Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →athola/war-room-checkpoint
Assesses decision reversibility and risk at critical checkpoints.
Passed 19 of 22 test cases with the skill, and 5 of 22 without it.
and 13 more in the full report
16 fixed5 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
When a decision point is evaluated and assigned to express mode, what boolean value is returned for should_escalate and what value is assigned to decision_type?
| Checked | Without skill | With skill |
|---|---|---|
| The should_escalate field is set to false. | Passed | Passed |
| The decision_type field is set to Type 2. | Missed | Passed |
The instructions your model reads when the skill loads.
Lightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.
Run make attune-test from the repository root to verify checkpoint
logic still works after changes.
This skill is not invoked directly by users. It is called by other commands (e.g., /do-issue, /pr-review) at critical decision points to:
| Command | Trigger Conditions |
|---|---|
/do-issue | 3+ issues, dependency conflicts, overlapping files |
/pr-review | >3 blocking issues, architecture changes, ADR violations |
/architecture-review | ADR violations, high coupling, boundary violations |
/fix-pr | Major scope, conflicting reviewer feedback |
| Situation | Use instead |
|---|---|
| A user asks for deliberation directly | Skill(attune:war-room) |
| The decision is cheap to reverse (high RS) | Proceed without a checkpoint |
| A panel already ruled on this decision | The prior verdict |
This skill decides whether deliberation is warranted and returns fast when it is not. A command that checkpoints every decision pays the scoring cost to be told to proceed almost every time, and re-checkpointing a settled call re-litigates it.
test cases passed, vs 5 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.