Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pleasedodisturb/chronoclaude/plugin install 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/timestamps)<a href="https://agentmods.dev/commands/pleasedodisturb/chronoclaude/timestamps"><img src="https://agentmods.dev/badge/commands/pleasedodisturb/chronoclaude/timestamps/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/timestamps"><img src="https://agentmods.dev/badge/commands/pleasedodisturb/chronoclaude/timestamps.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 | $0.00008 | $0.00362 |
| Opus 5 | $0.00004 | $0.00181 |
| Sonnet 5 | $0.00002 | $0.00072 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
timestamps 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 10d 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.
What it actually says
Context
- Current working directory: !
pwd - Arguments: $ARGUMENTS
Task
Display a timestamped timeline of messages from the current conversation transcript.
Step 1: Parse and display
Extract the count from $ARGUMENTS. If it is a positive integer, use it. Otherwise default to 20. Reject any non-numeric value — do not pass arbitrary strings to the script.
Run the parser, passing the current working directory (from the Context section above) via --cwd and the validated count. The script locates the right transcript by matching the working directory recorded inside Claude Code's transcript files — do not try to reconstruct the ~/.claude/projects/ path yourself (that breaks for paths containing dots, spaces, or other rewritten characters):
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/parse-transcript.py" --cwd "<cwd>" "<count>"
Replace <cwd> with the current working directory shown in the Context section, and <count> with the validated integer.
If the script prints "No transcript found …", relay that message to the user and stop.
Step 2: Present output
Display the script output in a code block so columns align. Do not add commentary beyond the timeline.
Constraints
- Never read the transcript with the Read tool — files can be very large.
- Only pass validated integers as the count argument.
- Pass the working directory exactly as shown in the Context section; do not invent project paths.
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.
- 10d ago First seen · 40 lines · 8 tokens per session scan A 833d216cea20
timestamps is a command published in the GitHub repository pleasedodisturb/chronoclaude (6 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 362 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 2026-08-31.
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).