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 skills add AraneaDev/claude-timestamp --skill timestampsgit clone --depth 1 https://github.com/AraneaDev/claude-timestampWrote 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/araneadev/claude-timestamp/timestamps)<a href="https://agentmods.dev/skills/araneadev/claude-timestamp/timestamps"><img src="https://agentmods.dev/badge/skills/araneadev/claude-timestamp/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/skills/araneadev/claude-timestamp/timestamps"><img src="https://agentmods.dev/badge/skills/araneadev/claude-timestamp/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 | $0.00039 | $0.00407 |
| Opus 5.5 | $0.00016 | $0.00163 |
| Sonnet 5.5 | $0.00008 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
timestamps scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Configure claude-timestamp
Use the repository's CLI so configuration is parsed and validated by the same
code used by the hooks. Run commands from the Git root, or resolve the root
with git rev-parse --show-toplevel.
Read schema.json first when the user asks for a setting you do not recognize.
It is the source of truth for keys, accepted values, aliases, presets, and
marker grammar. Do not silently invent or accept a value the schema rejects.
Show current settings with:
bash "$(git rev-parse --show-toplevel)/hooks/scripts/setup.sh" --show
Use the matching CLI flag for a requested change, for example:
bash "$(git rev-parse --show-toplevel)/hooks/scripts/setup.sh" --tz=Europe/Amsterdam
bash "$(git rev-parse --show-toplevel)/hooks/scripts/setup.sh" --display=short
bash "$(git rev-parse --show-toplevel)/hooks/scripts/setup.sh" --color=none
bash "$(git rev-parse --show-toplevel)/hooks/scripts/setup.sh" --tool-timing=on
Use --help and the flag table in hooks/scripts/setup.sh for the complete
mapping. For several changes, pass several flags in one invocation. Report
what changed and say that it takes effect on the next message.
For measured reports, use --session or --stats; do not estimate duration
from the conversation. History stores timings only, never message text.
Codex receives model-facing timing context and the end-of-session summary from
its hooks. It has no Claude-style MessageDisplay event, so the visual marker
is available in Claude Code but not in Codex.
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 Changed 0bd3a060bf1b
- 1mo ago First seen · 41 lines · 39 tokens per session scan A 85aa484d2448
timestamps is a skill published in the GitHub repository AraneaDev/claude-timestamp (3 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 407 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
monday-planning
Suggest a weekly training structure from recent load and deliver the plan.
add-source
Interactively add a new source to feed-sources.md with type inference, https and name-uniqueness validation, and category checking against feed-categories.md. Appends a formatted row to the Active Sources table. Invoke with /hermitd-feed:add-source.
when-done-switch-to
Arm a deferred model or effort switch. Use for "when done switch to", "after this drop to sonnet", or "switch model when idle".
fresh-start
Continue in a new chat without losing anything — writes a compact handoff to paste into a fresh conversation. Use whenever the user wants to move to a new chat or conversation, hits usage limits, says replies got slow or Claude forgets earlier details, or the conversation has grown long.
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.
monitor-activate
Activate the resident heartbeat and routine monitors.