refactor(discipline): rename re-anchor plugin to discipline

.claude-plugin/marketplace.json

@@ -381,8 +381,8 @@
       "tags": ["audit", "drift", "documentation", "configuration", "architecture", "verification", "claims", "skill"]
     },
     {
-      "name": "re-anchor",
-      "source": "./plugins/re-anchor",
+      "name": "discipline",
+      "source": "./plugins/discipline",
       "category": "quality",
       "tags": ["re-anchor", "discipline", "corrector", "research", "standards", "duplication", "incumbency", "terseness", "upstream", "conformance", "selection", "communication", "determinism", "consistency", "skills", "audit", "skill"]
     },
@@ -486,6 +486,7 @@
     "claude-config-audit": "claude-config",
     "boris": "playbooks",
     "thariq-skills": "playbooks",
-    "fable-5-playbook": "playbooks"
+    "fable-5-playbook": "playbooks",
+    "re-anchor": "discipline"
   }
 }

README.md

@@ -98,7 +98,7 @@ user opts in with `/plugin enable`; an existing install is never flipped by cata
 - [`mcp-tools`](plugins/mcp-tools) — Audits MCP server tool definitions against MCP-specification and Anthropic tool-design criteria and reports a per-tool PASS/WARN/FAIL scorecard covering description, parameters, naming, and annotations. Language-agnostic — Python (FastMCP), TypeScript, and .NET.
 - [`review`](plugins/review) — Code-review toolkit: six read-only reviewer agents (code, security, architecture, doc drift, build/test/lint, CI-log audit) plus two orchestration skills — a single-lens quality gate and a multi-surface review fan-out with severity-ranked, deduplicated findings.
 - [`codebase-health`](plugins/codebase-health) — Repo-wide drift audit between docs, config, code, and architecture: verifies every factual claim against reality via parallel subagent fan-out, severity-rates findings, and reports read-only, delegating remediation to the implementation/verification lanes. Audit dimensions are configurable through a tracked .claude/codebase-health.md config file written by the setup skill.
-- [`re-anchor`](plugins/re-anchor) — 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 — assumptions, asserted facts, concrete specifics, 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 — 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 — 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 deterministic sub-work — 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 judgement), 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 sweep-all-disciplines, a posture-batch runbook — not a corrector but a declared second species that composes them: it fans out an audit-only subagent per in-scope corrector, then applies 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. Firing one is a re-anchor, not an accusation; the audit may return clean.
+- [`discipline`](plugins/discipline) — 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 — assumptions, asserted facts, concrete specifics, 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 — 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 — 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 deterministic sub-work — 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 judgement), 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 sweep-all, a posture-batch runbook — not a corrector but a declared second species that composes them: it fans out an audit-only subagent per in-scope corrector, then applies 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. Firing one is a re-anchor, not an accusation; the audit may return clean.
 
 ### Maintenance
 

docs/conventions/loop-lane/README.md

@@ -178,12 +178,12 @@ start; new automated intake arriving mid-cycle is **reported, never chased**, so
 bot cannot hold a drain open indefinitely.
 
 **Subagent discipline preamble.** Every subagent a lane dispatches carries a standing discipline
-preamble. When the `re-anchor` plugin is installed, the dispatch prompt invokes its sweep —
-sweep-all-disciplines, use-your-skills, do-your-research; when it is absent, the dispatch prompt
+preamble. When the `discipline` plugin is installed, the dispatch prompt invokes its sweep —
+sweep-all, use-your-skills, do-your-research; when it is absent, the dispatch prompt
 inlines the equivalent standing instructions (verify claims against authoritative sources before
 acting, prefer installed skills over ad-hoc approaches, and re-check work against the active
 conventions). The reference is presence-gated with this inline fallback per the
-[seam-phrasing convention](../seam-phrasing/README.md) — `re-anchor` is never a hard dependency.
+[seam-phrasing convention](../seam-phrasing/README.md) — `discipline` is never a hard dependency.
 
 ## 5. Consumers and launch surfaces
 

plugins/re-anchor/.claude-plugin/plugin.json → plugins/discipline/.claude-plugin/plugin.json

@@ -1,8 +1,8 @@
 {
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
-  "name": "re-anchor",
-  "version": "0.8.0",
-  "description": "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 — assumptions, asserted facts, concrete specifics, 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 \u2014 no copied content, internal-name coupling, or closed capability lists), reason-dont-recite (interrogate inherited content \u2014 precedent is evidence of what is, never self-justifying authority), tighten-your-output (terseness discipline \u2014 fewer words or lines with no loss of meaning or correctness), recheck-against-upstream (existing state is not evidence of its own correctness \u2014 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 deterministic sub-work \u2014 counts, diffs, sorts, transforms, and scaffolds \u2014 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 judgement), use-your-skills (actually use the skills already in context \u2014 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 \u2014 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 \u2014 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 sweep-all-disciplines, a posture-batch runbook — not a corrector but a declared second species that composes them: it fans out an audit-only subagent per in-scope corrector, then applies 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. Firing one is a re-anchor, not an accusation; the audit may return clean.",
+  "name": "discipline",
+  "version": "0.9.0",
+  "description": "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 — assumptions, asserted facts, concrete specifics, 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 \u2014 no copied content, internal-name coupling, or closed capability lists), reason-dont-recite (interrogate inherited content \u2014 precedent is evidence of what is, never self-justifying authority), tighten-your-output (terseness discipline \u2014 fewer words or lines with no loss of meaning or correctness), recheck-against-upstream (existing state is not evidence of its own correctness \u2014 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 deterministic sub-work \u2014 counts, diffs, sorts, transforms, and scaffolds \u2014 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 judgement), use-your-skills (actually use the skills already in context \u2014 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 \u2014 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 \u2014 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 sweep-all, a posture-batch runbook — not a corrector but a declared second species that composes them: it fans out an audit-only subagent per in-scope corrector, then applies 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. Firing one is a re-anchor, not an accusation; the audit may return clean.",
   "author": {
     "name": "Melodic Software",
     "email": "info@melodicsoftware.com"

plugins/re-anchor/CHANGELOG.md → plugins/discipline/CHANGELOG.md

@@ -1,8 +1,57 @@
 # Changelog
 
-All notable changes to the `re-anchor` plugin are documented here. Format follows
+All notable changes to the `discipline` plugin are documented here. Format follows
 [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); this plugin uses semantic versioning.
 
+Entries below `0.9.0` were released under the plugin's former name, `re-anchor`.
+
+## [0.9.0]
+
+### Changed
+
+- **Renamed the plugin `re-anchor` -> `discipline`; every skill moves from
+  `/re-anchor:*` to `/discipline:*`.** Three defects in the old name, each verified rather
+  than asserted. (1) It was a bare verb — the sole outlier among 60 sibling plugins, all of
+  which are nouns or noun-phrases. (2) The `re-` prefix presumes a prior anchoring, but the
+  shared method's documented conversation-start case is a *first* posture-set with nothing
+  yet to re-anchor. (3) "Anchoring" is the cognitive-bias term of art — the plugin was named
+  after a bias `reason-dont-recite` exists to fight.
+
+  `discipline` is the word the plugin already used for itself 189 times ("a drift corrector
+  for research discipline"), so the name is the authors' own revealed vocabulary rather than
+  a coinage. Container/member word overlap (`/discipline:sweep-all`) is routine in this
+  marketplace — `/planning:plan`, `/debugging:debug`, `/visualization:visualize`,
+  `/work-items:work` all ship that shape.
+
+  Candidates rejected on evidence: `steering` (fails the conversation-start case; collides
+  with Codex "mid-turn steering" and ML "activation steering"), `calibration` (implies
+  adjustment against a measurable reference with quantified error — this work is
+  judgment-based, the same objection that rules out `invariants`), `salience` (accurate but
+  not a word a reader reaches for first), `grounding` (slug already taken).
+
+  **Migration, and its one manual step.** On Claude Code >= 2.1.193 the marketplace
+  `renames` map is followed at session start: an enabled `re-anchor@melodic-software`
+  loads as `discipline` instead of failing `plugin-not-found`, and the old key is
+  rewritten to the new one in the user, project, and local settings scopes for BOTH
+  `enabledPlugins` and `pluginConfigs` — so configured `batch_exclude` / `batch_promote` /
+  `batch_demote` / `research_deep_verification` values move across with no action. Two
+  edges: managed and policy scopes are read-only to Claude Code and are not rewritten, and
+  if `discipline@melodic-software` already carries its own `pluginConfigs` entry the new
+  id's values win and the old ones are dropped rather than merged. Below 2.1.193 nothing
+  is lost — the rename simply does not migrate, and the old name reports
+  `plugin-not-found`.
+
+  What the map does NOT rewrite is any invocation stored outside settings. In a consuming
+  repository's instruction files, an agent prompt, a saved workflow, or automation,
+  `/re-anchor:<skill>` must become `/discipline:<skill>` and `/plugin configure re-anchor`
+  must become `/plugin configure discipline` by hand.
+
+- **Renamed `sweep-all-disciplines` -> `sweep-all`.** Removes the one genuinely awkward
+  pairing the plugin rename introduced (`/discipline:sweep-all-disciplines`). This leaf
+  rename has NO compatibility entry — the `renames` map keys plugins, not skills — so
+  `/re-anchor:sweep-all-disciplines` becomes `/discipline:sweep-all` and any stored
+  reference to the old skill name must be updated by hand.
+
 ## [0.8.0]
 
 ### Added