Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →berabuddies/session-watchdog
Monitor session context levels and proactively save checkpoints before compaction.
Passed 16 of 20 test cases with the skill, and 8 of 20 without it.
and 7 more in the full report
9 fixed9 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
In the session watchdog framework, what token range defines the Safe operational tier where normal conversation proceeds without warnings or checkpoints?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies 0 to 140k tokens as the Safe level range. | Missed | Passed |
The instructions your model reads when the skill loads.
Monitors context levels, warns before compaction, and saves checkpoints to preserve important information.
| Level | Tokens | Action |
|---|---|---|
| Safe | 0-140k | Normal operation |
| Warning | 140k-160k | Warn user, save checkpoint |
| Critical | 160k-197k | Warn + stop unless urgent |
| Full | 197k+ | Compaction imminent |
Before each session and periodically during long conversations:
session_status
Check the contextTokens field from the response.
When approaching 80% (160k tokens):
Save checkpoint to memory file:
Alert user: Say: "⚠️ Approaching context limit (~160k tokens). Saving checkpoint to memory before continuing."
Ask user:
test cases passed, vs 8 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.