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.
npx agentmods add skills/alexei-led/cc-thingz/evolving-confignpx skills add alexei-led/cc-thingz --skill evolving-configgit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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.
[](https://agentmods.dev/skills/alexei-led/cc-thingz/evolving-config)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/evolving-config"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/evolving-config.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.01192 |
| Opus 5 | $0.00046 | $0.00596 |
| Sonnet 5 | $0.00018 | $0.00238 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
evolving-config scanned grade A with 1 finding 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 6d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Codex: `.codex/`, `~/.codex/config.toml`, project config, profiles, sandbox, approvals, MCP, skills, subagents. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolving Agent Configuration
Audit AI coding-agent configuration with local evidence first and current vendor docs second. Default to review-only. Apply fixes only after explicit approval.
Read first
references/RUBRIC.mdfor shared review dimensions and severity.references/platforms/claude-code.mdfor Claude Code surfaces.references/platforms/codex.mdfor Codex surfaces.references/platforms/pi.mdfor Pi surfaces.references/apply-fixes.mdonly when the user asks to fix or passes--fix.
Modes
Review-only is the default for prompts such as "review my config", "audit config", "check setup", or "what should I improve".
Fix mode starts only when the user explicitly asks for changes or passes --fix.
Even in fix mode, ask before risky changes: permissions, sandbox policy, hooks,
MCP servers, model routing, deletes, moves, broad rewrites, or private config.
Scope
Review these AI-agent configuration surfaces:
- Instruction files:
AGENTS.md,CLAUDE.md, command prompts, skill and agent bodies. - Claude Code:
.claude/, user/project/local settings, hooks, skills, agents, MCP, permissions. - Codex:
.codex/,~/.codex/config.toml, project config, profiles, sandbox, approvals, MCP, skills, subagents. - Pi:
.pi/,~/.pi/agent/, settings, packages, skills, extensions, prompts, themes, context files. - Plugin/package manifests and source-to-generated export rules.
- chezmoi or dotfile copies only when deployment is part of the request.
Do not review:
- app runtime config
- git hook hygiene
- score-only instruction prose or prompt quality; use
reviewing-instructions - product docs
- source-code quality
- generated output as the source of truth
Workflow
- Identify the requested platform, config root, and mode.
- If ambiguous, list detected config surfaces and ask which to audit.
- Inventory relevant files with paths, sizes, and source/generated status.
- Read current files before recommending changes.
- Use the platform reference and shared rubric to check expected structure, high-risk settings, invocation fit, and always-loaded context cost.
- When the audit touches skills, agents, prompts, or package manifests, inspect thin-router risk, weak pointers to must-read support files, and whether plugin grouping forces unrelated instructions into startup context.
- Use official docs or changelogs when syntax, feature availability, or deprecation status is uncertain.
- Use broad web research only for gaps or ecosystem comparisons; do not recommend changes from uncited blogs alone.
- Classify findings by impact and disruption.
- In fix mode, apply only approved changes and verify with available validation commands.
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.
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.
- 6d ago First seen · 133 lines · 92 tokens per session scan A 1edaaa679baa
evolving-config is a skill published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,192 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
peekaboo
Provides runtime observation and interaction for native macOS interfaces through accessibility state and screenshots. Use when the task depends on visible or interactive state in a running SwiftUI/AppKit app: what is rendered, focused, selected, enabled, reachable through menus/windows/dialogs, or experienced across a…
mobile-flows-maestro
This skill should be used when Maestro is explicitly requested or already present and the task is to author, run, or debug iOS/Android Maestro flows; use Maestro MCP; or handle Maestro selectors, system UI, permissions, Keychain, JavaScript, waits, device state, flakiness, or CI. Evidence includes a .maestro directory…
validate-mobile
Run a Maestro flow on an explicitly selected iOS or Android device and report behavioral evidence.
validate-api
Run the project's Hurl scenarios with an OIDC access token passed as a secret variable.
backend-architecture
This skill should be used for consequential backend architecture decisions: module or service boundaries; modular monoliths versus independent services; service extraction and data migration; data ownership and consistency; synchronous, event-driven, actor/stateful, or pipeline designs; failure isolation…
esp32-expert
This skill should be used for ESP32-specific hardware and runtime work in ESP-IDF, Arduino-ESP32, or PlatformIO projects: target/build detection, FreeRTOS tasks and ISRs, memory/DMA, peripherals, power, networking/security, OTA, crash diagnosis, and unattended reliability. Trigger on "debug this ESP32 crash", "review…