Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →alinaqi/mnemos
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies
Passed 16 of 19 test cases with the skill, and 3 of 19 without it.
and 21 more in the full report
15 fixed3 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
When beginning a new multi-step development task with task ID session-42, what is the initial step recommended for tracking our core objective in memory?
| Checked | Without skill | With skill |
|---|---|---|
| Runs mnemos add goal specifying the objective text and task identifier | Missed | Passed |
| Attaches the flag --task-id session-42 to the goal creation command | Missed | Passed |
The instructions your model reads when the skill loads.
Mnemos prevents lossy context compaction from destroying the structured knowledge you need most. It treats your working memory as a typed graph (MnemoGraph) where different types of knowledge have different eviction policies:
Mnemos monitors 4 dimensions of "agent fatigue" — all passively observed from hook data, no manual input needed:
| Dimension | Weight | Signal Source | What It Measures |
|---|---|---|---|
| Token utilization | 0.40 | Statusline JSON | How full the context window is |
| Scope scatter | 0.25 | PreToolUse file paths | How many directories the agent is bouncing between |
| Re-read ratio | 0.20 | PreToolUse Read calls | How often the agent re-reads files it already read (context loss) |
| Error density | 0.15 | PostToolUse outcomes | What fraction of tool calls are failing (agent struggling) |
Fatigue states and actions:
| State | Score | Action |
|---|---|---|
| FLOW | 0.0–0.4 | Normal operation |
| COMPRESS | 0.4–0.6 | Micro-consolidation runs (compress 3 ResultNodes, evict 1 cold ContextNode) |
| PRE-SLEEP | 0.6–0.75 | Checkpoint written, consolidation runs |
| REM | 0.75–0.9 | Emergency checkpoint, consider wrapping up |
| EMERGENCY | 0.9+ | Checkpoint written, hand off immediately |
fatigue.json on every API calltest cases passed, vs 3 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.