diff --git a/README.md b/README.md
index c04a971..091b134 100644
--- a/README.md
+++ b/README.md
@@ -38,8 +38,7 @@ flowchart LR
   create --> create_plan[kvb-create-plan]
   create --> create_requirement[kvb-create-requirement]
   code --> code_scope_guard[kvb-code-scope-guard]
-  code --> code_no_defaults[kvb-code-no-defaults]
-  code --> code_no_comments[kvb-code-no-comments]
+  code --> code_clean[kvb-code-clean]
   code --> code_refactor[kvb-code-refactor]
   code --> code_test[kvb-code-test]
   code --> code_tune[kvb-code-tune]
@@ -135,11 +134,10 @@ flowchart LR
   end
   subgraph cat_code [code]
     scope_guard[kvb-code-scope-guard]
-    no_defaults[kvb-code-no-defaults]
+    clean[kvb-code-clean]
     refactor[kvb-code-refactor]
     test[kvb-code-test]
     tune[kvb-code-tune]
-    comments_clean[kvb-code-no-comments]
     code_transcend[kvb-code-transcend]
   end
   subgraph cat_ci [ci]
@@ -223,7 +221,7 @@ flowchart LR
   edit_hook -. council gate .-> democracy
   reminders -.-> dream
   full_hour -.-> coach
-  code_task -.-> no_defaults
+  code_task -.-> clean
   code_task -.-> scope_guard
   spawn -.-> subagent_model
 
@@ -241,7 +239,10 @@ flowchart LR
   update_branches --> active_listening
   update_branches -. conflicts .-> merge_fix
   update_branches -. pushes .-> operator
-  commit_no_verify --> comments_clean
+  commit_no_verify --> clean
+  commit_next --> clean
+  clean --> sceptic
+  clean --> refactor
   commit_no_verify --> advocate
   advocate --> dialectic
   confidence --> break_risk
@@ -301,7 +302,6 @@ flowchart LR
   criticize --> dialectic
   criticize --> active_listening
   sceptic --> dialectic
-  sceptic --> no_defaults
   gaps --> sceptic
   gaps --> active_listening
   gaps --> requirement
@@ -363,9 +363,8 @@ flowchart LR
 
   test --> triage
   test --> dialectic
-  test --> no_defaults
-  test --> comments_clean
-  refactor --> comments_clean
+  test --> clean
+  refactor --> clean
 ```
 
 ## Requirements 📦
diff --git a/skills/kvb-check-principles/SKILL.md b/skills/kvb-check-principles/SKILL.md
index 093f608..f01c543 100644
--- a/skills/kvb-check-principles/SKILL.md
+++ b/skills/kvb-check-principles/SKILL.md
@@ -1,8 +1,8 @@
 ---
 name: kvb-check-principles
 description: >
-  Find violated principles (SPOT, DRY, KISS, SRP, trust boundaries) in a
-  repository, path or diff. Trigger on "sei skeptisch", "kritische
+  Find violated principles (SPOT, DRY, KISS, SRP, coupling, trust
+  boundaries) in a repository, path or diff. Trigger on "sei skeptisch", "kritische
   analyse", or "review the architecture".
 ---
 
@@ -31,16 +31,18 @@ Apply each independently; a finding belongs to exactly one:
 3. **SRP**: one reason to change per unit: the module that parses and
    persists, the function named "x and y", the role that configures, deploys
    and monitors. Name the two stakeholders who would each demand a change.
-4. **KISS**: mechanism nobody asked for: an abstraction with one
+4. **KISS/YAGNI**: mechanism nobody asked for: an abstraction with one
    implementation, a config value that never varies, a cache with no measured
    pressure, a retry loop around a deterministic call.
 5. **Security**, only at trust boundaries: unvalidated input reaching a
    query, shell, template or path; authorization checked in the caller
    instead of the resource; a secret in a default, log or image layer; a
    permission wider than the operation needs. Defensive findings only.
-6. **Silent defaults**: a fallback substituting a guess for a value the
-   caller failed to supply, turning a misconfiguration into wrong behaviour
-   instead of a loud failure (the `kvb-code-no-defaults` skill).
+6. **Fail fast**: a fallback guessing a value the caller failed to supply,
+   or a swallowed error: wrong behaviour instead of a loud failure (step 2
+   of the `kvb-code-clean` skill).
+7. **Coupling**: a dependency against the layer direction, an import cycle,
+   a reach into another unit's internals.
 
 ## Method
 
@@ -70,13 +72,12 @@ One table, worst blast radius first:
 
 Then at most three lines: what the scope excluded, which findings survived
 `kvb-think-dialectic` and which are still derived-only, and the one to fix
-first. No per-finding paragraphs; the operator asks when a row needs it.
+first.
 
 ## Rules
 
 - Never report formatting, naming taste or missing comments.
 - Mark each finding proven (grepped, read, reproduced) or derived (reasoned
   statically), and close with the `kvb-check-score` block for the audit.
-- No silent caps: if you ranked and cut, say how many findings were dropped
-  and by what rule.
+- No silent caps: say how many findings a cut dropped, by what rule.
 - Skepticism ends at the report: no fix, stage or refactor in this skill.
diff --git a/skills/kvb-code-clean/SKILL.md b/skills/kvb-code-clean/SKILL.md
new file mode 100644
index 0000000..5577df3
--- /dev/null
+++ b/skills/kvb-code-clean/SKILL.md
@@ -0,0 +1,79 @@
+---
+name: kvb-code-clean
+description: >
+  Purge comments, forbid defaults, check SPOT, DRY, SRP and coupling in a
+  change. Run AUTOMATICALLY before every commit or stage request and while
+  writing code.
+---
+
+On a commit or stage request, run this pass first, then the requested git
+action; never ask whether to run it. Step 2's rule also binds while writing
+code.
+
+The target is the added lines of every staged and unstaged change (`git
+diff` plus `git diff --cached`) and the units they touch. Never stage to run
+a check; after the pass, re-stage exactly the files staged before it. A pass that changes a bundle
+the operator already saw shows its new diff stat and score block before the
+commit call.
+
+## Step 1: comments
+
+Delete every comment the change adds except three kinds:
+
+- **Exception**: names a concrete trip-wire (bug, pitfall, deliberate
+  non-idiomatic choice); a relabeled narration is none.
+- **Parameter doc**: inputs, outputs, exit codes.
+- **Nocheck directive**: `noqa`, `shellcheck`, `type: ignore` and kin.
+
+Restated code, step narration, banners, "Note that", rationale prose and
+whatever the code, a name or the commit message already carries go. When in
+doubt, delete. Docstrings and script headers count: prose outside the
+parameter doc goes too, and a `#` or `//` grep misses it.
+
+Block-comment languages are not line-oriented: in Jinja (`{# … #}`), C-like
+(`/* … */`), HTML (`<!-- … -->`) and kin, a closer alone on its line looks
+like a comment line; deleted with the rest, the opener swallows every live
+statement down to the next closer. Delete such a block by hand, count the
+delimiters (`grep -c '{#'` against `grep -c '#}'`), re-parse the file and
+diff it against `git show HEAD:<path>`: only comment lines may leave. A green
+lint proves nothing here.
+
+## Step 2: defaults
+
+Every parameter, option, setting, environment lookup and template variable
+is supplied by its caller. A missing value aborts at the earliest moment
+(argument parsing, config load, container start) with an error naming the
+key and where to set it; optionality is an explicit `None`/`null` branch at
+the call site, never a fallback inside the accessor.
+
+`false`, `null`, `""` and an empty list or map are free. Any other default
+carries a comment saying why the value is right for every caller that omits
+it; "sensible", "standard" and "usual" justify nothing.
+
+Run `${CLAUDE_SKILL_DIR}/scripts/defaults.py --repo <dir>` (`--staged`:
+index only; `--file <path>`: an untracked file); exit 1 means hits. Judge
+hits by `defaults.md` next to this file; it also lists what the script
+misses.
+
+## Step 3: principles
+
+Apply the lenses of the `kvb-check-principles` skill (SPOT, DRY, SRP,
+KISS/YAGNI, security at trust boundaries, fail fast, coupling) and its
+method (graph first, siblings grepped, every `file:line` read) to the
+touched units. Judge what this change adds or worsens; an older violation in
+a touched unit is one report line, not a fix.
+
+- Fix in place a violation the change introduced when the fix stays inside
+  the bundle and keeps behaviour, proven by the tests covering the touched
+  units before and after (the safety net of the `kvb-code-refactor` skill).
+- Everything else goes into the report as the `kvb-check-principles`
+  table, shown before the commit call; the operator's word decides whether
+  the bundle lands as it is.
+
+## Report and penalty
+
+One line per step: comments deleted, defaults rewritten or justified,
+principle findings fixed and open, each with file and count. Whatever you
+wrote yourself is admitted without excuses, lowers the bundle's 🎯 fix and
+raises its 💥 break in the `kvb-check-score` block, and goes into persistent
+agent memory (date and pattern), so the calibration persists.
diff --git a/skills/kvb-code-clean/defaults.md b/skills/kvb-code-clean/defaults.md
new file mode 100644
index 0000000..d0401a0
--- /dev/null
+++ b/skills/kvb-code-clean/defaults.md
@@ -0,0 +1,54 @@
+# Judging defaults
+
+Step 2 of the `kvb-code-clean` skill reads this file when `defaults.py`
+reports hits or a review needs the whole rule.
+
+A default is a guess written where the caller's intent is least known: it
+turns a missing value into a plausible wrong answer, and two callers read the
+same call differently (one means "use the default", the other forgot).
+
+## Free and justified defaults
+
+`false`, `null` (`None`, `nil`, `undefined`), `""` and an empty list or map
+MAY be defaults without justification: they denote absence, not a guessed
+value. `${VAR:-}`, `d.get(k)`, `a ?? null` and `def f(a=None)` are fine.
+
+Every other default (a number, a non-empty string, list or map, an enum
+member, a path, a timeout) MUST carry a comment on or directly above it, in
+the project's exception-comment form if it has one, saying why that value is
+right for every caller that omits it; no comment, no default. The comment
+names the assumption so a reviewer can disagree.
+
+"Sensible", "standard", "usual", "conventional", "every other project does
+it", "obvious" and "keeps the signature short" justify nothing: they assert
+someone else chose. A valid justification names why this value is right for
+a caller who says nothing. The operator asking for a specific default, in
+this conversation, for this value, settles it without a comment.
+
+## Judge each hit
+
+- **Real default**: rewrite it as the printed replacement, at the value's
+  true owner.
+- **Justified**: a `justified?` hit stays only if its comment meets the bar
+  above.
+- **False positive**: a `candidate` (`??`, `||`, Python `or`) that is logic,
+  or no default at all; report why.
+
+## What the script cannot see
+
+Go fields left to zero values (a constructor validating every field),
+defaults in a Helm `values.yaml` (none; fail on the missing input), Docker
+`ENV` placeholders for config (`${VAR:?VAR is required}`), Java overloads
+filling an optional parameter (required constructor arguments), and any other
+value-resolution fallback (`?:`, `getOrElse`, `fallback`, a dataclass field).
+
+## How to apply
+
+- Before writing any parameter, ask what happens if the caller omits it;
+  anything but "it fails and says so" gets rewritten.
+- Pushing a default one layer up is no fix: a caller passing an invented
+  constant only moved the guess. Require the value at its true owner
+  (operator, inventory, deployment config).
+- Removing an existing default is a behaviour change, never a silent
+  drive-by: name it and let the operator decide whether it lands in this
+  change or its own.
diff --git a/skills/kvb-code-no-defaults/scripts/defaults.py b/skills/kvb-code-clean/scripts/defaults.py
similarity index 99%
rename from skills/kvb-code-no-defaults/scripts/defaults.py
rename to skills/kvb-code-clean/scripts/defaults.py
index 9d9e247..db7e25b 100755
--- a/skills/kvb-code-no-defaults/scripts/defaults.py
+++ b/skills/kvb-code-clean/scripts/defaults.py
@@ -550,7 +550,7 @@ def call_default(node: ast.Call):
     elif "getenv" in (attribute, name) or attribute == "get":
         fallback = node.args[1] if len(node.args) == 2 else keywords.get("default")
         owner = ast.unparse(func.value) if attribute == "get" else "os.environ"
-        instead = "os.environ[key]" if owner.endswith("environ") else f"{owner}[key]"
+        instead = "os.environ[name]" if owner.endswith("environ") else f"{owner}[name]"
     else:
         return []
     if fallback is None or absent(fallback):
@@ -580,7 +580,7 @@ def scan_python(path: str, text: str, wanted: set[int] | None) -> list[Hit]:
         tree = ast.parse(text, filename=path)
         tokens = list(tokenize.generate_tokens(io.StringIO(text).readline))
     except (SyntaxError, ValueError, tokenize.TokenError) as error:
-        raise ScanError(f"{path}: not parseable as Python: {error}") from error
+        raise ScanError(f"{path}: unparseable Python: {error}") from error
     commented = {token.start[0] for token in tokens if token.type == tokenize.COMMENT}
     comment_only = {line for line, row in enumerate(text.split("\n"), 1) if row.lstrip().startswith("#")}
     hits = []
diff --git a/skills/kvb-code-no-comments/SKILL.md b/skills/kvb-code-no-comments/SKILL.md
deleted file mode 100644
index ce135b6..0000000
--- a/skills/kvb-code-no-comments/SKILL.md
+++ /dev/null
@@ -1,38 +0,0 @@
----
-name: kvb-code-no-comments
-description: >
-  Purge explanatory comments from staged and unstaged changes. Run
-  AUTOMATICALLY before every commit or stage request (commit, commit
-  no-verify, stage next, "commite ..."); also on comment complaints.
----
-
-On a commit or stage request, run this audit first, then the requested git
-action; never ask whether to run it.
-
-Audit the added lines of every staged and unstaged change (`git diff` plus
-`git diff --cached`) and delete every explanatory comment:
-
-1. Delete restated code, step narration, section banners, "Note that",
-   rationale prose, apology comments, and any comment whose information the
-   code, task name or commit message already carries. When in doubt, delete.
-2. Keep only parameter and exit-code docs, nocheck/noqa/shellcheck
-   directives, and project-sanctioned exception markers naming a concrete
-   trip-wire. A relabeled narration is not an exception; delete it.
-3. Block-comment languages are not line-oriented. In Jinja (`{# … #}`),
-   C-like (`/* … */`), HTML (`<!-- … -->`) and their kin, a closing delimiter
-   alone on its line looks like a comment line; deleted with the rest, it
-   lets the opening delimiter swallow every live statement down to the next
-   closer. Never strip these with a line filter: delete the whole block by
-   hand, count the delimiters (`grep -c '{#'` against `grep -c '#}'`) and
-   re-parse the file.
-4. Re-run the project's comment lint if one exists. Green does NOT prove the
-   deletion safe: a swallowed block stays syntactically valid, so lint and
-   parser pass over code that no longer executes. Diff against the pre-edit
-   revision (`git show HEAD:<path>`) and confirm only comment lines left.
-5. Do not stage to run a check (the `kvb-git-commit-next` skill's step 4 says
-   why). After the audit, re-stage exactly the files staged before it.
-6. Penalty: anything you wrote yourself goes into the report (file and
-   count, no excuses), lowers your confidence numbers for the affected
-   bundle, and is written to persistent agent memory (extend the existing
-   minimal-comments feedback entry with the date and the pattern you slipped
-   on) so the calibration survives the session.
diff --git a/skills/kvb-code-no-defaults/SKILL.md b/skills/kvb-code-no-defaults/SKILL.md
deleted file mode 100644
index d75ac61..0000000
--- a/skills/kvb-code-no-defaults/SKILL.md
+++ /dev/null
@@ -1,80 +0,0 @@
----
-name: kvb-code-no-defaults
-description: >
-  Forbid defaults for parameters, settings and environment lookups;
-  demand explicit values. Apply AUTOMATICALLY whenever code, config,
-  templates or infrastructure are written, edited or reviewed.
----
-
-A default is a guess written where the caller's intent is least known: it
-turns a missing value into a plausible wrong answer, and two callers read the
-same call differently (one means "use the default", the other forgot). Never
-write a substantive default: require the value; when it is absent, fail at
-once and loudly, naming the missing thing.
-
-## The rule
-
-1. Every parameter, option, setting, environment lookup, column and template
-   variable MUST be supplied explicitly by its caller.
-2. A missing value MUST abort at the earliest moment (argument parsing,
-   config load, container start), never at the point of use and never by
-   proceeding with a substitute.
-3. The error MUST name the missing key and where to set it.
-4. Genuine optionality MUST be an explicit named case the call site handles:
-   `None`/`null` in a visible branch is fine, a fallback baked into the
-   accessor is not.
-
-## Free and justified defaults
-
-`false`, `null` (`None`, `nil`, `undefined`), `""` and an empty list or map
-MAY be defaults without justification: they denote absence, not a guessed
-value. `${VAR:-}`, `d.get(k)`, `a ?? null` and `def f(a=None)` are fine.
-
-Every other default (a number, a non-empty string, list or map, an enum
-member, a path, a timeout) MUST carry a comment on or directly above it, in
-the project's exception-comment form if it has one, saying why that value is
-right for every caller that omits it; no comment, no default. The comment
-names the assumption so a reviewer can disagree.
-
-"Sensible", "standard", "usual", "conventional", "every other project does
-it", "obvious" and "keeps the signature short" justify nothing: they assert
-someone else chose. A valid justification names why this value is right for
-a caller who says nothing. The operator asking for a specific default, in
-this conversation, for this value, settles it without a comment.
-
-## Detect
-
-Before presenting a diff or a review, run
-`${CLAUDE_SKILL_DIR}/scripts/defaults.py --repo <dir>` (`--staged`: index
-only; `--file <path>`: a whole untracked file). Each hit prints `file:line`,
-language, construct and replacement; exit 1 means hits. Judge each:
-
-- **Real default**: rewrite it as the replacement, at the value's true owner.
-- **Justified**: a `justified?` hit stays only if its comment meets the bar
-  above.
-- **False positive**: a `candidate` (`??`, `||`, Python `or`) that is logic,
-  or no default at all; report why.
-
-Check by hand what the script cannot see: Go fields left to zero values (a
-constructor validating every field), defaults in a Helm `values.yaml` (none;
-fail on the missing input), Docker `ENV` placeholders for config
-(`${VAR:?VAR is required}`), Java overloads filling an optional parameter
-(required constructor arguments), and any other value-resolution fallback
-(`?:`, `getOrElse`, `fallback`, a dataclass field).
-
-## How to apply
-
-- Before writing any parameter, ask what happens if the caller omits it;
-  anything but "it fails and says so" gets rewritten.
-- Pushing a default one layer up is no fix: a caller passing an invented
-  constant only moved the guess. Require the value at its true owner
-  (operator, inventory, deployment config).
-- Removing an existing default is a behaviour change, never a silent
-  drive-by: name it and let the operator decide whether it lands in this
-  change or its own.
-
-## Penalty
-
-An unjustified default you wrote: report it with file and count, no excuses;
-lower the bundle's confidence numbers; write the date and the construct to
-persistent agent memory so the calibration survives the session.
diff --git a/skills/kvb-code-refactor/SKILL.md b/skills/kvb-code-refactor/SKILL.md
index 7c58463..b10c65e 100644
--- a/skills/kvb-code-refactor/SKILL.md
+++ b/skills/kvb-code-refactor/SKILL.md
@@ -57,7 +57,7 @@ skill sets it up), grep and read after.
   nesting; magic values become a named constant at the use site.
 - **Errors**: never widen or swallow a caught exception, never remove a
   validation or security check to shorten code.
-- **Comments**: invoke the `kvb-code-no-comments` skill.
+- **Comments, defaults**: the `kvb-code-clean` skill.
 
 Never reformat a region without a substantive fix: cosmetic churn buries the
 real change. An architectural problem the change set cannot fix is reported,
diff --git a/skills/kvb-code-test/fix.md b/skills/kvb-code-test/fix.md
index 700f1a5..59be54b 100644
--- a/skills/kvb-code-test/fix.md
+++ b/skills/kvb-code-test/fix.md
@@ -23,8 +23,8 @@ after three simultaneous changes proves nothing about which one mattered.
     unbuilt artefact. Fix the environment or report it; do not patch code
     around it.
 - **Fix** with the smallest change that addresses the root cause, in the
-  project's idioms and under the `kvb-code-no-defaults` and
-  `kvb-code-no-comments` rules. Forbidden without explicit operator approval:
+  project's idioms and under the `kvb-code-clean` rules. Forbidden without
+  explicit operator approval:
   deleting, skipping, `xfail`-ing or commenting out a failing test; loosening
   an assertion to what the code produces; swallowing the exception the test
   surfaces; retries, sleeps or reruns over a flaky failure; disabling a linter
diff --git a/skills/kvb-git-commit-next/SKILL.md b/skills/kvb-git-commit-next/SKILL.md
index 14989a1..3b5de3a 100644
--- a/skills/kvb-git-commit-next/SKILL.md
+++ b/skills/kvb-git-commit-next/SKILL.md
@@ -18,7 +18,7 @@ description: >
    Wait for the operator's decision; do not commit.
 3. Nothing similar found, or the operator picked the staged version: run the
    kvb-git-commit-no-verify skill on the currently staged changes
-   (kvb-code-no-comments audit and kvb-check-legal check first, then the
+   (kvb-code-clean pass and kvb-check-legal check first, then the
    full staged diff and the kvb-check-score commit table of 📁 worktree,
    🌿 branch, 📊 diff stat, scores with 🛡️ security and gate, then
    `git commit --no-verify`, exact staging index only, its message carrying
@@ -40,10 +40,11 @@ description: >
    operator's own edits and local config. A file that carries two bundles is
    staged by line: `${CLAUDE_SKILL_DIR}/scripts/stage_hunks.py --repo
    <worktree> --file <path> --match <regex>`, first with `--dry-run`.
-5. For the newly staged bundle run the kvb-think-explain skill (what the
-   changes do and how the pieces interact, file:line-anchored), then the
-   kvb-check-confidence skill (its kvb-check-score block with 🛡️ security
-   from `security.py` of kvb-check-security, evidence, residuals).
+5. For the newly staged bundle run the kvb-code-clean pass, then the
+   kvb-think-explain skill (what the changes do and how the pieces
+   interact, file:line-anchored), then the kvb-check-confidence skill (its
+   kvb-check-score block with 🛡️ security from `security.py` of
+   kvb-check-security, evidence, residuals).
 6. Close with the staged bundle's commit table (`score.py ...
    --commit-table <worktree>`: 📁 worktree, 🌿 branch, 📊 diff stat, scores,
    gate), what remains unstaged, and wait for the operator's commit
diff --git a/skills/kvb-git-commit-no-verify/SKILL.md b/skills/kvb-git-commit-no-verify/SKILL.md
index ac94a28..4e9c4d1 100644
--- a/skills/kvb-git-commit-no-verify/SKILL.md
+++ b/skills/kvb-git-commit-no-verify/SKILL.md
@@ -6,9 +6,9 @@ description: >
   carried over to later commits.
 ---
 
-1. Run the kvb-code-no-comments audit over the staged and unstaged changes first,
-   then the kvb-check-legal check over the staging index. A legal blocker stops
-   here.
+1. Run the kvb-code-clean pass (comments, defaults, principles) over the
+   staged and unstaged changes first, then the kvb-check-legal check over
+   the staging index. A legal blocker stops here.
 2. Show in the message right before the `git commit` call, never only after
    it, the full staged diff (`git diff --cached`), then the commit table of
    the kvb-check-score skill (`score.py ... --commit-table <worktree>`):
diff --git a/skills/kvb-help/SKILL.md b/skills/kvb-help/SKILL.md
index e0080ee..cfb337b 100644
--- a/skills/kvb-help/SKILL.md
+++ b/skills/kvb-help/SKILL.md
@@ -16,8 +16,8 @@ Produce a one-shot overview of every skill the session can invoke:
    compressing the description instead of pasting it.
 3. When the operator names a specific skill or topic, explain only the
    matching skills in more depth: what they do, when they fire on their
-   own, and how they compose (e.g. kvb-git-commit-next → kvb-git-commit-no-verify →
-   kvb-code-no-comments).
+   own, and how they compose (e.g. kvb-git-commit-next →
+   kvb-git-commit-no-verify → kvb-code-clean).
 4. End with the activation hint: project installers or `make install` in
    the skills repository refresh the live copies; a restart loads renamed
    or new skills.
diff --git a/skills/kvb-skill-compile/SKILL.md b/skills/kvb-skill-compile/SKILL.md
index 094764e..51f47dd 100644
--- a/skills/kvb-skill-compile/SKILL.md
+++ b/skills/kvb-skill-compile/SKILL.md
@@ -40,7 +40,7 @@ Compile what runs often or went wrong; a one-off stays prose. Per candidate:
   library in the skills repository); no new language, framework or dependency
   without the operator.
 - **Interface**: every host path, name and value an explicit parameter (the
-  `kvb-code-no-defaults` skill), documented exit codes, `--json` when another
+  `kvb-code-clean` skill), documented exit codes, `--json` when another
   script or skill consumes the output.
 - **Location**: `skills/<skill>/scripts/<verb>.py` with a test under `tests/`
   in the skills repository; elsewhere the owning repository's convention,
diff --git a/skills/kvb-skill-transcend/SKILL.md b/skills/kvb-skill-transcend/SKILL.md
index 9b02d4c..8522336 100644
--- a/skills/kvb-skill-transcend/SKILL.md
+++ b/skills/kvb-skill-transcend/SKILL.md
@@ -33,7 +33,7 @@ new skill, a sharper step in an existing skill, a memory entry instead, or
 drop. A recurring deterministic move without a script goes to the
 `kvb-skill-compile` skill, any other recurring move to the `kvb-skill-tune`
 skill as evidence. A script is portable only once its host paths, names and
-values are explicit parameters (the `kvb-code-no-defaults` skill); one that
+values are explicit parameters (the `kvb-code-clean` skill); one that
 needs a secret, a credential or a single host is dropped or stays a memory
 entry.
 
@@ -49,8 +49,8 @@ or diff.
 
 - Write where the `kvb-skill-tune` skill's **Persistence** section says: the
   skills repository as source of truth, then the live mirrors.
-- Read every script whole before carrying it; strip comments the way the
-  `kvb-code-no-comments` skill does.
+- Read every script whole before carrying it; clean it the way the
+  `kvb-code-clean` skill does.
 - A carried script gets a unit test in the repository's `tests/` with a
   negative control, run once `watch.py admit --kind test-nostack` (the
   `kvb-org-organize` skill) prints `grant`; `make test` runs through
diff --git a/tests/test_defaults.py b/tests/test_defaults.py
index f0f9b07..34c3e5b 100644
--- a/tests/test_defaults.py
+++ b/tests/test_defaults.py
@@ -10,7 +10,7 @@ import unittest
 from pathlib import Path
 
 REPO_ROOT = Path(__file__).resolve().parents[1]
-SCRIPT = REPO_ROOT / "skills" / "kvb-code-no-defaults" / "scripts" / "defaults.py"
+SCRIPT = REPO_ROOT / "skills" / "kvb-code-clean" / "scripts" / "defaults.py"
 BASE = {
     "app.py": "import os\n\n\ndef old(a=1):\n    return a\n",
     "run.sh": 'echo "${OLD:-1}"\n',