discipline

Re-anchor research and no-assumptions discipline mid-session, then self-audit and correct the current work. Use when: 'do your research', 'you're guessing', 'cite that', 'stop assuming', 'evidence, not vibes', 'you skipped verification', 'that's training-data recall', 'research this properly', 'fact-check that', 'make sure that's right', or at conversation start to set the posture. For a heavy verification fan-out, a typed full inventory of the session's claims verified at a configurable depth, use the sibling do-your-research-deep.

Escalate research discipline to a heavy verification fan-out over a TYPED FULL INVENTORY of the session's claims, assumptions, asserted facts, concrete specifics (paths, defaults, flags, signatures), and load-bearing premises, verifying each against a primary source at a configurable depth (tiered by default, or full), then report a per-item ledger with verdict, source, source tier, consensus count, and recency. Use when: 'deep research pass', 'verify every claim', 'audit all our claims', 'fact-check everything', 'go make sure those are all right', 'we've made a lot of load-bearing claims', or when the session's own judgment is the suspected bias across many claims. For a single or small inline fact-check ('fact-check that'), use the sibling do-your-research.

Re-anchor to the organization's engineering standards, then audit the work in flight against them and correct violations with doc citations. Use when: 'follow our standards', 'follow the standards', 're-anchor to standards', 'does this match our conventions', 'audit against standards', 'you're drifting from our conventions', or at conversation start on a repo governed by shared conventions.

Hold the user's hand through a long multi-step job. Partition the remaining work into phases and present ONLY the current one, never the phases after it beyond a one-line 'Phase 1 of 8' count. Each phase names where to be, numbered steps with exact commands, the expected output, the common failure, who performs each step, and the exact reply that advances. Once invoked, this holds for the rest of the session. Use when: 'hold my hand', 'walk me through this', 'one step at a time', 'one phase at a time', 'don't show me the next step yet', 'guide me through all of this', 'exact steps', 'hand-hold'. This is a STANDING posture that withholds later steps: adhd:shape sets action-first formatting for every response and shows the whole list, adhd:clarify reshapes one dense message already on screen, wizard:generate writes a bash script the human runs with no assistant in the loop, and session-flow:workflow routes to the next stage without scripting its steps.

Re-anchor cooperative-communication discipline, Grice's conversational maxims plus the AI-augmented transparency maxim, then audit recent responses and agent-authored artifacts for what the reader actually needed: completeness in both directions, relevance, clarity, and disclosed boundaries. Use when: 'mind your maxims', 'communication quality', 'answer what I asked', 'you buried the answer', 'you didn't answer the question', 'too vague', 'stay on topic', 'is this clear', 'grice', 'maxims', or at conversation start to set the communication posture.

Re-anchor the discipline that a tool, library, framework, language, or approach is chosen to fit the actual problem, not reached for out of habit, availability, incumbency, or preconception, then audit the selection in flight and re-derive it from the problem. Use when: 'pick for the problem', 'right tool for the job', 'which library should we use', 'what framework', 'should we build this or use X', 'is this the right approach', 'you defaulted to X', 'we always reach for X', 'evaluate the options', 'choose a dependency', or at conversation start on a build-vs-buy or technology-selection decision.

Re-anchor pointer-over-copy discipline, then audit the work in flight for copied content, internal-name coupling, and closed capability lists, and correct by pointing at the living source. Use when: 'point don't copy', 'you copied that', 'don't duplicate the docs', 'cite instead of paste', 'link don't restate', 'you enumerated the tools', 'that couples to internal names', 'this will drift', or at conversation start on documentation work.

Re-anchor the discipline that inherited content is evidence of what is, never self-justifying authority, then audit the work in flight for decisions coasting on precedent and re-derive them from first principles. Use when: 'reason don't recite', 'why is it this way', 'challenge that convention', 'you're deferring to precedent', "that's just how it's done", 'question the inherited design', 'stop reciting the docs', 'is this actually right', or at conversation start on legacy or inherited code. Note the shared phrasing: this skill challenges whether a convention should STILL hold and re-derives it from first principles; when the ask is instead to RECOVER the original reasoning from the historical record, review discussion, tickets, design documents, that is '/discovery:trace-intent' if the discovery plugin is installed, and otherwise read that record directly before challenging what it says.

Re-anchor the discipline that existing state, config, code, docs, infra, is not evidence of its own correctness, then audit the surface in flight against CURRENT official upstream docs and classify each divergence. Use when: 'recheck against upstream', 'check this against the docs', 'is our config still current', 'did upstream change', 'are we still doing this right', 'verify against the official docs', 'this may have drifted from upstream', 'audit our setup against the vendor docs', or at conversation start on config, infra, or integration work.

Escalate upstream-conformance discipline to a heavy fan-out: dispatch fresh-context subagents doc-by-doc over a whole subsystem, framework, or repo, comparing each surface against its CURRENT official upstream docs, then report an inline divergence ledger. Use when: 'recheck the whole subsystem against upstream', 'audit every surface against the docs', 'deep upstream conformance pass', 'check the entire framework config against upstream', 'we depend on a lot of upstream surfaces and they may have drifted'. For a single inline recheck of the surface in play, use the sibling recheck-against-upstream.

Re-anchor the anti-fragmentation discipline that when an established way of doing something already exists, an idiom, structure, naming shape, doc format, or process, new work REUSES it or openly REPLACES it (migrate the old uses, record the decision); never a silent second, parallel way alongside. Then audit the work in flight for unexplained divergence from an established way. Replacing is first-class when evidence backs it, the sin is the SILENT second way, not divergence itself. Use when: 'reuse or replace', 'we already have a way of doing this', 'don't invent a second way', 'keep it one way', 'follow the existing pattern or replace it', 'be consistent', 'you added a parallel way', 'this diverges from how we do it elsewhere', or at conversation start on work that extends an established codebase, structure, or process.

Re-anchor the discipline that purely deterministic sub-work, counting, diffing, sorting, transforming, matching, arithmetic, gets a script that runs and returns real output, with the model reasoning only afterward over that output; then audit the work in flight for transforms executed by hand. Use when: 'script the deterministic work', 'you should have scripted that', 'don't eyeball that', 'you counted that by hand', 'compute that, don't estimate', 'diff it with a tool', 'stop hand-tallying', 'run it instead of guessing', or at conversation start on count-, diff-, or transform-heavy work. Not for authoring a requested script ('script it' as a work order), and not for a first-turn count/diff/transform work order ('diff these files', 'count the routes', 'convert all of these'). Doing that task with a tool is just doing the task; this corrector fires on drift.

Re-anchor adversarial self-scrutiny. Stop coasting on recent output, re-examine whether it is actually sound (not merely confidently produced) through a fresh-context pass blind to the reasoning that made it, and remediate with the user. Use when: 'scrutinize don't coast', 'wait, stop', 'are you sure about this', 'second-guess this', 'poke holes in what you just did', "you're steamrolling", 'push back on yourself', with an optional focus to scope the re-examination, or at conversation start to set the posture.

Validate the discipline plugin's configuration, the posture-batch overlay and do-your-research-deep's verification depth, and explain how to change it through Claude Code's plugin configuration prompt. Use when: 'set up discipline', 'configure discipline', 'discipline setup', 'is discipline configured', 'what's in my posture batch', 'what's my deep-research depth', or the user wants to adjust which correctors the batch runs or how deeply the research fan-out verifies. Actions: check (read-only verification, default and only action. This plugin's entire configuration is native userConfig, so there is nothing an apply could write).

Compose this plugin's discipline correctors into ONE batched pass. Requires conversation-inheriting fork subagents (`subagent_type: fork`); without fork mode it degrades to the posture digest and audits nothing. At conversation start it instead reports a cheap posture digest (which disciplines are in scope) with no audit. Use when: 'sweep all disciplines', 'ground ourselves', 're-anchor everything', 'run the whole re-anchor bundle', 'posture batch', 'set our posture before we start', 'batch the correctors', or at conversation start to set posture across every standing discipline at once. Membership is each corrector's own tier metadata; for a single discipline, invoke that corrector directly.

Re-anchor terseness discipline, say markdown in fewer words without semantic loss, write code in fewer lines when readability holds, then audit the work in flight for avoidable verbosity and tighten it. Use when: 'tighten your output', 'tighten this', 'too verbose', 'say it in fewer words', 'this is bloated', 'trim the code', 'simpler form', 'cut the wordiness', 'be more concise', or at conversation start on prose- or code-heavy work.

Re-anchor the discipline of actually using the skills available in the session. Scan the in-context skill listing, map the conversation and the task to the skills that fit, and invoke them instead of reinventing their procedure from scratch. Then audit the work in flight for a skill that should have fired and did not, and route forward. Invoke it now, and name the relevant skills when delegating to a subagent. Use when: 'use your skills', 'you have a skill for that', 'did you check your skills', 'there's a skill for this', 'you reinvented that', 'you skipped the skill', 'invoke your skills', or at conversation start to set the posture that available skills get used.

Stop. That last message did not land. Re-pitch it: back up as far as needed, add the context that was missing, write in ASD-STE100 Simplified Technical English, and use the project's own ubiquitous language. Type /discipline:wait-what the moment the reader notices they are skimming; only the reader knows when they stopped following.