by Melodic Software
Discipline correctors that re-anchor a standing rule mid-session, then audit both the work in flight and the pre-existing state and choices it trusts, and correct what has drifted: do-your-research (research and no-assumptions discipline; sibling do-your-research-deep escalates to a typed full inventory of the session's claims, namely assumptions, asserted facts, concrete specifics, and load-bearing premises, verified at a configurable depth and reported as a per-item ledger), follow-our-standards (alignment to the consuming org's engineering conventions), point-dont-copy (pointer-over-copy discipline: no copied content, internal-name coupling, or closed capability lists), reason-dont-recite (interrogate inherited content, since precedent is evidence of what is, never self-justifying authority), tighten-your-output (terseness discipline: fewer words or lines with no loss of meaning or correctness), recheck-against-upstream (existing state is not evidence of its own correctness, so audit config, code, and infra against current official upstream docs; sibling recheck-against-upstream-deep fans subagents doc-by-doc over a whole subsystem), pick-for-the-problem (tool, library, framework, and approach selection fitted to the problem, not reached for out of habit, availability, incumbency, or preconception), mind-your-maxims (cooperative-communication discipline per Grice plus the AI-augmented transparency maxim), script-the-deterministic-work (offload the deterministic sub-work of counts, diffs, sorts, transforms, and scaffolds to a script that runs, reserving model output for judgment over its real output; the audit runs both ways, also catching an existing script that over-reaches into judgment), use-your-skills (actually use the skills already in context: scan the listing, map the task, invoke the fitting skill instead of reinventing it, and name skills when delegating to a subagent), and reuse-or-replace (anti-fragmentation: new work reuses an established way of doing something or openly replaces it (migrate the old uses, record the decision), never silently stands up a second parallel way; divergence is allowed but owes a recorded reason proportional to blast radius), and scrutinize-dont-coast (adversarial self-scrutiny: stop coasting on your own recent output and re-examine whether it is sound, not merely confidently produced, through a fresh-context pass blind to the reasoning that made it, then remediate with the user; it stops the trajectory first and remediates collaboratively rather than autonomously). Plus further species that are not correctors (examples, not a fixed list, since each skill's own description is authoritative), including setup, sweep-all, a posture-batch runbook that composes them by fanning out an audit-only subagent per in-scope corrector, then applying the corrections on the main thread in a fixed order, with batch membership and order set by each corrector's own colocated tier metadata and an optional userConfig overlay, and wait-what, a one-shot user-invoked-only communication repair: type /discipline:wait-what when the last message did not land and the model re-pitches it, backing up as far as needed, adding the missing context, in ASD-STE100 Simplified Technical English, using the project's ubiquitous language; never model-invoked and never in the batch, and hold-my-hand, a standing session posture (neither a corrector nor a one-shot): it partitions the remaining work into phases and presents only the current one, never the phases after it beyond a one-line count, each phase naming where to be, numbered steps with exact commands, the expected output, the common failure, who performs each step, and the exact reply that advances; it stays out of the batch because a sweep must never impose a delivery posture the user did not ask for. Firing a corrector is a re-anchor, not an accusation; the audit may return clean.
Claude Code18 Skills