agentmods.dev

config

config is a command for coding agents from Not-Diamond/self-care. It costs 8 tokens per session (3,109 once invoked), scanned A, original, MIT.

A command for viewing or changing Self-Care settings, stored in the project's .self-care/config.json file. Self-Care analyzes agent execution traces for issues such as repeated steps, missing context, or guardrail violations.

In plain words
What is it for?
Use it to view or reset settings, enable or disable detection checks, change severity levels, add exclusions, and configure automatic fixes or analytics.
Why use it?
It lets you control which checks run and how they are handled without editing the configuration file manually.

Command

Part of the self-care plugin — 12 commands, 2 agents shipped together

not rated 28 4mo ago A scan 8 tokens original MIT
View the source file Not-Diamond/self-care
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.

agentmods
npx agentmods add commands/not-diamond/self-care/config
Clone the repo
git clone --depth 1 https://github.com/Not-Diamond/self-care

Or install self-care, the plugin that ships this one along with the rest of its 12 commands, 2 agents.

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 config

README.md
[![agentmods](https://agentmods.dev/badge/commands/not-diamond/self-care/config.svg)](https://agentmods.dev/commands/not-diamond/self-care/config)
Your own site
<a href="https://agentmods.dev/commands/not-diamond/self-care/config"><img src="https://agentmods.dev/badge/commands/not-diamond/self-care/config.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,109 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00008 $0.03109
Opus 5 $0.00004 $0.01554
Sonnet 5 $0.00002 $0.00622
Haiku 4.5 $0.00001 $0.00311

Measured 4d ago against content hash 10c129a4b828, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

config scanned grade A with 0 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 4d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/config.md · 445 lines

How it starts

The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Care Config

View or modify Self-Care configuration settings.

Config File Location

Settings are stored in the project-local config file: .self-care/config.json

Valid Skill IDs

grounding, missed-action, instruction-following, context-utilization,
goal-drift, persona-adherence, reasoning-action-mismatch, step-repetition,
tool-failure, premature-termination, contradictory-instructions,
missing-context, ambiguous-instructions, guardrail-violation

Instructions

Parse Arguments

Extract the subcommand from $ARGUMENTS:

  • If empty or whitespace-only: show current config
  • If analytics on or analytics off: toggle analytics
  • If disable (with or without a skill name): disable a skill
  • If enable (with or without a skill name): enable a skill
  • If severity <skill> <level>: set severity override
  • If severity <skill> reset: remove severity override
  • If exclude <pattern>: add exclusion pattern
  • If include <pattern>: remove exclusion pattern
  • If autofix <value>: set auto-fix behavior
  • If reset: reset analysis config to defaults
  • Otherwise: show usage help

Show Current Config (no arguments)

  1. Read the config file at .self-care/config.json using the Read tool.

  2. If the file exists and is valid JSON:

    Display the current settings:

    Self-Care Configuration
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Analytics: <enabled|disabled, or "not configured" if no analytics key>

Analysis Settings:
  Auto-fix: <auto|prompt|disabled>
  Disabled skills: <comma-separated list, or "none">
  Severity overrides: <skill: level pairs, or "none">
  Exclusions: <count> patterns

Config file: .self-care/config.json

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

To change settings:
  /self-care:config analytics on|off
  /self-care:config disable [skill]
  /self-care:config enable [skill]
  /self-care:config severity <skill> high|medium|low
  /self-care:config exclude <pattern>
  /self-care:config autofix auto|prompt|disabled

Read the full file on GitHub · 445 lines

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. 4d ago First seen · 445 lines · 8 tokens per session scan A 10c129a4b828

Subscribe to this mod's changes

config is a command published in the GitHub repository Not-Diamond/self-care (28 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 3,109 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLMagent-evaluationai-agentsclaude-codeobservabilityopentelemetry
Related

Other commands, from other repositories

optimize

Show TokenJam's savings/optimize report — where quota is going and what's recoverable. Equivalent to running tj optimize.

Metabuilder-Labs/tokenjam · 26 tokens

status

Show TokenJam's current status for every tracked agent — token usage, cost today, and active alerts. Equivalent to running tj status.

Metabuilder-Labs/tokenjam · 28 tokens

uninstall

Remove TokenJam's Claude Code integration — unwires the statusline, hooks, and OTel env vars that /onboard set up. Equivalent to running tj uninstall --yes. Does not remove the plugin itself.

Metabuilder-Labs/tokenjam · 45 tokens

doctor

Run TokenJam's health check — config, ingest endpoint, and storage. Equivalent to running tj doctor.

Metabuilder-Labs/tokenjam · 22 tokens

onboard

Set up TokenJam for this Claude Code install — wires the zero-token statusline, the resume-brief SessionStart hook, and local OTel telemetry ingest via the existing tj onboard command. Runs 100% locally, no signup.

Metabuilder-Labs/tokenjam · 49 tokens

awesome-chatgpt

Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.

taishi-i/awesome-ChatGPT-repositories · 0 tokens