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`permissions.allow` entries (`Bash(*)`, `Bash(rm *)`, `Bash(sudo *)`), model pins in committed

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Audits and tunes every `settings.json` Claude Code reads — user (`~/.claude/settings.json`),
skills/calibrate-settings/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

calibrate-settings — per-feature bundle

You audit and tune settings.json files across every scope Claude Code reads. You receive one of two kinds of work:

  • Direct invocation (/claude-calibration:calibrate-settings) — audit everything, report findings, propose fixes inline. The user drives the conversation.
  • Dispatch from the calibrator — one approved plan row at a time, applied surgically.

In both cases the workflow is the same; only the framing differs.

1. Enumerate

bash <BUNDLE>/scripts/enumerate.sh "$PROJECT_DIR"

Yields TSV scope\tpath. Scope is user (~/.claude/settings.json), user-local (~/.claude/settings.local.json), project (<PROJECT_DIR>/.claude/settings.json), project-local (<PROJECT_DIR>/.claude/settings.local.json), or plugin-self (<plugin-root>/.claude/settings.json when the project is itself a plugin).

2. Lint

bash <BUNDLE>/scripts/lint.sh <path …>

Yields TSV path\tsignature\tseverity\tdetail. The signatures this bundle owns (see reference.md):

  • settings:invalid-json (HIGH)
  • settings:secret-in-committed (CRITICAL)
  • settings:dangerously-skip-permissions (CRITICAL)
  • settings:permissions-blanket-destructive (HIGH)
  • settings:model-pinned-in-committed (LOW)
  • settings:env-bloated (LOW)
  • settings:permissions-empty (LOW)
  • settings:precedence-surprise (LOW)

3. Fix — kind: edit rows

For each finding, the remediation pattern is in examples/<case>/:

  • settings:secret-in-committed → move the secret to .local.json (or an env-var reference); rotate the exposed credential.
  • settings:dangerously-skip-permissions → remove the reference; if a workflow needed it, surface the underlying tool calls and add narrow permissions.allow entries instead.
  • settings:permissions-blanket-destructive → replace Bash(*) / Bash(rm *) / Bash(sudo *) with the smallest set of narrow Bash(<tool> *) entries that covers real usage.
  • settings:model-pinned-in-committed → move the model: pin to .local.json (per-machine) or drop it (let Claude pick).
  • settings:env-bloated → move per-machine values to .local.json; keep committed env minimal.
  • settings:permissions-empty → see examples/permissions-empty/{before,after}.md; copy the baseline allow-list from templates/settings.json.tmpl.
  • settings:invalid-json → fix the parse error reported in the detail.
  • settings:precedence-surprise → reconcile: either accept the managed override or surface the conflict to the policy owner.

Read the full file on GitHub · 97 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 97 lines · 197 tokens per session scan C 58d1dc7e93c4

Subscribe to this mod's changes

calibrate-settings is a skill published in the GitHub repository odere-pro/claude-calibration (1 stars, last pushed 1mo ago), licensed MIT. It adds 197 tokens to every session and 1,186 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.