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 Kepei-Lei102/breakwatch/plugin install breakwatchWrote 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/kepei-lei102/breakwatch/take-a-break)<a href="https://agentmods.dev/skills/kepei-lei102/breakwatch/take-a-break"><img src="https://agentmods.dev/badge/skills/kepei-lei102/breakwatch/take-a-break/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/kepei-lei102/breakwatch/take-a-break"><img src="https://agentmods.dev/badge/skills/kepei-lei102/breakwatch/take-a-break.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 | $0.00106 | $0.01489 |
| Opus 5 | $0.00053 | $0.00745 |
| Sonnet 5 | $0.00021 | $0.00298 |
| Haiku 4.5 | $0.00011 | $0.00149 |
Grade B, and why
take-a-break 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.
Streak tracking is automatic — two hooks in `~/.claude/settings.json` run How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Take a break
Streak tracking is automatic — two hooks in ~/.claude/settings.json run
~/.claude/worklog/breakwatch.py on every prompt and every turn end, in every
project. This skill is the manual side: reading the data and tuning it.
Commands
python3 ~/.claude/worklog/breakwatch.py status # current streak vs threshold
python3 ~/.claude/worklog/breakwatch.py report # last 14 days + did nudges work
python3 ~/.claude/worklog/breakwatch.py report 30 # any window
python3 ~/.claude/worklog/breakwatch.py recalibrate # propose new thresholds
python3 ~/.claude/worklog/breakwatch.py recalibrate --apply # write them
python3 ~/.claude/worklog/breakwatch.py devices # what output is detected, and the volume it picks
python3 ~/.claude/worklog/breakwatch.py alarm # fire a test alert, hear what it sounds like
python3 ~/.claude/worklog/breakwatch.py backfill # re-seed from transcripts (safe to re-run)
Warn before running alarm — it overrides mute by design. Check they are not
about to teach or present.
Installed as a plugin instead? The script is at
$CLAUDE_PLUGIN_ROOT/hooks/breakwatch.py; the data stays in ~/.claude/worklog/
either way, so history survives a reinstall.
Before changing anything, read HARNESS.md
(~/.claude/worklog/HARNESS.md on a manual install; beside the plugin root
otherwise.)
It carries the design invariants, and two of them govern every retune:
thresholds tune how often the system speaks, never whether the user listens,
and loosening is bounded while tightening is free. Ignoring compliance data
when setting thresholds looks like throwing away the most relevant signal. It is
the opposite: every retune is requested moments after a nudge caused friction,
so reasoning from compliance walks the system to silence by a sequence of
individually sensible steps. recalibrate enforces this — it reports the
compliance rate, then refuses to move thresholds with it.
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 · 103 lines · 106 tokens per session scan B b3a5a3703968
take-a-break is a skill published in the GitHub repository Kepei-Lei102/breakwatch (1 stars, last pushed 29d ago), licensed MIT. It adds 106 tokens to every session and 1,489 once invoked, about $0.0005 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 skills, from other repositories
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
checkpoint
Maintain a thirty-second return point (CHECKPOINT.md) and a single-use handoff (HANDOFF.md) so any session can resume mid-goal without archaeology. Use when a large unit of work finishes, a session enters its closing stretch, when leaving instructions for the next session, or when resuming and the user asks where…
handoff-create
Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current status, next steps, and code snippets. Use before ending a session or handing work to another agent.
schedule
Own the calendar as a ledger - fixed dates, event-triggered entries, and launch bundles that fire together or not at all. Use when work has deadlines or submission windows, reacts to outside events (an outage, a deprecation, a competitor incident), or needs several deliverables published near-simultaneously.
sitrep-panel
Keep a live local HTML report updated as you work on a task — a status board, a running "what's happening now" narrative, screenshots, and a newest-first log — served on localhost so the user can watch progress in a browser tab instead of reading the transcript. Use when the user invokes /sitrep-panel, asks for a…
handoff-update
Update an existing handoff document with current session progress. Applies section-specific merge rules: append-only for Work Done (never deletes history), replace for Status and Next Steps, merge for Files and Discoveries. Falls back to creating a new handoff if no source file is found.