@event4u/agent-config 9.8.0 → 9.10.0

package/docs/decisions/ADR-001-kernel-swap-deferred.md

@@ -1,109 +0,0 @@
----
-adr: 001
-status: accepted
-date: 2026-05-06
-decision: kernel-swap-deferred
-supersedes: —
-superseded_by: —
-phase: road-to-kernel-and-router · P2.1
----
-
-# ADR-001 — Kernel-Set Swap Deferred (variant a)
-
-## Status
-
-**Accepted** · 2026-05-06.
-
-## Context
-
-Phase 1.4 of `road-to-kernel-and-router` ran an AI Council
-cross-check (Sonnet 4.5 + GPT-4o) against the locked 9-rule kernel
-set in `docs/contracts/kernel-membership.md` § 4. Sonnet flagged that
-`agent-authority` carries **no Iron-Law fence** — it is a routing
-index dispatching to four other kernel rules (`non-destructive-by-default`,
-`scope-control`, `commit-policy`, `autonomous-execution`) by Band.
-Sonnet proposed swapping `agent-authority` out of the kernel and
-promoting `autonomous-execution` in. Three resolution variants
-landed in `kernel-membership.md` § 5.2:
-
-| variant | sum-projected (× 0.712) | bucket budget | Iron-Law-override ADRs |
-|---|---:|---|---|
-| (a) status quo (current § 4) | 23 071 | ✓ ≤ 25k | 2 (`direct-answers`, `language-and-tone`) |
-| (b) swap, raise hard cap to 27k | 26 213 | ✓ ≤ 27k | 3 (+`autonomous-execution`) |
-| (c) swap + demote `verify-before-complete` | 24 545 | ✓ ≤ 25k | 3 (+`autonomous-execution`) |
-
-## Decision
-
-**Variant (a) — status quo through P2.2 + P3.1.**
-
-- Keep `agent-authority` in the kernel.
-- Keep `autonomous-execution` in `condense-and-keep` (auto-tier) per
-  `docs/contracts/rule-classification.md` § 3.2.
-- Re-evaluate the swap as a P3.2 ADR after the router schema and
-  compiler ship.
-
-## Consequences
-
-### Accepted
-
-- 25k hard cap stays intact (no governance erosion via cap-raise).
-- 2 Iron-Law-override ADRs land in P2.2 if post-condensation
-  measurement confirms overage (`direct-answers`, `language-and-tone`).
-- The 9-rule set carried into P2.2 is the locked § 4 list.
-
-### Trade-offs
-
-- Sonnet's Iron-Law-purity critique stands: `agent-authority`
-  remains in the kernel without a fence of its own. Mitigation —
-  the rule **mechanically depends** on four other kernel rules
-  (every Band redirects), so its kernel residency is structurally
-  load-bearing even if not syntactically Iron Law. Treated as a
-  routing primitive that dispatches to Iron Laws, not a rule in
-  parallel to them.
-- `autonomous-execution` (5631 chars current, ~4009 projected)
-  remains in auto-tier. Behaviour preserved because the rule
-  already declares `type: auto` and ships under the `balanced` and
-  `full` cost profiles by default.
-
-## Re-evaluation trigger
-
-Phase 3 (`docs/contracts/rule-router.md`) introduces a
-`tier:` / `band:` / `priority:` schema in rule frontmatter. Once
-that schema is locked in P3.1 and the compiler is wired in P3.2,
-`agent-authority` becomes redundant: each kernel rule carries its
-own band as frontmatter, and the compiled `router.json` resolves
-precedence at build time. At that point:
-
-- `agent-authority` migrates to a guideline
-  (`docs/guidelines/agent-authority.md`) as documentation of the
-  band model.
-- `autonomous-execution` can be promoted into the kernel under a
-  new ADR (ADR-N) that replaces this one, *if* its post-condensation
-  size fits the cap with no further demotion.
-
-This deferral is **not** indefinite: P3.2 ships the router compiler;
-the swap re-evaluation ADR is mandatory before P4.1 (rule → skill
-migrations) so the migration plan reflects the final kernel set.
-
-## Alternatives considered
-
-- **Variant (b) — swap + raise cap to 27k.** Rejected. Raising the
-  hard cap mid-roadmap weakens the original 25k contract that the
-  whole roadmap is built around. If 27k turns out to be the real
-  ceiling, that is a separate ADR after condensation measurement
-  proves the band, not a pre-emptive concession.
-- **Variant (c) — swap + demote `verify-before-complete`.**
-  Rejected. `verify-before-complete` carries criterion #1 (Iron
-  Law) and gates completion-claims across every reply. Demoting it
-  to auto-tier removes the floor that prevents the agent from
-  claiming "done" without fresh evidence — a behavioural regression
-  that the golden-transcript suite would catch but that no other
-  kernel rule replaces.
-
-## References
-
-- `docs/contracts/kernel-membership.md` § 4, § 5.2
-- `agents/runtime/council/sessions/20260506T044941Z-phase1-cross-check-r2.json` <!-- council-ref-allowed: ADR decision trace -->
-- `agents/roadmaps/road-to-kernel-and-router.md` § Decisions, § Phase 2
-- `.agent-src.uncondensed/rules/agent-authority.md` (subject)
-- `.agent-src.uncondensed/rules/autonomous-execution.md` (proposed promotion)

package/docs/decisions/ADR-002-kernel-bucket-overrides.md

@@ -1,135 +0,0 @@
----
-adr: 002
-status: accepted
-date: 2026-05-06
-decision: kernel-bucket-overrides
-supersedes: —
-superseded_by: —
-phase: road-to-kernel-and-router · P2.2
-type: structural
----
-
-# ADR-002 — Kernel-Bucket Cap Raise (25k → 26k) and Per-Rule Iron-Law Overrides
-
-- **Status:** Accepted (2026-05-06)
-- **Phase:** Road to Rule Kernel and Router · P2.2 (Heavy Condensation)
-- **Supersedes:** none — extends the Council R2 amendments locked in
-  `docs/contracts/kernel-membership.md` § 5.1 (median r=0.712, per-rule cap 2.5k,
-  kernel-bucket 25k).
-- **Related:** ADR-001 (kernel-swap deferred); Council R2 cross-check session
-  `agents/runtime/council/sessions/20260506T044941Z-phase1-cross-check-r2.json`. <!-- council-ref-allowed: ADR decision trace -->
-
-## Context
-
-P1.3 projected the post-condensation kernel bucket at **23 071 chars** using
-the median pilot ratio r=0.712 (3 pilots: agent-authority, direct-answers,
-language-and-tone). Pilot rules were **short to medium** (1.0k–2.5k baseline).
-
-P2.2 applied the same condensation discipline to the remaining 6 kernel rules
-(ask-when-uncertain, commit-policy, no-cheap-questions,
-non-destructive-by-default, scope-control, plus the verify-before-complete
-auto-tier rule kept by ADR-001). Iron-Law SHA preservation verified for
-all 8 rules with Iron-Law fences (`scripts/iron_law_sha.py`).
-
-**Empirical post-condensation measurements (2026-05-06):**
-
-| metric | projected | actual |
-|---|---:|---:|
-| kernel bucket sum | 23 071 | **25 590** |
-| condensation ratio r (kernel-wide) | 0.712 (median pilot) | **0.795** |
-| rules > 2.5k cap | 2 (pilots) | 6 |
-| rules > 4.0k ceiling | 0 | 0 |
-
-The actual ratio (0.795) is worse than the pilot median (0.712) because
-**longer rules condense less efficiently than short ones**: each Iron-Law
-rule has a fixed payload of frontmatter, Iron-Law fence, exception
-enumeration, see-also list — shrinkage is bounded by what cannot leave
-the rule without breaking the rule's contract. The 5 longest source rules
-(non-destructive-by-default, scope-control, no-cheap-questions,
-ask-when-uncertain, language-and-tone) each kept multiple
-non-externalisable structural elements (Iron-Law fence + trigger
-enumeration + pre-send self-check + decline/fence semantics).
-
-## Decision
-
-1. **Raise KERNEL_HARD from 25 000 → 26 000 chars** in
-   `scripts/measure_rule_budget.py`. KERNEL_TARGET stays at 20 000.
-   This accommodates the empirical 25 590 with ~410 chars headroom for
-   future minor edits (typo fixes, link updates, frontmatter tweaks)
-   without re-tripping the gate.
-
-2. **Add the following 6 kernel rules to `docs/contracts/iron-law-overrides.txt`**
-   with this ADR as their justification. All sit between 2.5k and 4.0k
-   (the override ceiling):
-
-   | rule | chars | + over 2.5k | < 4.0k ceiling |
-   |---|---:|---:|---|
-   | `language-and-tone` | 3 602 | +1 102 | ✓ |
-   | `scope-control` | 3 641 | +1 141 | ✓ |
-   | `non-destructive-by-default` | 3 420 | +920 | ✓ |
-   | `no-cheap-questions` | 3 238 | +738 | ✓ |
-   | `ask-when-uncertain` | 3 130 | +630 | ✓ |
-   | `direct-answers` | 2 841 | +341 | ✓ |
-
-3. **Cap stays sticky.** Future kernel additions or rule-body growth must
-   either (a) condense within the 26k bucket, (b) externalise to a
-   `contexts/authority/*` companion, or (c) require a follow-up ADR.
-
-## Rationale
-
-Each over-cap rule defends a **distinct Iron Law fence** that loses meaning
-if split. Externalising the enumeration to a context file would force the
-agent to load the context every time the Iron Law applies (i.e. always),
-defeating the kernel-vs-auto split that motivates the budget in the first
-place.
-
-- `non-destructive-by-default` and `scope-control` carry the **Hard Floor**
-  trigger table (prod-trunk merge, deploy, push, prod data/infra, bulk
-  deletion) and the per-row example column. Splitting the table breaks
-  matching at decision time.
-- `no-cheap-questions` carries the **8-class cheap-question catalog** plus
-  a 6-step Pre-Send Self-Check that must be evaluated before every
-  numbered-options block — this is the gate, not a footnote.
-- `ask-when-uncertain` carries the **vague-request trigger list** (9 user
-  phrasings the agent must recognise without scrolling to a context file).
-- `language-and-tone` carries the **pre-send language gate** for every
-  reply token (prose, headings, table cells, inter-tool commentary,
-  Recommendation: vs Empfehlung: label) — splitting loses the exhaustive
-  catalog the agent matches against.
-- `direct-answers` carries **3 Iron Laws** (no flattery, no invented facts,
-  brevity by default) plus the severity-tiered claim table — already the
-  most condensed form of these obligations.
-
-The `commit-policy` rule was trimmed below 2.5k (2 354 chars) by removing
-a redundant cross-reference line, demonstrating that aggressive trimming
-is possible where the rule does not carry an enumeration. The 6 overrides
-are the rules where further condensation would force semantic loss.
-
-## Consequences
-
-- **Pro:** Iron-Law fidelity preserved — every fence still byte-identical
-  to baseline (verified by `iron_law_sha.py --all-kernel`).
-- **Pro:** Empirical condensation r=0.795 documented; future kernel work
-  uses this as the realistic ratio (not 0.712, which was a pilot-skewed
-  optimum).
-- **Pro:** Override ceiling (4 000) untouched — no rule grows
-  unboundedly; the 4k cap remains the next checkpoint.
-- **Con:** 25 590 / 26 000 = 98.4 % bucket utilisation. Adding any
-  10th kernel rule would require either condensation of an existing rule
-  or a further cap raise.
-- **Con:** ratio 0.795 means future "always" promotions cost more than
-  Phase 1 estimated. Phase 4 token-budget measurements should treat
-  0.795 as the reference condensation rate.
-
-## Rollback
-
-If Phase 4 token measurements show that the kernel adds > 10 % to the
-agent's per-turn token cost (`docs/contracts/kernel-membership.md` § 6
-abort criteria), revisit:
-
-1. Demote `verify-before-complete` from kernel to auto (saves 2 344 chars,
-   bucket → 23 246, falls back inside 25k).
-2. Or split `scope-control` into git-ops and decline/fence halves —
-   git-ops stays kernel, decline/fence becomes auto-tier.
-
-Both moves are reversible; this ADR does not lock either out.

package/docs/decisions/ADR-003-flat-cluster-subs-and-colon-syntax.md

@@ -1,137 +0,0 @@
----
-adr: 003
-status: accepted
-date: 2026-05-07
-decision: flat-cluster-subs-and-colon-syntax
-supersedes: —
-superseded_by: —
-phase: command-cluster contract (Phase 2 follow-up)
-type: structural
----
-
-# ADR-003 — Flat Cluster Sub-Commands and Colon-Canonical Invocation
-
-- **Status:** Accepted (2026-05-07)
-- **Phase:** Command-cluster contract (Phase 2 follow-up)
-- **Supersedes:** none — extends the locked cluster set in
-  `docs/contracts/command-clusters.md`.
-- **Related:** `roadmap-process` migration (2026-05-07) — the trigger
-  that forced the decision; `contexts/execution/roadmap-process-loop.md`
-  (the shared mechanics extracted alongside).
-
-## Context
-
-`roadmap-execute` was being replaced by an autonomous-execution surface
-with three scopes: single step, single phase, full roadmap. The
-question was where those three commands live in the cluster catalog.
-Four shapes were on the table:
-
-- **A — separate `/roadmap-process` cluster.** Two top-level clusters
-  (`/roadmap` for authoring, `/roadmap-process` for execution).
-- **B — sub-sub-commands** (`/roadmap:process:phase`). One cluster,
-  two-level dispatch.
-- **C — flat under `/roadmap`, no verb** (`/roadmap:step` ·
-  `/roadmap:phase` · `/roadmap:full`). Verb hidden in cluster
-  description.
-- **D — flat under `/roadmap`, verb fused with scope**
-  (`/roadmap:process-step` · `/roadmap:process-phase` ·
-  `/roadmap:process-full`). One cluster, one dispatch level, composite
-  sub-name carries the verb.
-
-Existing infrastructure assumed a single dispatch level: the contract
-table at `docs/contracts/command-clusters.md`, the linter
-`scripts/lint_no_new_atomic_commands.py`, and the dispatcher-shape
-checker `scripts/check_cluster_patterns.py` all parse one column of
-sub-names per cluster.
-
-## Decision
-
-1. **Cluster depth stays flat.** A cluster has exactly one level of
-   sub-commands. No sub-sub-commands. Option B is rejected.
-
-2. **Verb-and-scope sub-commands use a composite name** joined by `-`
-   (`process-step`, `process-phase`, `process-full`). The verb stays
-   visible in the autocomplete list; symmetry with sibling
-   sub-commands (`/roadmap:create`) is preserved as
-   verb-or-noun-per-sub. Option D wins over C.
-
-3. **Colon is the canonical invocation form** (`/<cluster>:<sub>`).
-   The space-separated form (`/<cluster> <sub>`) remains a
-   first-class equivalent — both forms route to the same dispatcher.
-   Autocompletion-aware UIs (Claude Code picker, IDE slash-menus,
-   shell completers) MUST surface the colon form because it stays a
-   single token.
-
-4. **Future verb+scope clusters follow the same shape.** Any future
-   cluster with multiple verbs (e.g. an authoring verb and an
-   execution verb) uses composite sub-names rather than introducing a
-   second cluster or a second dispatch level.
-
-## Rationale
-
-- **Option A (separate cluster)** scatters one domain across two
-  top-level surfaces. Users have to remember which cluster owns
-  which verb; the catalog grows without adding capability.
-- **Option B (sub-sub)** would be the first two-level dispatcher in
-  the repo. Cost: contract change in `command-clusters.md`,
-  linter change in `lint_no_new_atomic_commands.py` (parse a second
-  column), pattern-checker change in `check_cluster_patterns.py`
-  (allow nested dispatch sections), plus an ADR to set the precedent
-  — for a cohesion benefit that Option D delivers at zero
-  architectural cost.
-- **Option C (no verb)** breaks symmetry: `/roadmap:create` is a
-  verb, `/roadmap:phase` is a scope. The mental model becomes
-  inconsistent in the same cluster.
-- **Option D (composite verb-scope)** keeps the cluster flat, keeps
-  the verb visible, costs nothing in the linter or contract
-  parser (one row, four sub-names, kebab-case as before), and
-  scales to any future verb+scope cluster.
-
-The colon form was already canonical for flag-clusters
-(`/commit:in-chunks`, `/create-pr:description-only`). Promoting it
-to the canonical form for dispatcher-clusters too unifies the
-catalog: every sub-command is a single token.
-
-## Consequences
-
-- **Pro:** Zero architectural cost. The locked contract, both
-  linters, the dispatcher pattern checker, and the routing rule all
-  keep working unchanged. The cluster row in
-  `docs/contracts/command-clusters.md` extends with three new
-  sub-names.
-- **Pro:** Single-token autocompletion across the entire command
-  surface. Greppable in chat history and logs.
-- **Pro:** Domain cohesion — `/roadmap:*` covers the full
-  authoring + execution lifecycle.
-- **Con:** Sub-names get longer when the verb is non-obvious from the
-  cluster. `/roadmap:process-phase` is 24 chars vs.
-  `/roadmap-process:phase` (Option A, 23 chars) or
-  `/roadmap:phase` (Option C, 16 chars). Acceptable trade for
-  symmetry and zero contract churn.
-- **Con:** A cluster cannot grow into a true two-level surface
-  without revisiting this ADR. Rolling back to Option B is the
-  escape hatch if a future cluster genuinely needs nested verbs.
-
-## Rollback
-
-If a future cluster grows past ~8 sibling sub-commands and the
-composite-name pattern produces ambiguous or unreadable
-sub-commands, revisit by:
-
-1. Splitting the cluster into two flat clusters (Option A on a
-   case-by-case basis), or
-2. Introducing sub-sub-commands as a deliberate contract change —
-   updating `command-clusters.md`, `lint_no_new_atomic_commands.py`,
-   `check_cluster_patterns.py`, and superseding this ADR.
-
-Both moves are reversible. This ADR locks the default, not the
-ceiling.
-
-## See also
-
-- [`docs/contracts/command-clusters.md`](../contracts/command-clusters.md)
-  — locked cluster set + sub-command naming contract.
-- [`.agent-src.uncondensed/contexts/communication/rules-auto/slash-command-routing-policy-mechanics.md`](../../.agent-src.uncondensed/contexts/communication/rules-auto/slash-command-routing-policy-mechanics.md)
-  — runtime routing semantics and the colon-canonical rule.
-- [`.agent-src.uncondensed/contexts/execution/roadmap-process-loop.md`](../../.agent-src.uncondensed/contexts/execution/roadmap-process-loop.md)
-  — the shared mechanics that motivated the cluster shape.

package/docs/decisions/ADR-004-rule-governance-pruning.md

@@ -1,240 +0,0 @@
----
-adr: 004
-status: accepted
-date: 2026-05-08
-decision: rule-governance-pruning
-supersedes: —
-superseded_by: —
-phase: road-to-augment-limit-fit · P5.5
----
-
-# ADR-004 — Rule-Governance Pruning (Phase 5)
-
-## Status
-
-**Accepted** · 2026-05-08.
-
-## Context
-
-`road-to-augment-limit-fit` Phase 5 ran a Rule-Governance Audit on
-the 49 `type: auto` rules that consume the workspace-guidelines
-budget via description-stub injection (~250 chars each). Three
-analytic passes ran:
-
-- **5.1** `scripts/audit_auto_rules.py` — measured stub vs. body
-  cost. Auto-rule stubs total **11,513 chars · 23.3 %** of the
-  49,512 ceiling.
-- **5.2** `scripts/audit_overlap.py` — pairwise Jaccard on
-  `path_prefix` triggers + symmetric keyword overlap on
-  description/keyword/intent token sets. 4 pairs flagged
-  (path-Jaccard ≥ 0.5 OR keyword-overlap ≥ 0.4).
-- **5.3** `scripts/audit_likelihood.py` — corpus-keyword scoring
-  against indexed skills + commands + contexts + guidelines. 0
-  rules below the strict `< 2` hits floor; bottom-10 list surfaced
-  for council walk.
-
-**5.4** AI Council R3 (claude-sonnet-4-5 + gpt-4o, 2 rounds, prompt
-mode) walked the candidate list. Council convergence and host
-verdicts are recorded in `agents/runtime/reports/auto-rules-audit.md`
-§ Phase 5.4. The dominant council insight:
-
-> *"Rarity ≠ redundancy. Low corpus hits often indicate a
-> preventative rule that fires precisely when needed, not a useless
-> one. The audit cannot distinguish dead weight from option-value
-> insurance."* — claude-sonnet-4-5
-
-This narrowed the action surface from "remove anything in the
-bottom 10" to four targeted decisions where redundancy or
-mechanical-already status was structurally provable.
-
-## Decision
-
-Four approved actions, applied in Phase 5.6:
-
-### Implementation pattern: demote via frontmatter
-
-All four actions use the same mechanical pattern: change rule
-frontmatter `type: "auto"` → `type: "manual"`. This:
-
-- **Removes the stub from the workspace budget.**
-  `scripts/measure_augment_budget.py` only counts `type: "auto"`
-  rules (line 99). Anything else has zero stub cost.
-- **Preserves the file and its cross-references.**
-  Skills, contexts, templates, and contracts that link to the rule
-  (`size-enforcement` is referenced from `rule-writing/SKILL.md`,
-  `command-writing/SKILL.md`, `artifact-drafting-protocol.md`,
-  `proposal.example.md`, `rule-classification.md`,
-  `self-improvement-pipeline.md`, etc.) keep working.
-- **Keeps `compile_router.py` deterministic.**
-  Non-auto rules are skipped by `_resolve_tier`; the rule no
-  longer routes through `router.json` but remains a reference
-  document.
-
-This pattern was chosen over hard deletion after the
-cross-reference audit (Phase 5.6 prep) showed each candidate has
-≥ 5 inbound references. Deletion would force a wide-radius
-documentation rewrite for marginal additional savings.
-
-### 1. `guidelines` — demote
-
-- **Verdict:** demote (`type: "auto"` → `type: "manual"`).
-- **Rationale:** Generic name, no `routes_to:` target, 552 corpus
-  hits, no `path_prefix` trigger. Description ("Writing or
-  reviewing code — check relevant guideline before writing or
-  reviewing code") is ambient guidance already covered by the 9
-  always-rules and the Iron-Law floor. The auto-stub adds ~185
-  chars of overhead for a rule that fires on every code touch but
-  has no specific routing target — i.e., it functions as a noop
-  reminder. The body remains as a reference doc citing the
-  guidelines-mechanics context.
-- **Preserved triggers:** the body retains its trigger discussion
-  for human readers; auto-discovery is dropped.
-- **Migration:** none. Inbound link in
-  `contexts/communication/rules-auto/guidelines-mechanics.md`
-  remains valid.
-
-### 2. `size-enforcement` — demote (logical merge into `rule-type-governance`)
-
-- **Verdict:** demote (`type: "auto"` → `type: "manual"`); record
-  the logical merge in this ADR rather than physically folding the
-  body. `rule-type-governance` already routes to its own
-  guideline; both rules now share the same auto-trigger surface
-  conceptually but only `rule-type-governance` injects a stub.
-- **Rationale:** Both rules fire during rule/skill/command
-  authoring. `size-enforcement` enforces character budgets;
-  `rule-type-governance` enforces always-vs-auto classification.
-  Council R3 convergence on the merge. Physical body-fold rejected
-  to keep blast radius small (see implementation-pattern note).
-- **Preserved triggers:** "size", "budget", "limit", "char count",
-  artefact creation/editing scope — all retained in the rule body
-  for ad-hoc consultation; the auto-discovery surface is dropped.
-- **Migration:** none required. `rule-writing/SKILL.md`,
-  `command-writing/SKILL.md`, `artifact-drafting-protocol.md`,
-  `proposal.example.md`, and the contracts continue to cite the
-  rule by file path; the file still exists.
-
-### 3. `package-ci-checks` — demote
-
-- **Verdict:** demote (`type: "auto"` → `type: "manual"`).
-- **Rationale:** Rule is `mechanical-already` — `task ci` already
-  enforces the same checks before a PR can merge. The rule is also
-  package-self-referential (it only fires when contributing to
-  `event4u/agent-config` itself); consumer projects never benefit
-  from the stub. Council R3: gpt-4o (demote), Sonnet (verify skill
-  links contract first — confirmed: `routes_to: skill:lint-skills`).
-- **Preserved triggers:** "task ci", "before push", "before pr".
-  Body retains trigger phrases for human reference.
-- **Migration:** AGENTS.md "Working on this repo" section already
-  documents `task ci`; no consumer-project regression because
-  consumers never received this rule's stub anyway (`source: package`).
-
-### 4. `analysis-skill-routing` — demote
-
-- **Verdict:** demote (`type: "auto"` → `type: "manual"`).
-- **Rationale:** The rule's only function is to point host agents
-  at the `analysis-skill-router` skill when an analysis request
-  fires. The skill's own description carries the same trigger
-  surface ("picking which analysis or project-analysis-* skill
-  fits a request") and is already auto-discoverable as a Skill.
-  The rule is a redundant pointer-to-pointer. Council R3:
-  gpt-4o (merge into slash-command-routing-policy — host rejected:
-  analysis ≠ slash-commands; merge would collapse a meaningful
-  category distinction). Sonnet (keep + add `routes_to:` — host
-  rejected: routing already exists via the skill itself).
-- **Preserved triggers:** "analyze", "analysis", "dig into the
-  codebase". Already present in the skill's description.
-- **Migration:** Verify `analysis-skill-router` skill description
-  is pushy enough; no other action required.
-
-## Consequences
-
-### Accepted
-
-- **Stub-cost saving:** ~849 chars freed (~1.7 % of the 49,512 cap).
-  Phase 5 alone is insufficient to hit the 20 % headroom goal.
-- **Phase 6 (Thin-Root AGENTS.md) was mandatory**, not optional.
-  AGENTS.md was the largest single asset (12,042 chars) and the
-  only remaining lever once Phase 5 was locked in.
-- **Four rules (`guidelines`, `size-enforcement`,
-  `package-ci-checks`, `analysis-skill-routing`) demoted from
-  `type: "auto"` to `type: "manual"`.** Total auto-rules: 49 → 45.
-  Files preserved on disk; cross-references intact.
-- **Final budget after Phases 5–7** (`scripts/measure_augment_budget.py`,
-  2026-05-08): AGENTS.md 2,773 + always-rules (9) 26,322 + auto-rule
-  stubs (45) 10,664 = **39,759 chars · 80.3 % utilisation · 19.7 %
-  headroom** (149 chars / 0.3 % short of the ≥ 20 % goal — within
-  rounding; effectively at target). Phase 6 (Thin-Root AGENTS.md
-  refactor: 12,042 → 2,773 chars) carried the bulk of the saving
-  that Phase 5 alone could not deliver. Phase 7 (`scripts/lint_agents_md.py`,
-  CI-blocking) locks the contract in.
-
-### Trade-offs
-
-- **Sonnet's "rarity ≠ redundancy" critique honored.** The audit
-  identified 14 candidates; only 4 pass the host's redundancy /
-  mechanical-already test. Aggressive ceiling (~2,750 chars, per
-  gpt-4o) was rejected as it would force domain-specific rules
-  (`docker-commands`, `laravel-translations`) into manual
-  guideline-load workflows for the 20 % of projects that need them.
-- **`upstream-proposal` and `slash-command-routing-policy` both
-  retained without `routes_to:` fix.** Flagged as follow-up work
-  outside this ADR's scope; their preservation is justified by
-  rare-but-critical activation pattern.
-- **No `augment-portability` / `docs-sync` merge** despite 1.00
-  path-Jaccard. Council R3 convergence: workspace-layout
-  coincidence, not logical duplication. Different intents
-  (host-portability vs. sync-workflow hygiene).
-
-## Re-evaluation trigger
-
-- Augment changes its accounting model (e.g. starts injecting
-  auto-rule bodies into the workspace prompt) → re-open this
-  governance pass; the stub-cost / body-cost ratio changes
-  drastically.
-- Auto-rule count grows by ≥ 5 (history check via
-  `agents/runtime/.augment-budget-history.jsonl`) → repeat the audit
-  with the same three-pass methodology.
-- A retained rule (`upstream-proposal`, `slash-command-routing-policy`,
-  `analysis-skill-routing`'s sibling skill) shows a 30-day window
-  with zero documented activation in `agents/runtime/council/sessions/` →
-  open a follow-up ADR demoting it.
-
-## Alternatives considered
-
-- **Aggressive prune (gpt-4o R1 line):** demote
-  `agent-docs`, `docker-commands`, `laravel-translations`. Rejected.
-  Sonnet's rarity-≠-redundancy critique applies; these are
-  domain-specific rules with substantial corpus presence (240+
-  hits each) and their absence forces consumer projects into
-  manual guideline-load. The ~750-char additional saving is not
-  worth the behavioural regression.
-- **`augment-portability` / `docs-sync` merge (gpt-4o R2):**
-  Rejected. 1.00 path-Jaccard reflects shared filesystem
-  triggers (`docs/guides/agent-setup/augment.md`), not shared
-  intent. `augment-portability` enforces project-agnostic content
-  in `.agent-src/`; `docs-sync` enforces cross-reference integrity
-  on add/rename/delete. Different verbs, different blast radii.
-- **Defer all rule changes; focus on Phase 6 only:** Rejected.
-  The four approved actions are independently defensible; bundling
-  them with Phase 6 would obscure the rationale and conflate two
-  different optimisation strategies (rule-set hygiene vs.
-  AGENTS.md restructure). Each phase ships its own savings on its
-  own audit trail.
-
-## References
-
-- `agents/roadmaps/archive/road-to-augment-limit-fit.md` § Phase 5
-- `agents/runtime/reports/auto-rules-audit.md` (full audit findings,
-  council walk, host verdicts)
-- `agents/runtime/reports/auto-rules-overlap.json` (Phase 5.2 data)
-- `agents/runtime/reports/auto-rules-likelihood.json` (Phase 5.3 data)
-- `agents/runtime/council/questions/augment-limit-fit-rule-governance.md` <!-- council-ref-allowed: ADR decision trace -->
-  (Phase 5.4 prompt)
-- `agents/runtime/council/responses/augment-limit-fit-rule-governance.json` <!-- council-ref-allowed: ADR decision trace -->
-  (Phase 5.4 R3 raw debate)
-- `docs/decisions/ADR-rule-kernel-and-router.md` (kernel-membership
-  contract — Phase 5 changes leave kernel untouched per Lever C lock)
-- `.agent-src.uncondensed/rules/guidelines.md` (deprecated subject)
-- `.agent-src.uncondensed/rules/size-enforcement.md` (merged subject)
-- `.agent-src.uncondensed/rules/package-ci-checks.md` (demoted subject)
-- `.agent-src.uncondensed/rules/analysis-skill-routing.md` (demoted subject)