@event4u/agent-config 1.21.0 → 1.23.0

package/.agent-src/skills/skill-writing/SKILL.md

@@ -295,6 +295,29 @@ utility libs, or simple state managers.
 * Renaming a heading to "Procedure:" without numbered steps or `###` sub-headings
 * **Always run `python3 scripts/skill_linter.py` before saving — 0 FAIL required**
 
+## Frugality Standards
+
+Apply the [Frugality Charter](../../contexts/contracts/frugality-charter.md)
+to every skill you author.
+
+**Examples in this artifact:**
+- Per the charter's default-terse rule, the SKILL.md `## Procedure`
+  opens with the action ("Run the linter"), not "Let me walk you
+  through…".
+- Per the cheap-question check, only emit numbered-options output
+  when consequences differ — never as a stylistic choice.
+- Per the post-action summary suppression, the example output ships
+  the artifact, not a wrapping `## Status` / `## Summary` block.
+
+**Pre-save self-check:**
+1. Does any procedure step open with "Let me", "Now I will", "Found
+   it", "OK", or "Alright"?
+2. Does the skill prescribe numbered-options output without a real
+   consequence trade-off?
+3. Does the example output include a post-action summary block?
+4. Does the description carry filler ("comprehensive", "advanced",
+   "powerful")?
+
 ## Do NOT
 
 * Write documentation-style, pointer-only, or too-broad skills ("Laravel skill")

package/.agent-src/skills/systematic-debugging/SKILL.md

@@ -2,6 +2,7 @@
 name: systematic-debugging
 description: "Use when hitting a bug, test failure, crash, or unexpected behavior — enforces reproduce → isolate → hypothesize → verify before any fix — even when the user just says 'this is broken' or 'quick fix'."
 source: package
+council_depth: deep
 ---
 
 # systematic-debugging
@@ -35,10 +36,28 @@ papers over an unknown cause is a regression waiting to happen.
 
 ```
 NO FIX WITHOUT ROOT CAUSE. NO ROOT CAUSE WITHOUT EVIDENCE.
+NO BUG MARKED FIXED WITHOUT A REGRESSION TEST.
 ```
 
 "I think it's probably X" is not evidence. A log line, a stack trace, a
-diff, a reproduced failure — those are evidence.
+diff, a reproduced failure — those are evidence. A green run after a
+manual edit is not a regression test — a test that fails without the fix
+and passes with it, is.
+
+## The 6-phase loop (the spine)
+
+Every debug session walks these six phases in order. Treat them as a
+checklist — tick each box before claiming the bug fixed:
+
+- [ ] **1. Reproduce** — bug triggers on demand, smallest possible setup _(Phase 1)_
+- [ ] **2. Minimize** — smallest failing case isolated, irrelevant context stripped _(Phase 1, step 2)_
+- [ ] **3. Hypothesize** — one testable theory stated in one sentence _(Phase 3)_
+- [ ] **4. Instrument** — log / breakpoint / trace at the boundary where expected ≠ actual _(Phase 2)_
+- [ ] **5. Fix** — single, minimal change targeting the root cause _(Phase 4, step 2)_
+- [ ] **6. Regression-test** — failing test added that catches the bug returning **(MANDATORY — no exception)** _(Phase 4, step 1 + Validation checklist)_
+
+Skipping a box (especially #2 or #6) is the single biggest cause of
+wasted debug time and re-opened bugs.
 
 ## Procedure
 
@@ -242,10 +261,11 @@ When reporting debug findings to the user:
 
 Before declaring a bug fixed:
 
+* [ ] **6-phase loop** — all six boxes (Reproduce → Minimize → Hypothesize → Instrument → Fix → Regression-test) ticked
 * [ ] The failure was reproduced before any code changed
 * [ ] The root cause is named explicitly, not "probably"
 * [ ] Evidence (log, trace, diff) supports the named root cause
-* [ ] A failing test reproducing the bug was added or updated
+* [ ] **Regression test added — MANDATORY**: a test that fails without the fix and passes with it. No exception. "Manual reproduction confirmed gone" is not a regression test
 * [ ] The fix is minimal and targets the root cause, not the symptom
 * [ ] The regression test now passes
 * [ ] Adjacent tests still pass

package/.agent-src/skills/technical-specification/SKILL.md

@@ -1,7 +1,8 @@
 ---
 name: technical-specification
-description: "Use when the user says "write a spec", "create RFC", or "document this decision". Writes technical specifications, RFCs, and ADRs with clear structure."
+description: "Use when the user says "write a spec", "create RFC", "write a PRD", or "document this decision". Writes technical specifications, PRDs, RFCs, and ADRs with clear structure."
 source: package
+council_depth: deep
 ---
 
 # technical-specification
@@ -10,6 +11,7 @@ source: package
 
 Use this skill when:
 - Writing a technical specification for a new feature or system
+- Writing a Product Requirements Document (PRD) when user pain leads and solution shape follows
 - Creating an architecture decision record (ADR)
 - Documenting a technical RFC (Request for Comments)
 - Planning a significant technical change that needs team review
@@ -69,6 +71,59 @@ For complex features or systems. Stored in `agents/features/` or module `agents/
 - {Links to related docs, tickets, or external resources}
 ```
 
+### Product Requirements Document (PRD)
+
+For features whose **shape is product-driven** rather than implementation-driven —
+when "what users get" matters more than "how the code is wired". Use a PRD
+when a Technical Specification would over-index on internals and under-index
+on user value. Stored in `agents/features/` next to the technical spec when
+both exist.
+
+```markdown
+# PRD: {Title}
+
+## Status
+{ Draft | In Review | Approved | Shipped | Parked }
+
+## Problem
+{The user-visible pain. One paragraph. Cite evidence — support tickets,
+analytics, user quotes — not assumptions.}
+
+## Success Criteria
+- {Measurable outcome with a number and a timeframe}
+- {Another measurable outcome}
+
+## Non-Goals
+- {What this PRD explicitly does NOT cover — protect scope}
+
+## User Stories
+- As a {role}, I want to {action}, so that {outcome}.
+- As a {role}, I want to {action}, so that {outcome}.
+
+## Major Modules
+{The 3-7 functional building blocks the feature decomposes into. One
+sentence each — what it does, not how. Implementation lives in the
+technical spec, not here.}
+
+- **{Module name}** — {one-sentence responsibility}
+- **{Module name}** — {one-sentence responsibility}
+
+## Open Questions
+- [ ] {Unresolved product question — pricing, permission, copy, edge case}
+
+## References
+- {Links to research, related PRDs, technical spec when it exists}
+```
+
+**PRD vs Technical Specification — when to pick which:**
+
+- **PRD first** when the user pain is clear but the solution shape is not
+  ("users can't share dashboards" → PRD scopes the problem; spec follows).
+- **Spec first** when the solution shape is clear but the implementation
+  is non-trivial ("rebuild auth on OAuth2" → spec leads; PRD often skipped).
+- **Both** when the feature is large enough that product and engineering
+  decisions belong in different artifacts.
+
 ### Architecture Decision Record (ADR)
 
 For significant technical decisions. Stored in `agents/decisions/`.
@@ -161,6 +216,8 @@ If a developer reads only this document, they should be able to build it.
 ## Auto-trigger keywords
 
 - technical spec
+- PRD
+- product requirements
 - RFC
 - ADR
 - architecture decision

package/.agent-src/skills/test-driven-development/SKILL.md

@@ -27,6 +27,30 @@ Do NOT use when:
 * Catch edge cases **before** they become production bugs.
 * Leave every change with a regression test that runs in CI.
 
+## Escalate to a SPARC-style 5-phase workflow when
+
+Plain TDD (red → green → refactor) is the right size for **most** work.
+A small subset benefits from a gated 5-phase wrapper —
+**S**pec → **P**seudocode → **A**rchitecture → **R**efine → **C**omplete —
+where each gate produces a written artifact before the next phase runs.
+
+Decision tree — escalate if **any** branch is true:
+
+* The ticket has **AC count > 5** (the spec itself is non-trivial — write
+  it down before testing it).
+* The change **modifies a contract** consumed by ≥1 other module
+  (public API signature, persisted schema, event payload, queue message).
+* The change cuts across **≥3 modules / bounded contexts** at once.
+
+When escalating: drop the `Spec` artifact in `agents/roadmaps/` (or the
+project's planning location), capture it as an ADR via [`adr-create`](../adr-create/SKILL.md)
+when the decision is load-bearing, then run plain TDD inside each
+`Refine` cycle. Do **not** skip RED→GREEN inside a SPARC phase — the
+wrapper adds gates, not exemptions.
+
+For everything else (single-AC ticket, leaf-module change, bug fix),
+stay on plain TDD — the section above.
+
 ## The core discipline
 
 ```

package/.agent-src/skills/threat-modeling/SKILL.md

@@ -2,6 +2,7 @@
 name: threat-modeling
 description: "Use when adding auth, webhooks, uploads, queues, secrets, tenant boundaries, or public endpoints — produces trust boundaries + abuse cases mapped to files, BEFORE implementation."
 source: package
+council_depth: deep
 ---
 
 # threat-modeling

package/.agent-src/templates/agent-settings.md

@@ -204,12 +204,12 @@ pipelines:
 
 # --- Roadmap execution ---
 #
-# Controls when /roadmap execute runs the project's quality pipeline.
+# Controls when /roadmap:process-* runs the project's quality pipeline.
 # Step checkboxes and the dashboard are ALWAYS updated in the same
 # response — that cadence is governed by `roadmap-progress-sync` and
 # is non-negotiable. This setting only governs *quality tool runs*.
 roadmap:
-  # When to run quality tools during /roadmap execute.
+  # When to run quality tools during /roadmap:process-step|phase|full.
   #   end_of_roadmap = once, before archiving (default — fastest, fewest tokens)
   #   per_phase      = once after every completed phase
   #   per_step       = after every completed step (legacy; highest token cost)
@@ -293,6 +293,16 @@ commands:
     # Commands to never suggest. Still work when typed explicitly.
     blocklist: []
 
+  # Pre-creation preview of the generated PR description in `/create-pr`.
+  # When `false` (default): skip the title/body preview + adjust loop;
+  # use the generated content directly to create the PR. Saves agent
+  # tokens by avoiding a re-render of the full description in chat.
+  # When `true`: show title and body in copyable code blocks and ask
+  # for adjustments before creating the PR.
+  # `/create-pr:description-only` always previews — that is its sole purpose.
+  create_pr:
+    preview_description: false
+
 # --- Telemetry (artefact engagement, default-off) ---
 #
 # Records — at task / phase-step boundaries — which artefacts (skills,
@@ -301,6 +311,69 @@ commands:
 # repo (gitignored). Maintainer-targeted feature; consumers leave it
 # off. See `.augment/contexts/contracts/artifact-engagement-flow.md`
 # (once Phase 3 of road-to-artifact-engagement-telemetry lands).
+# --- Verbosity (token frugality) ---
+#
+# Five toggles controlling what the agent shows after acting.
+# Default = terse. Flip to true to restore legacy verbose output.
+# See agents/roadmaps/road-to-token-frugality.md for the full rationale
+# and the contexts/contracts/frugality-charter.md for the writer-side
+# standard.
+verbosity:
+  # Show generated commit messages, PR titles/bodies, branch names
+  # before acting. false = use generated content directly.
+  preview_artifacts: false
+
+  # Confirmation prompts for routine workflow steps when there is
+  # one obvious answer ("looks good — commit?"). Iron-Law gates
+  # (commit-policy, scope-control git-ops, non-destructive) ALWAYS
+  # ask regardless of this flag.
+  routine_confirmations: false
+
+  # Offer "run AI Council on this?" inside delivery commands
+  # (/feature-plan, /review-changes, /roadmap-create). Council
+  # commands themselves (/council, /create-pr → already excluded)
+  # are unaffected.
+  offer_council_in_delivery: false
+
+  # Multi-line status / summary blocks after a successful action.
+  # off | minimal | full — default minimal (one-line confirmation).
+  post_action_reports: minimal
+
+  # Intent announcements ("Let me check…", "Now I will…", "Found
+  # it") in skill bodies. false = act and emit the result.
+  intent_announcements: false
+
+  # Script stdout chatter from `scripts/*.py`, `scripts/*.sh`, and
+  # `.augment/scripts/`. Read by the helper module
+  # `scripts/_lib/script_output.py`.
+  #   silent  = stderr only; success = no output
+  #   minimal = one summary line per script (default)
+  #   verbose = pre-Phase-10 behaviour (per-step prints)
+  # Override per-process: AGENT_SCRIPT_VERBOSITY={silent,minimal,verbose}
+  # Iron-Law surfaces (release confirms, install secrets prompts,
+  # error markers) ignore this key and stay loud.
+  script_output: minimal
+
+  # Suppress the `task: [name] cmd...` echo line that Taskfile prints
+  # before each task body. false = keep echoes (default Taskfile
+  # behaviour). true = the Taskfile sets `silent: true` on every
+  # safe task per Phase 10.3.
+  taskfile_command_echo: false
+
+# --- Caveman speak (authoring-only) ---
+#
+# Caveman-style compression scope for newly authored prose. The
+# compile-time toggle (`caveman.speak`) is added in Phase 8.
+# `speak_scope` lands now so the charter and consumers can pin it.
+caveman:
+  # speak_scope = how widely caveman-speak grammar applies in chat
+  #   off          = no caveman grammar in output (compile-time still
+  #                  governed by caveman.speak)
+  #   prose_only   = caveman in body prose; numbered options +
+  #                  Iron-Law-literal blocks stay full prose
+  #   aggressive   = caveman everywhere except Iron-Law literals
+  speak_scope: prose_only
+
 telemetry:
   artifact_engagement:
     # Master switch. `false` (default) produces zero file IO and zero
@@ -332,6 +405,10 @@ Personal and project-level settings (initial file written by
 **Key paths use dot-notation** to denote nesting: `personal.user_name`
 lives under `personal:` in YAML.
 
+The `verbosity.*` and `caveman.speak_scope` rows are summarized below;
+the canonical narrative lives in
+[`docs/customization.md` § Verbosity](../../docs/customization.md#verbosity).
+
 | Key path | Values | Default | Description |
 |---|---|---|---|
 | `cost_profile` | `minimal`, `balanced`, `full`, `custom` | `minimal` | Selects which agent surfaces are active. See [Cost profiles](#cost-profiles). |
@@ -361,7 +438,7 @@ lives under `personal:` in YAML.
 | `hooks.chat_history.enabled` | `true`, `false` | `true` | Register the chat-history hooks (`append` on `after_step`, `halt_append` on `on_halt`). Gated by **both** this flag AND `chat_history.enabled`; either off → no chat-history hook registers. Schema v4: every entry self-identifies via a 16-char session fingerprint, no ownership/sidecar layer. |
 | `hooks.chat_history.script` | path | `scripts/chat_history.py` | Override path to the chat-history CLI. Set only when the script lives outside the standard location. |
 | `pipelines.skill_improvement` | `true`, `false` | `true` | When `true`: propose learning capture after meaningful tasks. When `false`: silent. Included in every profile except `custom`. |
-| `roadmap.quality_cadence` | `end_of_roadmap`, `per_phase`, `per_step` | `end_of_roadmap` | When `/roadmap execute` runs the project's quality pipeline. Default skips per-step / per-phase runs and gates only the final archival. `per_phase` runs once after every phase; `per_step` is the legacy verbose mode. Step checkboxes and the dashboard are always updated regardless. `verify-before-complete` still requires fresh output before any "roadmap complete" claim. |
+| `roadmap.quality_cadence` | `end_of_roadmap`, `per_phase`, `per_step` | `end_of_roadmap` | When `/roadmap:process-step|phase|full` runs the project's quality pipeline. Default skips per-step / per-phase runs and gates only the final archival. `per_phase` runs once after every phase; `per_step` is the legacy verbose mode. Step checkboxes and the dashboard are always updated regardless. `verify-before-complete` still requires fresh output before any "roadmap complete" claim. |
 | `subagents.implementer_model` | model alias or empty | _(empty)_ | Model for implementer subagents. Empty = same tier as session model. See [subagent-configuration](../contexts/subagent-configuration.md). |
 | `subagents.judge_model` | model alias or empty | _(empty)_ | Model for judge subagents. Empty = one tier above implementer (opus if sonnet, sonnet if haiku). |
 | `subagents.max_parallel` | integer | `3` | Maximum parallel subagent invocations. `1` serializes. |
@@ -375,6 +452,13 @@ lives under `personal:` in YAML.
 | `commands.suggestion.cooldown_seconds` | integer | `600` | Cooldown between re-suggestions of the same `(command, evidence)` pair. `600` = 10m. |
 | `commands.suggestion.max_options` | integer | `4` | Max number of command suggestions before the always-present "run as-is" option (total rendered = `max_options + 1`). |
 | `commands.suggestion.blocklist` | list of command names | `[]` | Commands that never appear as a suggestion. They still work when typed explicitly. |
+| `commands.create_pr.preview_description` | `true`, `false` | `false` | When `false`: `/create-pr` skips the title/body preview + adjust loop and uses the generated content directly. Saves agent tokens. When `true`: show title and body before creating and ask for adjustments. `/create-pr:description-only` always previews regardless of this setting. |
+| `verbosity.preview_artifacts` | `true`, `false` | `false` | Show generated commit messages, PR titles/bodies, branch names before acting. `false` = use generated content directly. See [`road-to-token-frugality`](../../../agents/roadmaps/road-to-token-frugality.md) Phase 2/3. |
+| `verbosity.routine_confirmations` | `true`, `false` | `false` | Confirmation prompts for routine workflow steps when there is one obvious answer ("looks good — commit?"). Iron-Law gates (`commit-policy`, `scope-control` git-ops, `non-destructive-by-default`) ALWAYS ask regardless. |
+| `verbosity.offer_council_in_delivery` | `true`, `false` | `false` | Offer "run AI Council on this?" inside delivery commands (`/feature-plan`, `/review-changes`, `/roadmap-create`). Council commands themselves are unaffected. |
+| `verbosity.post_action_reports` | `off`, `minimal`, `full` | `minimal` | Multi-line status / summary blocks after a successful action. `off` = no report; `minimal` = one-line confirmation; `full` = bullet list. |
+| `verbosity.intent_announcements` | `true`, `false` | `false` | Intent announcements ("Let me check…", "Now I will…", "Found it") in skill bodies. `false` = act and emit the result. |
+| `caveman.speak_scope` | `off`, `prose_only`, `aggressive` | `prose_only` | How widely caveman-speak grammar applies in chat. `off` = no caveman grammar; `prose_only` = caveman in body prose, numbered options + Iron-Law-literal blocks stay full prose; `aggressive` = caveman everywhere except Iron-Law literals. Compile-time toggle (`caveman.speak`) lands in Phase 8. |
 | `telemetry.artifact_engagement.enabled` | `true`, `false` | `false` | Master switch for the artefact engagement log. Default-off; zero file IO and zero token cost when `false`. Maintainer-targeted; consumers leave it off. |
 | `telemetry.artifact_engagement.granularity` | `task`, `phase-step`, `tool-call` | `task` | Boundary at which events are recorded. `tool-call` is expensive — opt-in only. |
 | `telemetry.artifact_engagement.record.consulted` | `true`, `false` | `true` | When `true`: record artefacts loaded into context. |

package/.agent-src/templates/command.md

@@ -20,6 +20,11 @@ name: {command-name}
 description: {Short description of what the command does}
 disable-model-invocation: true
 skills: [{optional-skill-1}, {optional-skill-2}]
+suggestion:
+  eligible: true
+  trigger_description: "natural-language pattern, comma-separated examples"
+  trigger_context: "concrete signal — branch name, file pattern, recent tool output"
+# council_depth: deep   # uncomment for architecture/refactor/bug-diagnose commands
 ---
 
 <!-- FRONTMATTER RULES (delete this comment when done):
@@ -27,6 +32,17 @@ skills: [{optional-skill-1}, {optional-skill-2}]
   - description: short, human-readable — what the command does
   - disable-model-invocation: ALWAYS true for commands (prevents Claude from auto-invoking)
   - skills: optional — list skills this command references or delegates to
+  - suggestion: REQUIRED — drives the in-host command suggester
+    - eligible: true  → set trigger_description + trigger_context
+    - eligible: false → set rationale (why never auto-suggested)
+    See agents/contexts/command-suggestion-eligibility.md for guidance.
+  - council_depth: optional — only `deep` is accepted. **Omit the key
+    for default depth** (`standard` is the implicit default and is
+    rejected by the schema — every frontmatter byte counts). Set `deep`
+    when this command triggers AI Council on architecture, refactoring,
+    or bug-diagnosis artefacts. The host translates `deep` into
+    `--depth deep` on the council CLI, raising the round floor to
+    `ai_council.deep_min_rounds`. See .augment/skills/ai-council/SKILL.md.
 -->
 
 # /{command-name}
@@ -51,16 +67,21 @@ skills: [{optional-skill-1}, {optional-skill-2}]
 
 ### N. Present findings
 
-<!-- For audit/analysis commands: always present findings before applying changes.
-     For action commands: show summary of what was done. -->
+<!-- For audit/analysis commands: state findings, then act or hand back.
+     For action commands: state what was done.
 
-Ask the user:
+     Default-terse per the
+     [Frugality Charter](../contexts/contracts/frugality-charter.md):
+     no preview-then-confirm pair, no "Ready to proceed?" gate, no
+     numbered options unless options differ in *consequence* (per
+     `no-cheap-questions § Pre-Send Self-Check`). Routine confirmations
+     are governed by `verbosity.routine_confirmations: false` (default).
 
-```
-> 1. {Option 1}
-> 2. {Option 2}
-> 3. Skip — report only
-```
+     Only emit a numbered-options block when ALL of:
+       1. Two or more options carry distinct consequences (not sequencing/format),
+       2. The user has not fenced the next step (per `scope-control § fenced step`),
+       3. No option violates `commit-policy`, `scope-control § git-ops`,
+          or `non-destructive-by-default`. -->
 
 ## Rules
 
@@ -74,7 +95,7 @@ Ask the user:
 
 Before considering a command complete:
 
-- [ ] **Frontmatter**: has `name`, `description`, `disable-model-invocation: true`
+- [ ] **Frontmatter**: has `name`, `description`, `disable-model-invocation: true`, `suggestion` block
 - [ ] **Steps**: numbered sub-headings (`### 1.`, `### 2.`, ...)
 - [ ] **Source of truth**: works on `.agent-src.uncompressed/`, not `.agent-src/` or `.augment/`
 - [ ] **No auto-apply**: presents findings, asks before destructive changes

package/.agent-src/templates/roadmaps.md

@@ -36,14 +36,22 @@ Templates for roadmap files stored in `agents/roadmaps/` or `app/Modules/{Module
     creating the roadmap — not during execution. Default: stay on the
     current branch. If the user declines, the topic is closed for this
     roadmap. See [`scope-control`](../rules/scope-control.md#decline--silence--no-re-asking-on-the-same-task).
+15. **Declare complexity tier.** Every roadmap declares
+    `complexity: lightweight` or `complexity: structural` in frontmatter.
+    Lightweight (default): ≤ 6 phases, ≤ 600 lines, no nested council
+    debates inside the roadmap. Structural (rare, opt-in): contract-layer
+    or budget-invariant changes; multi-round council, file-ownership
+    matrices, > 600 lines. Enforced by `task lint-roadmap-complexity`.
+    Standard: [`docs/contracts/roadmap-complexity-standard.md`](../docs/contracts/roadmap-complexity-standard.md).
 
 ---
 
 ## Quality Gates (always apply at completion)
 
 Every roadmap must pass the project's quality pipeline before it is
-considered done. **When** the pipeline runs during `/roadmap execute` is
-governed by `roadmap.quality_cadence` in `.agent-settings.yml`
+considered done. **When** the pipeline runs during
+`/roadmap:process-step|phase|full` is governed by
+`roadmap.quality_cadence` in `.agent-settings.yml`
 (`end_of_roadmap` default → once before archival; `per_phase` → after
 every phase; `per_step` → after every step). Either way, a final fresh
 run is mandatory before "complete" per `verify-before-complete`.

package/.agent-src/templates/rule.md

@@ -73,6 +73,7 @@ type: "always"
 tier: "kernel"
 description: "{One-line trigger sentence — what fires this rule}"
 source: package
+# council_depth: deep   # uncomment for rules that gate architecture/refactor/bug-diagnose flows
 load_context:
   - contexts/{area}/{file}.md
 triggers:
@@ -84,6 +85,12 @@ routes_to:
 
 # {Rule Title}
 
+<!-- Default-terse per the
+  [Frugality Charter](../contexts/contracts/frugality-charter.md):
+  start with the obligation. No "This rule explains…" / "The purpose of
+  this rule is…" / narrative intro before the Iron Law. Body sections
+  are pointers, not playbooks — defer detail to skills/guidelines. -->
+
 **Iron Law.** {The single non-negotiable behavior the rule enforces.}
 
 ## When this fires
@@ -119,6 +126,7 @@ for full detail; rules are pointers, not playbooks.}
 | `triggers` | no | Required on non-kernel rules per `rule-router.md`. |
 | `routes_to` | no | `skill:`, `guideline:`, `command:`, `contract:` targets. Forbidden on kernel rules. |
 | `alwaysApply` | no | Cursor/Cline sidecar — by convention `true` for `type: always`. |
+| `council_depth` | no | Only `deep` is accepted; **omit the key for default depth** (`standard` is the implicit default and is rejected by the schema — every frontmatter byte counts). Set `deep` when this rule gates AI Council on architecture, refactoring, or bug-diagnosis flows. Host translates to `--depth deep` on the council CLI. See `.augment/skills/ai-council/SKILL.md`. |
 
 ## Size budget
 

package/.agent-src/templates/skill.md

@@ -41,6 +41,23 @@ status: active
   See guidelines/agent-infra/runtime-layer.md for details.
 -->
 
+<!-- COUNCIL DEPTH (optional — delete this comment when done):
+  Add `council_depth: deep` to the frontmatter when this skill triggers
+  AI Council on architecture, refactoring, or bug-diagnosis artefacts.
+  The host translates `deep` into `--depth deep` on the council CLI,
+  raising the round floor to `max(ai_council.deep_min_rounds,
+  ai_council.min_rounds)`.
+
+  Only `deep` is accepted. **Omit the key for default depth** —
+  `standard` is the implicit default and is rejected by the schema
+  (every frontmatter byte counts against the context window).
+
+  Example:
+    council_depth: deep
+
+  See .augment/skills/ai-council/SKILL.md.
+-->
+
 <!-- DESCRIPTION RULES (delete this comment when done):
   - Start with "Use when..." — this is a TRIGGER, not a summary
   - Include 2-3 phrases users actually say: "create a DTO", "add column", "fix tests"
@@ -119,6 +136,38 @@ Do NOT use when:
 - Do NOT {anti-pattern 2}.
 - Do NOT {anti-pattern 3}.
 
+<!-- FRUGALITY STANDARDS (writer skills only — REQUIRED for skills whose
+  name ends in `-writing`, `-authoring`, or `-create`, AND for any
+  skill on the `FRUGALITY_WRITER_SKILLS` allowlist in
+  `scripts/skill_linter.py`. Mid-/untiered non-writer skills MUST
+  remove this section entirely.
+
+  Layer-1 of the linter checks for:
+    1. The literal H2 `## Frugality Standards`,
+    2. A markdown link matching the regex
+       `\[[^\]]+\]\([^)]*frugality-charter\.md[^)]*\)`.
+
+  Body shape — single charter cite, then 3–5 decidable pre-save
+  questions framed as *applying the charter*, not parallel rules
+  (council Pass #4 finding 0.B):
+
+  ## Frugality Standards
+
+  Per the [Frugality Charter](../../contexts/contracts/frugality-charter.md),
+  this writer applies the default-terse standard: no narrative intros,
+  no preview-then-confirm gates, no numbered options without a real
+  trade-off.
+
+  Pre-save self-check:
+  1. Does every body section start with the obligation, not an intro?
+  2. Are numbered options absent unless options differ in *consequence*?
+  3. Is every cited rule linked, not restated?
+  4. {artifact-specific question — e.g., for `command-writing`:
+     "Does the command honor `verbosity.routine_confirmations: false`?"}
+  5. {artifact-specific question — e.g., for `rule-writing`:
+     "Does the rule body open with the Iron Law, no preamble?"}
+-->
+
 <!-- SENIOR-TIER STUB BLOCKS (delete entire section if not `tier: senior`):
   Senior-tier skills (frontmatter `tier: senior`) require four extra
   blocks per `.agent-src.uncompressed/rules/skill-quality.md` §

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Shared agent configuration \u2014 skills for AI coding tools (Claude Code, Augment, Cursor, Cline, Windsurf, Gemini CLI).",
-    "version": "1.21.0"
+    "version": "1.23.0"
   },
   "plugins": [
     {
@@ -15,6 +15,7 @@
       "source": "./",
       "strict": false,
       "skills": [
+        "./.claude/skills/adr-create",
         "./.claude/skills/adversarial-review",
         "./.claude/skills/agent-docs-writing",
         "./.claude/skills/agent-handoff",
@@ -42,6 +43,9 @@
         "./.claude/skills/chat-history-import",
         "./.claude/skills/chat-history-learn",
         "./.claude/skills/chat-history-show",
+        "./.claude/skills/challenge-me",
+        "./.claude/skills/challenge-me-vision",
+        "./.claude/skills/challenge-me-with-docs",
         "./.claude/skills/check-current-md",
         "./.claude/skills/check-refs",
         "./.claude/skills/code-refactoring",
@@ -58,6 +62,7 @@
         "./.claude/skills/context-document",
         "./.claude/skills/context-refactor",
         "./.claude/skills/conventional-commits-writing",
+        "./.claude/skills/cost-report",
         "./.claude/skills/copilot-agents",
         "./.claude/skills/copilot-agents-init",
         "./.claude/skills/copilot-agents-optimization",
@@ -109,6 +114,7 @@
         "./.claude/skills/git-workflow",
         "./.claude/skills/github-ci",
         "./.claude/skills/grafana",
+        "./.claude/skills/grill-me",
         "./.claude/skills/guideline-writing",
         "./.claude/skills/implement-ticket",
         "./.claude/skills/jira-integration",
@@ -168,6 +174,7 @@
         "./.claude/skills/package-test",
         "./.claude/skills/performance",
         "./.claude/skills/performance-analysis",
+        "./.claude/skills/persona-writing",
         "./.claude/skills/pest-testing",
         "./.claude/skills/php-coder",
         "./.claude/skills/php-debugging",
@@ -201,12 +208,17 @@
         "./.claude/skills/review-routing",
         "./.claude/skills/rice-prioritization",
         "./.claude/skills/roadmap",
+        "./.claude/skills/roadmap-ai-council",
         "./.claude/skills/roadmap-create",
-        "./.claude/skills/roadmap-execute",
         "./.claude/skills/roadmap-management",
+        "./.claude/skills/roadmap-process-full",
+        "./.claude/skills/roadmap-process-phase",
+        "./.claude/skills/roadmap-process-step",
+        "./.claude/skills/roadmap-writing",
         "./.claude/skills/rtk-output-filtering",
         "./.claude/skills/rule-compliance-audit",
         "./.claude/skills/rule-writing",
+        "./.claude/skills/script-writing",
         "./.claude/skills/security",
         "./.claude/skills/security-audit",
         "./.claude/skills/sentry-integration",

package/AGENTS.md

@@ -167,9 +167,9 @@ appends to `agents/.rule-budget-history.jsonl`.
 
 ```
 .agent-src.uncompressed/      ← edit here
-  skills/       (136 skills)
-  rules/        (58 rules)
-  commands/     (95 commands)
+  skills/       (140 skills)
+  rules/        (60 rules)
+  commands/     (103 commands)
   personas/     (7 personas)
   templates/    (AGENTS.md, copilot-instructions.md, skill.md, …)
   contexts/