Menu
Use for reusable suspicion belief recipes in software and coding-agent work.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Use when improving a Coworld player through one diagnosed failure and completed comparison evidence.
Use when compiling, validating, and uploading a notsus change as a new Crewrift policy version.
Use when decoding a Crewrift replay for authoritative deaths, survival, movement, roles, tasks, or rewards.
Use when verifying that the notsus Bedrock vote advisor fires before an advisor-sensitive evaluation.
Use when classifying a stuck, failed, empty, or zero-scoring evaluation as infrastructure or policy failure.
Use when finding and statistically confirming a reproducible Crewrift crux before changing the policy.
| name | suspicion-belief |
| description | Use for reusable suspicion belief recipes in software and coding-agent work. |
On-demand recipes (1). Trigger→action heuristics; pull the relevant one when its situation arises.
generic · ⚠ session-derived, unverified
Do not collapse two distinct failure modes into one conclusion: an action that fails on first attempt may mean a transient/preliminary condition was not met (e.g. an agent never actually reached the target rectangle -- a navigation failure), not that the action is fundamentally invalid (e.g. the target belongs to someone else). Use a first-attempt failure to trigger a RETRY of the precondition (re-navigate) before concluding the target is invalid; treating the transient failure as permanent evidence corrupts belief. Conversely, once a conclusion is legitimately reached that a target is not actionable, make that knowledge STICKY -- persist it and prevent re-committing to the same target rather than recomputing and re-forgetting each visit, since persistent negative beliefs prevent oscillation. sources: opencode:ses_1fecece4dffe779FmeajgdwhMD
