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 s-a-s-k-i-a/claude-code-timestamps/plugin install chat-timestampsWrote 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/s-a-s-k-i-a/claude-code-timestamps/timestamps)<a href="https://agentmods.dev/commands/s-a-s-k-i-a/claude-code-timestamps/timestamps"><img src="https://agentmods.dev/badge/commands/s-a-s-k-i-a/claude-code-timestamps/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/s-a-s-k-i-a/claude-code-timestamps/timestamps"><img src="https://agentmods.dev/badge/commands/s-a-s-k-i-a/claude-code-timestamps/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 | $0.00009 | $0.00625 |
| Opus 5 | $0.00005 | $0.00313 |
| Sonnet 5 | $0.00002 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00063 |
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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Current working directory: !
pwd - Arguments: $ARGUMENTS
Task
Show a timestamped timeline of the current Claude Code session. The parser locates the session transcript itself (by matching the recorded working directory), so you do not need to find or pass any transcript path.
Step 0: Inline-timestamp toggle (only if the first argument is inline)
If $ARGUMENTS begins with the word inline, this is a toggle for the
experimental inline-timestamp feature (a dim [HH:MM:SS] shown live on each
assistant message). Run the toggle script with the rest of the arguments
(on, off, toggle, or nothing/status), show its output, and stop — do
not render the timeline:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/inline-toggle.py" on
(Use the same Python launcher fallback as Step 2.) Otherwise continue below.
Step 1: Interpret arguments
Parse $ARGUMENTS into options for the parser:
- count — the first whole number, if any (e.g.
50). Otherwise omit it (defaults to 20). Never pass a non-numeric value as the count. --seconds— add this flag if the arguments containsecondsorsec(showsHH:MM:SS).--tools— add this flag if the arguments containtoolsortool(includes tool-call lines, which are hidden by default).
Step 2: Run the parser
Run the parser, passing --cwd "$PWD" plus the options from Step 1. Example for /timestamps 50 seconds:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/parse-transcript.py" 50 --seconds --cwd "$PWD"
Python launcher fallback (important for cross-platform use): run the command with python3. If that fails — on Windows python3 is often a non-functional Microsoft Store stub that prints an install message and exits non-zero — retry the identical command with py -3, and if that also fails, with python. Use the first launcher that prints a timeline.
Step 3: Present output
Show the parser's output verbatim inside a code block so the columns line up. Do not add commentary beyond the timeline.
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 · 60 lines · 0 tokens per session scan A 5d6058cb6f96
timestamps is a command published in the GitHub repository s-a-s-k-i-a/claude-code-timestamps (11 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 625 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.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.