Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The pr-verify verifier failed head 27fe8d09c14b60b1b31c95b3500227b75e97161c. What it wrote, as data:

What it wrote (26 lines)
Summary: Issue #16028 is part 1 of #15729, covering the list and the ladder. The ladder half is done
  correctly. The README moves to 3.2.0 and gains Selection rules rows for
  `/architecture:enforce-boundaries` and `/session-flow:retro`. It also says that a skill with no
  selection rule of its own has no row and hands the rung to `/corrections:codify`, and it names the
  readers that use a copy only for the boundary list. The CHANGELOG has a 3.2.0 entry, which is a
  minor bump as its own rules require. All five regenerated copies match the canonical text. There
  is one changelog fragment per carrier. The diff adds no new skill (AC10) and cuts nothing (AC7).
  CI on the judged head is green: Check Managed Files, Lint Repo, Check Skills, Test Bash (0) and
  Test Python (0) all succeeded
  (https://github.com/melodic-software/claude-code-plugins/actions/runs/43935023014). The capture
  was blocked by the credit gate, which counts neither way. Two parts of the spec are not met.
  First, AC12 requires every existing skill that places enforcement or an instruction to be on the
  recorded list with its route. That list exists only in the pull request body, and it is visibly
  cut off: it ends at `/planning:design` followed by "-…". So the list is incomplete and AC12 cannot
  be confirmed. Second, the dogfooding step appears only in a side remark under "Not verified" that
  refers to "the step named in the PR body", but the body never states it on its own. No secrets,
  takeover-set files, holds or settings are touched. I found no text that tries to steer the
  reviewer.
- PR body (Summary, "Recorded list"): the quoted list is cut off after `/planning:design` with "-…",
  so it is not true that every existing enforcement- or instruction-placing skill is on the recorded
  list with its route (AC12). Restore the full list in the body, or record it in a file in the
  repository, so that every skill from the sweep appears with its route.
- PR body: the dogfooding step is only mentioned in passing under "Not verified" ("the step named in
  the PR body"), and the body never actually states it. Add a line that names this repository's
  dogfooding step, e.g. running `/harness-config:audit-automation-gaps` here after release plus
  `scripts/sync-shared-copies.sh --check`.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

pr-unblock / address-feedback: UNCERTAIN, left open

Evidence: docs/contracts/enforcement-ladder/README.md:201, .changes/architecture/work-resolve-issue-issue-16028-43931031836-1-c160e39a.md:1

Both points hold: the Summary's recorded list stops at /planning:design followed by a cut-off entry, and the body never states the dogfooding step on its own. Neither point can be fixed in this round. The full list cannot be recovered from the checkout: no file in the repository holds the sweep, and the cut-off entries (the rest of the presence-gated group and any groups after it) exist only in the earlier run's output. Rebuilding them would take a fresh sweep across every plugin's skills and agents, which is too much for one scoped change, and a guessed list would weaken AC12 rather than show it is met. The verifier's alternative, recording the list in a repository file, needs a new file, and check-paths refuses one (for example docs/contracts/enforcement-ladder/enforcement-placing-skills.md). Putting the sweep inside the ladder README (line 201 is where it says skills with no row hand the rung to codify) would add a per-repository inventory to a contract that is copied into five plugins. That is a design decision for a person. A body-only edit cannot carry a fix in this mode. A person should restore the full list, either in the body or in a file they choose, and add a line naming the dogfooding step, for example running /harness-config:audit-automation-gaps in this repository after release plus scripts/sync-shared-copies.sh --check.

Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
---
bump: patch
---

### Changed

- The bundled enforcement ladder is 3.2.0: its Selection rules table gains an
`/architecture:enforce-boundaries` row, stating the rule that skill already applies (the first
rung, strongest first, that can express a boundary rule's form), and a `/session-flow:retro` row.
No rung, id or criterion changes.
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
---
bump: patch
---

### Changed

- The bundled enforcement ladder is 3.2.0: its Selection rules table gains the
`/architecture:enforce-boundaries` and `/session-flow:retro` rows, and it states that a skill
that applies no selection rule of its own has no row and hands the choice of rung to `/corrections:codify` when that skill is available. No
rung, id or criterion changes.
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
---
bump: patch
---

### Changed

- The bundled enforcement ladder is 3.2.0: its Selection rules table gains the
`/architecture:enforce-boundaries` and `/session-flow:retro` rows. No rung, id or criterion
changes, so `rule-inventory.sh` counts the same rungs and tiers; only its printed ladder version
changes.
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
---
bump: patch
---

### Changed

- The bundled enforcement ladder is 3.2.0: its Selection rules table gains the
`/architecture:enforce-boundaries` and `/session-flow:retro` rows, and it records that this
plugin's copy is read by the `architecture-guardian` agent for the "Where boundary rules live"
list only. No rung, id or criterion changes.
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
---
bump: patch
---

### Changed

- The bundled enforcement ladder is 3.2.0: its Selection rules table gains a `/session-flow:retro`
row, stating the rule the retro already applies (a finding a check could decide first wires or
repairs an existing check; otherwise it goes to `/corrections:codify` when that skill is
available; without it, the strongest rung that can decide it once it meets guardrail criterion
items 1, 2 and 7), and an `/architecture:enforce-boundaries` row. No rung, id
or criterion changes.
10 changes: 10 additions & 0 deletions docs/contracts/enforcement-ladder/CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,16 @@ Notable changes to the enforcement ladder (SemVer). Renaming, removing or moving
bump. Adding a rung, a reader's selection rule or a boundary-rule location is a minor bump.
Wording-only clarification is a patch.

## [3.2.0] - 2026-11-16

- Added: the `/architecture:enforce-boundaries` and `/session-flow:retro` reader rows, the two
carriers that apply their own selection rule and had no row.
- Added: a skill that places enforcement or an instruction and applies no selection rule of its
own has no reader row and hands the rung to `/corrections:codify` when that skill is available.
The readers that use a copy only for the "Where boundary rules live" list and pick no rung are
named: the `review` plugin's `architecture-guardian` agent, and `/architecture:improve` (the
`boundaries` and `conventions` lenses) and `/architecture:improve-layout`.

## [3.1.1] - 2026-11-15

- Changed: the Rungs section names the sources of the order: Lauren Tan's talk and principle file
Expand Down
14 changes: 12 additions & 2 deletions docs/contracts/enforcement-ladder/README.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
enforcement-ladder: 3.1.1
enforcement-ladder: 3.2.0
---

# Enforcement ladder
Expand Down Expand Up @@ -192,9 +192,19 @@ Each reader walks the same rungs with a different question.
|---|---|---|
| `/harness-config:audit-automation-gaps` | Is this concern already covered, and if not, what should cover it? | the strongest rung that covers the concern; a concern a stronger rung already covers is not a gap |
| `/corrections:codify` | Which rung should stop this recurring mistake, described in the session, in a findings file (`findings`) or in review comments (`reviews`)? | the strongest rung that can decide the mistake and passes the guardrail criterion; a mistake that fails the criterion stays on the guidance tier or `human-review`, and `make-impossible` is only proposed |
| `/architecture:enforce-boundaries` | Which mechanism should hold this recorded boundary rule? | the first rung, strongest first, that can express the rule's form: a build-time boundary the ecosystem already has, then the boundary tool the repository already uses, then a maintained tool researched now, then a check in the repository's own check convention; a rule that fails the guardrail criterion gets no check |
| `/session-flow:retro` | Should this session finding be a check, and on which rung? | a finding a check could decide first wires or repairs an existing check that should have caught it; otherwise it goes to `/corrections:codify` when that skill is available; without it, the strongest rung that can decide the finding, once it meets guardrail criterion items 1, 2 and 7 as judged from the finding itself; a finding that fails one of them stays on the guidance tier |

"Strongest" is an order over this one list: it asks what leaves the least room for a whole class of
mistakes. Neither skill reorders the list.
mistakes. No reader reorders the list.

A skill that places enforcement or an instruction and applies no selection rule of its own has no
row here: it hands the choice of rung to `/corrections:codify` when that skill is available. Some
readers with no row read a copy for the "Where boundary rules live" list only and pick no rung: the
`review` plugin's `architecture-guardian` agent, and the `boundaries` and `conventions` lenses of
`/architecture:improve` and `/architecture:improve-layout`, which read the `architecture` copy.
The `boundaries` lens sends each confirmed rule to `/corrections:codify findings` as an
`architecture-test` proposal.

## Reordering

Expand Down
14 changes: 12 additions & 2 deletions plugins/architecture/skills/improve/research/enforcement-ladder.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
enforcement-ladder: 3.1.1
enforcement-ladder: 3.2.0
---

<!-- GENERATED from docs/contracts/enforcement-ladder/README.md by scripts/sync-shared-copies.sh. Do not edit this copy:
Expand Down Expand Up @@ -195,9 +195,19 @@ Each reader walks the same rungs with a different question.
|---|---|---|
| `/harness-config:audit-automation-gaps` | Is this concern already covered, and if not, what should cover it? | the strongest rung that covers the concern; a concern a stronger rung already covers is not a gap |
| `/corrections:codify` | Which rung should stop this recurring mistake, described in the session, in a findings file (`findings`) or in review comments (`reviews`)? | the strongest rung that can decide the mistake and passes the guardrail criterion; a mistake that fails the criterion stays on the guidance tier or `human-review`, and `make-impossible` is only proposed |
| `/architecture:enforce-boundaries` | Which mechanism should hold this recorded boundary rule? | the first rung, strongest first, that can express the rule's form: a build-time boundary the ecosystem already has, then the boundary tool the repository already uses, then a maintained tool researched now, then a check in the repository's own check convention; a rule that fails the guardrail criterion gets no check |
| `/session-flow:retro` | Should this session finding be a check, and on which rung? | a finding a check could decide first wires or repairs an existing check that should have caught it; otherwise it goes to `/corrections:codify` when that skill is available; without it, the strongest rung that can decide the finding, once it meets guardrail criterion items 1, 2 and 7 as judged from the finding itself; a finding that fails one of them stays on the guidance tier |

"Strongest" is an order over this one list: it asks what leaves the least room for a whole class of
mistakes. Neither skill reorders the list.
mistakes. No reader reorders the list.

A skill that places enforcement or an instruction and applies no selection rule of its own has no
row here: it hands the choice of rung to `/corrections:codify` when that skill is available. Some
readers with no row read a copy for the "Where boundary rules live" list only and pick no rung: the
`review` plugin's `architecture-guardian` agent, and the `boundaries` and `conventions` lenses of
`/architecture:improve` and `/architecture:improve-layout`, which read the `architecture` copy.
The `boundaries` lens sends each confirmed rule to `/corrections:codify findings` as an
`architecture-test` proposal.

## Reordering

Expand Down
14 changes: 12 additions & 2 deletions plugins/corrections/skills/codify/reference/enforcement-ladder.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
enforcement-ladder: 3.1.1
enforcement-ladder: 3.2.0
---

<!-- GENERATED from docs/contracts/enforcement-ladder/README.md by scripts/sync-shared-copies.sh. Do not edit this copy:
Expand Down Expand Up @@ -195,9 +195,19 @@ Each reader walks the same rungs with a different question.
|---|---|---|
| `/harness-config:audit-automation-gaps` | Is this concern already covered, and if not, what should cover it? | the strongest rung that covers the concern; a concern a stronger rung already covers is not a gap |
| `/corrections:codify` | Which rung should stop this recurring mistake, described in the session, in a findings file (`findings`) or in review comments (`reviews`)? | the strongest rung that can decide the mistake and passes the guardrail criterion; a mistake that fails the criterion stays on the guidance tier or `human-review`, and `make-impossible` is only proposed |
| `/architecture:enforce-boundaries` | Which mechanism should hold this recorded boundary rule? | the first rung, strongest first, that can express the rule's form: a build-time boundary the ecosystem already has, then the boundary tool the repository already uses, then a maintained tool researched now, then a check in the repository's own check convention; a rule that fails the guardrail criterion gets no check |
| `/session-flow:retro` | Should this session finding be a check, and on which rung? | a finding a check could decide first wires or repairs an existing check that should have caught it; otherwise it goes to `/corrections:codify` when that skill is available; without it, the strongest rung that can decide the finding, once it meets guardrail criterion items 1, 2 and 7 as judged from the finding itself; a finding that fails one of them stays on the guidance tier |

"Strongest" is an order over this one list: it asks what leaves the least room for a whole class of
mistakes. Neither skill reorders the list.
mistakes. No reader reorders the list.

A skill that places enforcement or an instruction and applies no selection rule of its own has no
row here: it hands the choice of rung to `/corrections:codify` when that skill is available. Some
readers with no row read a copy for the "Where boundary rules live" list only and pick no rung: the
`review` plugin's `architecture-guardian` agent, and the `boundaries` and `conventions` lenses of
`/architecture:improve` and `/architecture:improve-layout`, which read the `architecture` copy.
The `boundaries` lens sends each confirmed rule to `/corrections:codify findings` as an
`architecture-test` proposal.

## Reordering

Expand Down
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
enforcement-ladder: 3.1.1
enforcement-ladder: 3.2.0
---

<!-- GENERATED from docs/contracts/enforcement-ladder/README.md by scripts/sync-shared-copies.sh. Do not edit this copy:
Expand Down Expand Up @@ -195,9 +195,19 @@ Each reader walks the same rungs with a different question.
|---|---|---|
| `/harness-config:audit-automation-gaps` | Is this concern already covered, and if not, what should cover it? | the strongest rung that covers the concern; a concern a stronger rung already covers is not a gap |
| `/corrections:codify` | Which rung should stop this recurring mistake, described in the session, in a findings file (`findings`) or in review comments (`reviews`)? | the strongest rung that can decide the mistake and passes the guardrail criterion; a mistake that fails the criterion stays on the guidance tier or `human-review`, and `make-impossible` is only proposed |
| `/architecture:enforce-boundaries` | Which mechanism should hold this recorded boundary rule? | the first rung, strongest first, that can express the rule's form: a build-time boundary the ecosystem already has, then the boundary tool the repository already uses, then a maintained tool researched now, then a check in the repository's own check convention; a rule that fails the guardrail criterion gets no check |
| `/session-flow:retro` | Should this session finding be a check, and on which rung? | a finding a check could decide first wires or repairs an existing check that should have caught it; otherwise it goes to `/corrections:codify` when that skill is available; without it, the strongest rung that can decide the finding, once it meets guardrail criterion items 1, 2 and 7 as judged from the finding itself; a finding that fails one of them stays on the guidance tier |

"Strongest" is an order over this one list: it asks what leaves the least room for a whole class of
mistakes. Neither skill reorders the list.
mistakes. No reader reorders the list.

A skill that places enforcement or an instruction and applies no selection rule of its own has no
row here: it hands the choice of rung to `/corrections:codify` when that skill is available. Some
readers with no row read a copy for the "Where boundary rules live" list only and pick no rung: the
`review` plugin's `architecture-guardian` agent, and the `boundaries` and `conventions` lenses of
`/architecture:improve` and `/architecture:improve-layout`, which read the `architecture` copy.
The `boundaries` lens sends each confirmed rule to `/corrections:codify findings` as an
`architecture-test` proposal.

## Reordering

Expand Down
14 changes: 12 additions & 2 deletions plugins/review/context/enforcement-ladder.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
enforcement-ladder: 3.1.1
enforcement-ladder: 3.2.0
---

<!-- GENERATED from docs/contracts/enforcement-ladder/README.md by scripts/sync-shared-copies.sh. Do not edit this copy:
Expand Down Expand Up @@ -195,9 +195,19 @@ Each reader walks the same rungs with a different question.
|---|---|---|
| `/harness-config:audit-automation-gaps` | Is this concern already covered, and if not, what should cover it? | the strongest rung that covers the concern; a concern a stronger rung already covers is not a gap |
| `/corrections:codify` | Which rung should stop this recurring mistake, described in the session, in a findings file (`findings`) or in review comments (`reviews`)? | the strongest rung that can decide the mistake and passes the guardrail criterion; a mistake that fails the criterion stays on the guidance tier or `human-review`, and `make-impossible` is only proposed |
| `/architecture:enforce-boundaries` | Which mechanism should hold this recorded boundary rule? | the first rung, strongest first, that can express the rule's form: a build-time boundary the ecosystem already has, then the boundary tool the repository already uses, then a maintained tool researched now, then a check in the repository's own check convention; a rule that fails the guardrail criterion gets no check |
| `/session-flow:retro` | Should this session finding be a check, and on which rung? | a finding a check could decide first wires or repairs an existing check that should have caught it; otherwise it goes to `/corrections:codify` when that skill is available; without it, the strongest rung that can decide the finding, once it meets guardrail criterion items 1, 2 and 7 as judged from the finding itself; a finding that fails one of them stays on the guidance tier |

"Strongest" is an order over this one list: it asks what leaves the least room for a whole class of
mistakes. Neither skill reorders the list.
mistakes. No reader reorders the list.

A skill that places enforcement or an instruction and applies no selection rule of its own has no
row here: it hands the choice of rung to `/corrections:codify` when that skill is available. Some
readers with no row read a copy for the "Where boundary rules live" list only and pick no rung: the
`review` plugin's `architecture-guardian` agent, and the `boundaries` and `conventions` lenses of
`/architecture:improve` and `/architecture:improve-layout`, which read the `architecture` copy.
The `boundaries` lens sends each confirmed rule to `/corrections:codify findings` as an
`architecture-test` proposal.

## Reordering

Expand Down
14 changes: 12 additions & 2 deletions plugins/session-flow/skills/retro/reference/enforcement-ladder.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
enforcement-ladder: 3.1.1
enforcement-ladder: 3.2.0
---

<!-- GENERATED from docs/contracts/enforcement-ladder/README.md by scripts/sync-shared-copies.sh. Do not edit this copy:
Expand Down Expand Up @@ -195,9 +195,19 @@ Each reader walks the same rungs with a different question.
|---|---|---|
| `/harness-config:audit-automation-gaps` | Is this concern already covered, and if not, what should cover it? | the strongest rung that covers the concern; a concern a stronger rung already covers is not a gap |
| `/corrections:codify` | Which rung should stop this recurring mistake, described in the session, in a findings file (`findings`) or in review comments (`reviews`)? | the strongest rung that can decide the mistake and passes the guardrail criterion; a mistake that fails the criterion stays on the guidance tier or `human-review`, and `make-impossible` is only proposed |
| `/architecture:enforce-boundaries` | Which mechanism should hold this recorded boundary rule? | the first rung, strongest first, that can express the rule's form: a build-time boundary the ecosystem already has, then the boundary tool the repository already uses, then a maintained tool researched now, then a check in the repository's own check convention; a rule that fails the guardrail criterion gets no check |
| `/session-flow:retro` | Should this session finding be a check, and on which rung? | a finding a check could decide first wires or repairs an existing check that should have caught it; otherwise it goes to `/corrections:codify` when that skill is available; without it, the strongest rung that can decide the finding, once it meets guardrail criterion items 1, 2 and 7 as judged from the finding itself; a finding that fails one of them stays on the guidance tier |

"Strongest" is an order over this one list: it asks what leaves the least room for a whole class of
mistakes. Neither skill reorders the list.
mistakes. No reader reorders the list.

A skill that places enforcement or an instruction and applies no selection rule of its own has no
row here: it hands the choice of rung to `/corrections:codify` when that skill is available. Some
readers with no row read a copy for the "Where boundary rules live" list only and pick no rung: the
`review` plugin's `architecture-guardian` agent, and the `boundaries` and `conventions` lenses of
`/architecture:improve` and `/architecture:improve-layout`, which read the `architecture` copy.
The `boundaries` lens sends each confirmed rule to `/corrections:codify findings` as an
`architecture-test` proposal.

## Reordering

Expand Down
Loading