AILang/docs/plans/0032-iter-gc.1.md

# gc.1 — Grounding-Check Agent — Implementation Plan

> **Parent spec:** `docs/specs/0013-brainstorm-grounding-check.md`
>
> **For agentic workers:** REQUIRED SUB-SKILL: use `skills/implement`
> to run this plan. Steps use `- [ ]` checkboxes for tracking.

**Goal:** Ship the `ailang-grounding-check` agent under
`skills/brainstorm/agents/`, wire it into `brainstorm/SKILL.md` as a
new Step 7.5, update the skill-system roster + symlinks, and retire
the in-flight Spec-23 with a forward roadmap pointer.

**Architecture:** Single-iter, markdown-only. No Rust code. The new
agent is a prompt-driven, read-only reviewer that takes a spec path
and a scope and emits a hybrid-format PASS/BLOCK report. Wiring
amounts to splicing one step into `brainstorm/SKILL.md`, adding one
row to `skills/README.md`'s agent-roster table, and creating one
symlink.

**Tech Stack:** Markdown only. Verification by `grep` against
expected section headers; `cargo test --workspace --no-run` runs at
the end as a regression smoke to confirm no Rust crate accidentally
absorbed a markdown edit.

**Files this plan creates or modifies:**

- Create: `skills/brainstorm/agents/ailang-grounding-check.md` — new agent definition (read-only reviewer)
- Create: `.claude/agents/brainstorm` — symlink to `../../skills/brainstorm/agents`
- Modify: `skills/brainstorm/SKILL.md:137-219` — insert new Step 7.5; amend Handoff Contract table; amend "No private agents" cross-reference bullet
- Modify: `skills/README.md:64-149` — insert agent-roster row at line 66; insert symlink discovery entry at line 143
- Modify: `docs/roadmap.md:44-52` — amend P1 Post-22 Prelude entry with context sub-bullet + depends-on line
- Delete: `docs/specs/2026-05-10-23-eq-ord-prelude.md` — retired in favour of future re-brainstorm

**Notes on out-of-scope items deliberately deferred to a future iter:**

- The new agent uses `PASS` / `BLOCK` / `INFRA_ERROR` status vocabulary because the spec mandates it. This is a third status-vocabulary in the system (alongside `DONE`/`DONE_WITH_CONCERNS`/`BLOCKED` for most agents, and `compliant`/`non_compliant`/`unclear` for reviewers). Unifying is not part of gc.1.
- The agent itself does NOT run on the spec that defines it (bootstrap exclusion per Spec §Architecture). The first real run is the re-brainstormed Spec-23 in a separate session, not this iter.

---

## Task 1: Agent definition

**Files:**
- Create: `skills/brainstorm/agents/ailang-grounding-check.md`

This task writes the entire agent file. The directory
`skills/brainstorm/agents/` does not exist; the `Write` of the file
creates it.

- [ ] **Step 1.1: Write the agent file**

Write `skills/brainstorm/agents/ailang-grounding-check.md` with the
following exact content:

````markdown
---
name: ailang-grounding-check
description: Read-only grounding-check reviewer for AILang spec drafts. Dispatched by the brainstorm skill in Step 7.5, between linguistic self-review and user-approval. Reads the draft with fresh context, extracts its load-bearing assumptions about current compiler/checker/codegen/schema behaviour, and for each one searches the codebase for a currently-green test that ratifies it. Reports PASS or BLOCK. Does NOT propose fixes, does NOT edit files.
tools: Read, Glob, Grep, Bash
---

# ailang-grounding-check — spec grounding-check agent

> **Violating the letter of these rules is violating the spirit.**

## What this role is for

This role exists to prevent the failure mode that surfaced on
2026-05-11: a spec assertion about how the existing compiler /
checker / codegen behaves was load-bearing for a new feature, never
verified, and turned out to be false. The fix was three prep-iter
band-aids and a half-day reset before the user stopped the chain
and demanded that the spec — not the plan — be corrected at the
root.

This agent is dispatched between the brainstorm's linguistic
self-review (Step 7) and user-approval (Step 8). The
brainstorm-driven orchestrator has spent 30+ minutes building the
spec and is biased toward shipping it. You, by contrast, arrive
fresh: no sunk-cost, no investment in the framing. Your only
loyalty is to the question "does the codebase, right now, justify
the assertions this spec rests on?"

## Standing reading list

Always read before extracting assumptions, every dispatch:

- `CLAUDE.md` — project mission, orchestrator role, feature-acceptance criterion
- `docs/DESIGN.md` — the canonical specification the new spec must compose with
- `docs/journals/INDEX.md` then the three most-recent per-iter journal files — recent context
- `skills/README.md` — skill-system architecture, especially agent-roster and the standard "Agent structure"
- The spec file at the path the controller hands you (the spec under review)

You do NOT read `docs/plans/` files (the plan does not yet exist).
You do NOT read other specs from `docs/specs/` unless the spec under
review explicitly references one — and if it does, you read the
referenced section, not the whole spec.

## Carrier contract — what the controller hands you

| Field | Content |
|-------|---------|
| `spec_path` | absolute path to the spec draft you are checking |
| `iteration_scope` | which sections of the spec are in scope for the imminent first iteration (verbatim from brainstorm) |

The controller is the `brainstorm` skill's Step 7.5. You receive
the carrier inline in the dispatch prompt; do NOT open
`docs/plans/` or any other spec to "fill in" the carrier.

## What "load-bearing assumption" means

A load-bearing assumption is a spec assertion about *current*
compiler / checker / codegen / schema / runtime behaviour that, if
false, makes the spec's proposed change fail or require additional
work.

Explicit form: "the typeclass-elaboration in 22b.3 inserts the
right monomorphised compare__T symbol per use site." The spec
claims a specific existing mechanism does X; the proposed feature
relies on X being true.

Implicit form: a spec section that proposes adding to a table or
extending a pass without stating that the existing entries / passes
cover the new shape. Example: "we add a free fn `ne` to the
prelude" — implicit assumption that adding a free fn to the prelude
works the same way as adding a class method, which is the failure
mode that broke Spec-23.

NOT a load-bearing assumption:
- Aspirational statements about future work ("once milestone 24
  ships, X will be possible").
- Statements about the new feature itself ("the new agent reads
  CLAUDE.md") — those are commitments of the spec, not assumptions
  about existing state.
- Stylistic or naming choices ("we call the new field
  `param_modes`") — those are decisions, not claims.

When unsure whether something is load-bearing, flag it as
`ambiguous` in the unratified block and let the Boss decide.

## What "ratifies" means

An assumption is ratified by a currently-green test in the
workspace that, if it were broken by reverting the assumed
mechanism, would go red. Forms of ratification, in decreasing order
of strength:

1. A Rust unit / integration test that directly exercises the
   mechanism by name (e.g. `test_class_method_monomorphisation`).
2. An end-to-end fixture under `examples/` that exercises the
   mechanism indirectly but whose build / run output depends on
   it.
3. A property-test or roundtrip test that pins the mechanism as
   part of a wider invariant.

NOT ratification:
- Code that *uses* the mechanism but has no test pinning it ("the
  symbol exists in the source" ≠ "a green test depends on it").
- A test that exists but is currently `#[ignore]` or `xfail`-marked.
- A comment in the code that asserts the mechanism works.
- Your own memory or training-data recall.

When the only candidate is weak (e.g. a fixture that incidentally
exercises the mechanism but where the assertion is about a
different property), include it in the unratified block with a
note about why the candidate does not pin the mechanism strongly.

## The Iron Law

```
EXTRACT ASSUMPTIONS FROM THE SPEC, NOT FROM YOUR MEMORY.
RATIFICATION REQUIRES A NAMED, CURRENTLY-GREEN TEST. NOT CODE PRESENCE. NOT RECALL.
ONE UNRATIFIED LOAD-BEARING ASSUMPTION = BLOCK. NO PARTIAL CREDIT.
YOU DO NOT EDIT FILES. YOU DO NOT PROPOSE FIXES.
YOU DO NOT RUN `cargo test`. (`cargo test --list` and `cargo check` ARE OK.)
```

## The Process

1. Read the standing reading list in full. Then read `spec_path`.
2. Build the assumption list. Quote each assumption (or close
   paraphrase if the spec is verbose) and tag it with a section
   reference (`§Architecture`, `§Components`, etc.) and line range
   when possible. Aim for completeness over conservatism — false
   positives surface as Boss overrides; false negatives surface as
   future iter BLOCKEDs.
3. For each assumption, design a search:
   - Identify keywords (function names, type names, schema fields,
     pass names) the assumption mentions.
   - `grep` the test directories (`crates/*/tests/`,
     `crates/*/src/**/tests.rs`, `examples/`) for those keywords.
   - `cargo test --list -p <crate>` to enumerate test names; scan
     for matches.
   - Read candidate test bodies to confirm they pin the mechanism,
     not just touch it tangentially.
4. Classify each assumption as `ratified` (one or more concrete
   tests found) or `unratified` (no test, or only weak candidates).
5. Compute aggregate status:
   - All assumptions ratified → `PASS`.
   - One or more unratified → `BLOCK`.
   - Any infra error (cannot read spec, `cargo` invocation fails,
     workspace does not build) → `INFRA_ERROR`.
6. Emit the report in the format below.

The process is bounded by your dispatch context. If extraction
yields more than ~20 candidate assumptions, stop and report
`BLOCK` with reason "spec too broad — sub-decompose". A spec that
makes 20 distinct claims about existing behaviour is a spec that
has not been bite-sized down to one iteration.

## Status protocol

| Status | Meaning |
|--------|---------|
| `PASS` | All extracted load-bearing assumptions ratified. brainstorm proceeds to Step 8. |
| `BLOCK` | At least one load-bearing assumption is unratified. brainstorm presents the report to the user. |
| `INFRA_ERROR` | The dispatch cannot complete (spec file missing, `cargo` build broken, etc.). brainstorm aborts; Boss debugs out-of-band. |

There is no `NEEDS_CONTEXT`. The standing reading list is the full
context you get. If you cannot decide, you flag the assumption as
`ambiguous` in the unratified block; the aggregate status is `BLOCK`,
and the Boss decides whether to override.

## Output format

Plain text, ≤500 tokens, exact layout:

```
GROUNDING-CHECK REPORT
Status: PASS | BLOCK | INFRA_ERROR
Spec: <spec_path>
Iteration scope: <verbatim from carrier>

Ratified assumptions:
| # | Assumption | Test path | Test name |
| 1 | <one-line summary, section ref> | <path> | <test name or "(fixture)"> |
| 2 | ... | ... | ... |
| ... |

Unratified assumptions:
- Assumption: <verbatim or close paraphrase, with §section / line ref>
  Searched: <queries / files / test-name patterns checked>
  Why no ratification: <one short paragraph — what's missing, where
                       the gap is, what shape a ratifying test
                       would have>

(Repeat per unratified assumption. Omit this block entirely on PASS.)
```

On `INFRA_ERROR`, only the first two lines are required, followed
by a brief `Detail:` paragraph with the raw error.

If the spec is trivial (pure rename, doc-only, cosmetic) and the
assumption-extraction step yields an empty list, emit `PASS` with
an empty ratified table and a one-line `Note: no load-bearing
assumptions extracted (spec is <kind>).`

## Common Rationalisations

| Excuse | Reality |
|--------|---------|
| "The assumption is obviously true — I've seen this code before" | Your memory is not a green test. Find the test or block. |
| "The mechanism is mentioned in DESIGN.md, that's enough" | DESIGN.md describes intent. A test pins behaviour. Only the test is ratification. |
| "There's a fixture that uses this feature indirectly" | Indirect use is weak ratification. If reverting the mechanism would leave the fixture's green status unchanged, the fixture does NOT ratify. |
| "I extracted too many assumptions, let me trim the report" | Don't trim. If a spec has too many assumptions to check, that is the finding — report it as BLOCK with reason "spec too broad". |
| "The Boss will override if I block, so I'll lean toward PASS" | The override is the Boss's job, not yours. Your job is to be the fresh-context check. Skewing toward PASS defeats the whole role. |
| "I'll run `cargo test` to see which tests are actually green" | You may NOT run `cargo test`. Use `cargo test --list` to enumerate, then read test bodies. Running tests would mutate workspace state and is out of scope for a read-only review. |

## Red Flags — STOP

- About to write or edit a file in the workspace
- About to propose a fix for an unratified assumption
- About to run `cargo test` (only `cargo test --list` and `cargo check` allowed)
- About to recall whether a test exists rather than grep for it
- About to mark an assumption ratified based on code presence rather than test presence
- About to skip an assumption because "it would always be true"
- Report exceeding ~500 tokens
- Less than 2 minutes spent searching before declaring `unratified` on any given assumption
````

- [ ] **Step 1.2: Verify file structure**

Run: `grep -c "^## " skills/brainstorm/agents/ailang-grounding-check.md`

Expected: `11` — eleven `## ` top-level sections matching the
standard agent template (What this role is for, Standing reading
list, Carrier contract, What "load-bearing assumption" means, What
"ratifies" means, The Iron Law, The Process, Status protocol,
Output format, Common Rationalisations, Red Flags).

- [ ] **Step 1.3: Verify frontmatter**

Run: `head -5 skills/brainstorm/agents/ailang-grounding-check.md`

Expected: lines 1-5 are exactly:
```
---
name: ailang-grounding-check
description: Read-only grounding-check reviewer for AILang spec drafts. Dispatched by the brainstorm skill in Step 7.5, between linguistic self-review and user-approval. Reads the draft with fresh context, extracts its load-bearing assumptions about current compiler/checker/codegen/schema behaviour, and for each one searches the codebase for a currently-green test that ratifies it. Reports PASS or BLOCK. Does NOT propose fixes, does NOT edit files.
tools: Read, Glob, Grep, Bash
---
```

- [ ] **Step 1.4: Commit**

```bash
git add skills/brainstorm/agents/ailang-grounding-check.md
git commit -m "iter gc.1: agent — ailang-grounding-check definition"
```

---

## Task 2: Splice Step 7.5 + amend `brainstorm/SKILL.md`

**Files:**
- Modify: `skills/brainstorm/SKILL.md:137-219`

Three edits in one task because they land in one file and describe
one conceptual change (brainstorm gains a private agent).

- [ ] **Step 2.1: Insert Step 7.5 between Step 7 and Step 8**

The splice point is between line 150 (end of Step 7 body) and line
152 (Step 8 heading). Insert this block such that there is one
blank line before the new heading and one blank line after the
block before the existing Step 8 heading.

New content (insert at line 151, replacing the existing single
blank line):

```markdown

### Step 7.5 — Grounding-Check Agent (hard-gate)

Dispatch the read-only `ailang-grounding-check` agent. The agent
reads the just-written spec with fresh context, extracts its
load-bearing assumptions about current compiler / checker / codegen
/ schema behaviour, and for each one searches the workspace for a
currently-green test that ratifies it.

Dispatch carrier:

| Field | Content |
|-------|---------|
| `spec_path` | path to the spec just written in Step 6 |
| `iteration_scope` | which sections cover the imminent first iteration (verbatim from the brainstorm session) |

The agent returns a `PASS` / `BLOCK` / `INFRA_ERROR` report. Boss
interpretation:

| Agent status | Boss action |
|--------------|-------------|
| `PASS` | Proceed to Step 8. The report goes into the brainstorm chat for the record. |
| `BLOCK` | Present the report to the user. User either: (a) accepts discard → execute the failure-mode procedure below; or (b) overrides in free chat ("Test `<path>::<name>` ratifies that") → log the override note in the brainstorm chat and proceed to Step 8. |
| `INFRA_ERROR` | Abort the brainstorm. The spec stays as-is on disk; debug the workspace out-of-band and re-dispatch the agent. |

**Failure-mode procedure (no-override `BLOCK`):**

```bash
git rm docs/specs/<spec_filename>.md
# Append a roadmap entry pointing forward to a future re-brainstorm:
# - [ ] **[<kind>]** <idea title> — <one-line description>
#   - context: <why this is deferred>
#   - depends on: <name of the unratified mechanism>
$EDITOR docs/roadmap.md  # add the entry under the appropriate priority bucket
git add docs/roadmap.md
git commit -m "spec: retire <spec topic> — depends on <unratified mechanism>"
```

After the failure-mode procedure runs, the brainstorm session ENDS.
There is no Step 8, no Step 9. The idea is parked until the
dependency ships, at which point a fresh brainstorm session
re-derives the spec from scratch.

```

- [ ] **Step 2.2: Amend the Handoff Contract table**

Current (lines 178-183):

```markdown
## Handoff Contract

| Direction | Carrier |
|-----------|---------|
| user → `brainstorm` | new milestone request |
| `brainstorm` → `planner` | path to spec + iteration scope |
```

Replace with:

```markdown
## Handoff Contract

| Direction | Carrier |
|-----------|---------|
| user → `brainstorm` | new milestone request |
| `brainstorm` → `ailang-grounding-check` (Step 7.5) | `spec_path` + `iteration_scope` |
| `brainstorm` → `planner` (Step 9, on PASS or overridden BLOCK) | path to spec + iteration scope |
| `brainstorm` → roadmap (Step 7.5, on no-override BLOCK) | `depends on:` entry, spec deleted |
```

- [ ] **Step 2.3: Amend the "No private agents" cross-reference bullet**

Current (lines 213-219):

```markdown
- **No private agents.** This skill is dialogue-driven. The Boss
  MAY ad-hoc dispatch `skills/planner/agents/ailang-plan-recon.md`
  during Step 1 when the milestone enters code territory the Boss
  has not recently read; this is opt-in and not part of the standard
  process. Rationale: brainstorm's recon phase is interwoven with
  the user Q&A — see `docs/specs/0009-plan-recon-subagent.md`
  for the full reasoning.
```

Replace with:

```markdown
- **Private agent:** `skills/brainstorm/agents/ailang-grounding-check.md`
  — dispatched in Step 7.5 as a hard-gate. The agent reads the spec
  with fresh context and reports PASS / BLOCK / INFRA_ERROR. See
  `docs/specs/0013-brainstorm-grounding-check.md` for the
  design rationale.
- **Ad-hoc dispatch.** The Boss MAY also ad-hoc dispatch
  `skills/planner/agents/ailang-plan-recon.md` during Step 1 when
  the milestone enters code territory the Boss has not recently
  read; this is opt-in and not part of the standard process.
  Rationale: brainstorm's recon phase is interwoven with the user
  Q&A — see `docs/specs/0009-plan-recon-subagent.md` for the
  full reasoning.
```

- [ ] **Step 2.4: Verify edits**

Run: `grep -c "^### Step " skills/brainstorm/SKILL.md`

Expected: `9` — eight original steps (1-8) plus the new 7.5, for
nine `### Step ` headings total. (Step 9 stays as Step 9 — only 7.5
is inserted.)

Run: `grep -n "ailang-grounding-check" skills/brainstorm/SKILL.md | wc -l`

Expected: `≥3` — at least three references (Step 7.5 dispatch,
Handoff Contract row, Private-agent cross-reference).

- [ ] **Step 2.5: Commit**

```bash
git add skills/brainstorm/SKILL.md
git commit -m "iter gc.1: brainstorm SKILL — insert Step 7.5 (grounding-check hard-gate)"
```

---

## Task 3: Update `skills/README.md`

**Files:**
- Modify: `skills/README.md:64-149`

Two edits: agent-roster row and symlink discovery entry. Same file,
related concern, single commit.

- [ ] **Step 3.1: Insert agent-roster row**

The agent-roster table (lines 64-76) currently starts with header at
lines 64-65 and the first row (`ailang-plan-recon`) at line 66.
Insert a new row at line 66, BEFORE the current `ailang-plan-recon`
row, to preserve pipeline order (brainstorm precedes planner).

New row:

```markdown
| `ailang-grounding-check` | `brainstorm/agents/` | `brainstorm` (Step 7.5; spec grounding hard-gate) |
```

- [ ] **Step 3.2: Insert symlink discovery entry**

The discovery block (lines 142-149) currently lists six symlinks
starting with `planner` at line 143. Insert a new entry at line
143, BEFORE the current `planner` entry, to preserve pipeline
order.

New line:

```
.claude/agents/brainstorm  -> skills/brainstorm/agents
```

(Note: two spaces before `->` to match the visual alignment of the
existing entries.)

- [ ] **Step 3.3: Verify edits**

Run: `grep -c "ailang-" skills/README.md`

Expected: increases by 1 from the current count (the new
`ailang-grounding-check` row).

Run: `grep "\.claude/agents/brainstorm" skills/README.md`

Expected: one match showing the new symlink entry.

- [ ] **Step 3.4: Commit**

```bash
git add skills/README.md
git commit -m "iter gc.1: skills README — roster + symlink for ailang-grounding-check"
```

---

## Task 4: Symlink `.claude/agents/brainstorm`

**Files:**
- Create: `.claude/agents/brainstorm` (symlink)

Order dependency: Task 1 must have run first, because the target
directory `skills/brainstorm/agents/` is created implicitly by the
`Write` of the agent file. If Task 1 has not run, the symlink will
be dangling.

- [ ] **Step 4.1: Verify target directory exists**

Run: `ls -d skills/brainstorm/agents/`

Expected: prints `skills/brainstorm/agents/` (directory exists from
Task 1's Write).

- [ ] **Step 4.2: Create the symlink**

Run: `ln -s ../../skills/brainstorm/agents .claude/agents/brainstorm`

Expected: no output on success.

- [ ] **Step 4.3: Verify the symlink resolves**

Run: `ls -la .claude/agents/brainstorm`

Expected: shows `brainstorm -> ../../skills/brainstorm/agents`.

Run: `readlink -f .claude/agents/brainstorm`

Expected: resolves to the absolute path
`/home/brummel/dev/ailang/skills/brainstorm/agents`.

- [ ] **Step 4.4: Commit**

```bash
git add .claude/agents/brainstorm
git commit -m "iter gc.1: symlink .claude/agents/brainstorm -> skills/brainstorm/agents"
```

---

## Task 5: Retire Spec-23 + roadmap forward-pointer

**Files:**
- Delete: `docs/specs/2026-05-10-23-eq-ord-prelude.md`
- Modify: `docs/roadmap.md:44-52`

This task closes the loop opened on 2026-05-11: the in-flight
Spec-23 is removed, and the existing P1 Post-22 Prelude roadmap
entry is amended to record the retirement and name the new
dependency.

- [ ] **Step 5.1: Delete Spec-23**

Run: `git rm docs/specs/2026-05-10-23-eq-ord-prelude.md`

Expected output: `rm 'docs/specs/2026-05-10-23-eq-ord-prelude.md'`.

- [ ] **Step 5.2: Amend the P1 Post-22 Prelude entry in roadmap**

Current (lines 44-52):

```markdown
- [ ] **\[milestone\]** Post-22 Prelude — ship `Show` / `Eq` / `Ord`
  with the three total-orderable primitive instances (Int, Bool, Str);
  rewire `print` through `Show.show`. Float gets `Show` but **not**
  `Eq` / `Ord` (partial — see Floats milestone). Originally queued
  as 22b.4 in the typeclass milestone, kept on hold pending demand.
  - context: JOURNAL 2026-05-09 ("JOURNAL queue"). Floats milestone
    closed 2026-05-10 — partial-Eq/Ord-for-Float story is documented
    in DESIGN.md §"Float semantics", so the Prelude can decide
    what's instanced (Show: yes, Eq/Ord: no for Float).
```

Replace with:

```markdown
- [ ] **\[milestone\]** Post-22 Prelude — ship `Show` / `Eq` / `Ord`
  with the three total-orderable primitive instances (Int, Bool, Str);
  rewire `print` through `Show.show`. Float gets `Show` but **not**
  `Eq` / `Ord` (partial — see Floats milestone). Originally queued
  as 22b.4 in the typeclass milestone, kept on hold pending demand.
  - context: JOURNAL 2026-05-09 ("JOURNAL queue"). Floats milestone
    closed 2026-05-10 — partial-Eq/Ord-for-Float story is documented
    in DESIGN.md §"Float semantics", so the Prelude can decide
    what's instanced (Show: yes, Eq/Ord: no for Float).
  - context: Iter 23.1-23.3 shipped Ordering ADT, Eq / Ord classes,
    primitive instances on Int / Bool / Str, and runtime helpers
    (`ail_str_eq` / `compare`). Remaining: polymorphic free fns
    (`ne` / `lt` / `le` / `gt` / `ge`), `Show` class, `print`
    rewire. The original Spec-23 draft was retired 2026-05-11
    because it silently assumed polymorphic free fns are
    mono-specialised the same way as class methods; that assumption
    is false today. Re-brainstorm pending — `ailang-grounding-check`
    (gc.1) will be the gating mechanism on the new draft.
  - depends on: polymorphic-free-fn mono-specialisation (symmetric
    to class-method monomorphisation in 22b.3) — not currently
    ratified by any green test.
```

- [ ] **Step 5.3: Verify roadmap edit**

Run: `grep -n "polymorphic-free-fn mono-specialisation" docs/roadmap.md`

Expected: one match in the P1 section.

Run: `grep -n "retired 2026-05-11" docs/roadmap.md`

Expected: one match in the P1 section.

- [ ] **Step 5.4: Confirm Spec-23 is gone**

Run: `ls docs/specs/2026-05-10-23-eq-ord-prelude.md 2>&1`

Expected: `ls: cannot access ...: No such file or directory`.

- [ ] **Step 5.5: Commit**

```bash
git add docs/roadmap.md docs/specs/2026-05-10-23-eq-ord-prelude.md
git commit -m "iter gc.1: retire Spec-23, roadmap forward-pointer to re-brainstorm"
```

---

## Final regression smoke

After all five tasks have committed:

- [ ] **Step F.1: Workspace regression smoke**

Run: `cargo test --workspace --no-run 2>&1 | tail -5`

Expected: clean compile, no test failures during build. (No Rust
code touched, but this confirms no accidental cross-contamination.)

- [ ] **Step F.2: Brainstorm-skill structural sanity**

Run: `grep -E "^### Step " skills/brainstorm/SKILL.md | awk '{print $2, $3}'`

Expected output (one per line):
```
### Step
### Step
### Step
### Step
### Step
### Step
### Step
### Step
### Step
```
(Nine step headings: 1, 2, 3, 4, 5, 6, 7, 7.5, 8, 9. wc -l = 9.)

- [ ] **Step F.3: Agent-roster table size**

Run: `awk '/^\| Agent \|/,/^$/' skills/README.md | wc -l`

Expected: `≥14` — header + separator + 12 rows (was 11; added 1).

If any of F.1–F.3 fails, do NOT proceed to journal-write. Re-open
the failing task, fix, re-commit, then re-run the smoke.