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.
git clone --depth 1 https://github.com/pleasedodisturb/chronoclaudeWrote 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/commands/pleasedodisturb/chronoclaude/chronoclaude-config)<a href="https://agentmods.dev/commands/pleasedodisturb/chronoclaude/chronoclaude-config"><img src="https://agentmods.dev/badge/commands/pleasedodisturb/chronoclaude/chronoclaude-config/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.
<a href="https://agentmods.dev/commands/pleasedodisturb/chronoclaude/chronoclaude-config"><img src="https://agentmods.dev/badge/commands/pleasedodisturb/chronoclaude/chronoclaude-config.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.00695 |
| Opus 5 | $0.00009 | $0.00347 |
| Sonnet 5 | $0.00004 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade B, and why
chronoclaude-config scanned grade B 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 11d 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 directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Read the `env` block of `~/.claude/settings.json` (also check `settings.local.json`, and the project-scoped `.claude/settings.json` in the working directory). For each of the four variables, determine the effective st What it actually says
ChronoClaude surface configuration
Goal: report the effective on/off state of each chronoclaude surface and give the user a paste-ready settings.json snippet to toggle any of them. Do not modify any files — this command prints information only.
Surfaces and their environment variables (each defaults to on; a surface is off only when its variable is set to 0, false, off, or no, case-insensitive):
| Surface | What it does | Visible? | Env var |
|---|---|---|---|
| Passive timing block | Hidden [timing] block (local time, idle gap, last-turn duration) injected each prompt |
hidden (Claude only) | CLAUDE_TIMING_PASSIVE |
| Idle note | Visible [after 5m 2s] message when you return after >10s idle (terminal TUI; the VS Code panel does not render hook systemMessage) |
visible (on idle) | CLAUDE_TIMING_IDLE_NOTE |
| Message timestamp | Visible [HH:MM:SS] prefix on every assistant message (needs Claude Code 2.1.152+; colour auto-suppressed to plain in the VS Code panel, where raw ANSI would leak as [90m…[0m) |
visible (always) | CLAUDE_TIMING_MESSAGE_DISPLAY |
| Tool timeline | Auto-logs tool calls to a per-session JSONL the MCP get_timeline tool can read |
hidden (disk) | CLAUDE_TIMING_TIMELINE |
Steps:
-
Read the
envblock of~/.claude/settings.json(also checksettings.local.json, and the project-scoped.claude/settings.jsonin the working directory). For each of the four variables, determine the effective state: on unless explicitly set to a falsy value (0/false/off/no). You may also runprintenvfor the four variables to see what is currently exported into the session. -
Print a short table of each surface's current effective state (on/off) and where the setting came from (settings file, exported env, or default).
-
Print a paste-ready snippet to toggle. To disable a surface, add its variable set to
"0"in theenvblock; to re-enable, set"1"or remove the line. Example (disabling the visible message timestamp, leaving the rest on):{ "env": { "CLAUDE_TIMING_MESSAGE_DISPLAY": "0" } } -
Note that env-var toggles are read by the hook scripts at invocation time, so changes take effect on the next session start (or after the env is re-exported). Suggest
/reload-pluginsafter editing scripts, but for env changes a new session is the reliable path. -
Close with a one-line reminder that all surfaces are independent — e.g. you can keep the visible
[HH:MM:SS]on while turning the hidden passive block off, or vice-versa.
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.
- 11d ago First seen · 38 lines · 18 tokens per session scan B 7d346ee3d24c
chronoclaude-config is a command published in the GitHub repository pleasedodisturb/chronoclaude (6 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 695 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sofa
Search and read peer-verified solutions on Stack Overflow for Agents (SOFA) — status, search, read. Read-only CONSUME phase; clean no-op when SOFA is not configured.
create-skill
Scaffold a new scaffolding-compatible skill: an interactive flow that creates skills/ /SKILL.md from the canonical template, composes a TRIGGER/SKIP description, and validates the result.
learn
Distill a finished conversation into classified knowledge candidates and propose (never auto-apply) memory writes or a new-skill hand-off. Closes the loop between a completed agent chain and the persistent memory system.
init-rules
Scaffold opt-in path-scoped nested CLAUDE.md rule files into the project to lazy-load per-area conventions while keeping routing always-loaded.
init-openspec
Initialize OpenSpec in a project directory with the scaffolding-workflow schema.
context
Analyze and optimize Claude Code's context configuration (analyze, optimize, or reset).