@event4u/agent-config 7.5.0 → 8.0.0

package/dist/agent-src/skills/roadmap-writing/SKILL.md

@@ -84,6 +84,25 @@ and council-pass notes capture the *why*; checkboxes capture the
 [`roadmap-progress-sync`](../../rules/roadmap-progress-sync.md)
 Iron Law #2.
 
+### 4b. Declare the execution mode (frontmatter)
+
+Every new roadmap declares how a later `/roadmap:process-*` run should
+interact, via `execution.mode:` in frontmatter — `autonomous` (one
+run-start execution-contract confirmation, then uninterrupted except
+safety floors), `phase-checkpoints` (halt + compact status per phase
+boundary), or `interactive` (absent-field default; omit field).
+Semantics: [`templates/roadmaps.md` rule 19](../../templates/roadmaps.md);
+run mechanics:
+[`roadmap-execution-contract`](../../contexts/execution/roadmap-execution-contract.md).
+Field is intent, never a permission grant — grants happen only at the
+run-start contract. `/roadmap:create` asks this as one question; when
+authoring a roadmap directly, ask it too (follow-ups pre-select the
+parent's mode but always re-ask). **Authoring duty for `autonomous`:**
+steps must be precise enough to clear `ask-when-uncertain` vague-
+trigger patterns — vagueness resolved at authoring time, not mid-run;
+pre-existing `[~]` items in an `autonomous` roadmap draw a lint
+warning (they guarantee the archival gate fires later).
+
 ### 5. Exit & rollback per phase
 
 Each phase declares **exit criteria** (decidable signals that the
@@ -91,6 +110,17 @@ phase is done) and **rollback** (what to revert if the phase fails).
 A phase without exit criteria is open-ended; a phase without
 rollback assumes success.
 
+### 5b. Blockers are structured, not free prose
+
+Gate only user or maintainer can clear — decision, external
+dependency, evidence threshold, kernel-budget soak window — records
+as `## Blockers` entry (`### blocker: <id>` with `Status` / `Owner` /
+`Blocks` / `What to do` / `Resolved when`), never a stray "blocked on
+X" sentence. Dashboard generator parses these into overview's
+`Blocker` column and per-roadmap breakdown. Full shape:
+[`templates/roadmaps.md` rule 20](../../agent-src/templates/roadmaps.md).
+Omit section entirely when roadmap has no such gate.
+
 ### 6. Step-marker semantics — pick `[~]` (defer) vs `[-]` (cancel) honestly
 
 Difference carries load when authoring (and especially when rewriting
@@ -166,7 +196,7 @@ capabilities into the suite:
 
 Ordinary internally-originated roadmap → **skip this section**; §§ 0–7
 are the whole job. Don't bolt a Provenance block or gap-table onto a
-plan needing neither (template rule 18).
+plan needing neither (template rule 19).
 
 When it fires, add four moves to §§ 0–7:
 
@@ -282,7 +312,7 @@ to every roadmap you author.
   skill dump, not integration.
 * Add a `## Provenance` block (or gap-table) to an **internally
   originated** roadmap — § 8 is conditional; an empty Provenance section
-  is noise (template rule 18).
+  is noise (template rule 19).
 * Name the raw competitor / tool in a tracked roadmap, or paste a raw
   source link — anonymize + `ENC1:`-encrypt
   ([`source-confidentiality`](../../rules/source-confidentiality.md)).

package/dist/agent-src/skills/root-cause-frameworks/SKILL.md

@@ -1,18 +1,15 @@
 ---
 name: root-cause-frameworks
 description: "Use when tracing the root cause of a resolved incident or recurring bug — 5-whys chain, fishbone categorisation, contributing-factors split — even if the user says 'why does this keep breaking?'."
-source: package
 domain: quality
 model_tier: high
 workspaces:
   - engineering
 packs:
   - analysis-workbench
-lifecycle: active
 trust:
   level: professional
   confidence: medium
-  human_review_required: false
 install:
   default: false
   removable: true

package/dist/agent-src/skills/security-audit/SKILL.md

@@ -3,6 +3,7 @@ model_tier: high
 name: security-audit
 description: "ONLY when user explicitly requests: security audit, vulnerability scan, or penetration test review. NOT for regular feature work."
 domain: quality
+parallelizable: files
 workspaces:
   - engineering
 packs:

package/dist/agent-src/skills/skill-improvement-pipeline/SKILL.md

@@ -116,6 +116,10 @@ After creation:
 2. Copy to `.augment/`
 3. Mark hash: `./scripts-run src/scripts/condense --mark-done "{relative_path}"`
 4. Regenerate tools: `./scripts-run src/scripts/condense --generate-tools`
+5. **If from a knowledge page** (`agents/knowledge/procedures/skill-candidates.md`
+   or any `agents/knowledge/` page) — degrade the source to a pointer;
+   promotion isn't complete otherwise (double-maintenance risk):
+   `./scripts-run src/scripts/degrade_to_pointer --source "<knowledge-path>[#<anchor>]" --artifact "{relative_path}" --date "<YYYY-MM-DD>"`
 
 ### Step 5: Decide scope
 

package/dist/agent-src/skills/source-discovery/SKILL.md

@@ -38,9 +38,9 @@ discover the real source  →  Evidence Report (Verified / Assumed / Gaps)  →
 Scaffold the report cheaply so it never gets skipped:
 
 ```bash
-python3 src/scripts/evidence_report.py git-state            # fail-fast: abort if a rebase/merge/cherry-pick is in progress
-python3 src/scripts/evidence_report.py init --task "<task>" # writes the gitignored session report
-python3 src/scripts/evidence_report.py add --bucket verified --claim "users.email is unique" --source "db/schema/users.sql:23"
+./scripts-run src/scripts/evidence_report git-state            # fail-fast: abort if a rebase/merge/cherry-pick is in progress
+./scripts-run src/scripts/evidence_report init --task "<task>" # writes the gitignored session report
+./scripts-run src/scripts/evidence_report add --bucket verified --claim "users.email is unique" --source "db/schema/users.sql:23"
 ```
 
 **Provenance on every item** (`observed_at` / `source` / `version`). Within a
@@ -165,6 +165,25 @@ signal, never silently commit); trust and commit are always human-gated. Full mo
 the three classes + memory tiers:
 [`project-intelligence`](../../agent-src/contexts/execution/project-intelligence.md).
 
+## Knowledge capture (`api_shape_learned` / `convention_detected` events)
+
+A confirmed API/GraphQL shape (§B) or an observed coding convention with
+≥ 2 supporting locations is worth persisting for the team, distinct
+from the per-session Evidence Report above. Append to the knowledge
+intake — never write a tracked page mid-task:
+
+```bash
+./scripts-run src/scripts/emit_knowledge_event --type api_shape_learned \
+    --endpoint "<path>" --method "<verb>" --request-schema '<json>' --response-schema '<json>'
+
+./scripts-run src/scripts/emit_knowledge_event --type convention_detected \
+    --pattern "<pattern>" --evidence "file:line" --sample-size <N> --scope project
+```
+
+`/team-knowledge consolidate` turns accumulated events into
+`agents/knowledge/concepts/` pages as a reviewed batch — see
+[`knowledge-pages`](../../templates/contexts/knowledge-pages.md).
+
 ## Gotchas
 
 - A card's positive structure is **never** "Verified" on the card alone — it is

package/dist/agent-src/skills/subagent-orchestration/SKILL.md

@@ -307,22 +307,41 @@ prefer the cheaper one (`do-and-judge` < `do-and-judge-two-stage` <
 
 ### 4. Dispatch
 
-Hand off to the matching command:
-
-* `do-and-judge` → [`/do-and-judge`](../../commands/do-and-judge.md)
-* `do-in-steps` → [`/do-in-steps`](../../commands/do-in-steps.md)
-* `judge` (standalone) → [`/judge`](../../commands/judge.md)
-
-Modes without a dedicated command (`do-in-parallel`,
-`do-competitively`, `judge-with-debate`) are orchestrated inline via
-the skill — describe the dispatch explicitly in chat so the user can
-follow it.
+Use the matching dispatch prompt and orchestrate inline via this skill.
+Describe each dispatch step explicitly in chat so the user can follow it.
+
+* `do-and-judge` → [`prompts/do-and-judge.md`](prompts/do-and-judge.md)
+* `do-and-judge-two-stage` → [`prompts/do-and-judge-two-stage.md`](prompts/do-and-judge-two-stage.md)
+* `do-in-steps` → [`prompts/do-in-steps.md`](prompts/do-in-steps.md)
+* `do-in-parallel` → [`prompts/do-in-parallel.md`](prompts/do-in-parallel.md)
+* `do-competitively` → [`prompts/do-competitively.md`](prompts/do-competitively.md)
+* `judge-with-debate` → [`prompts/judge-with-debate.md`](prompts/judge-with-debate.md)
+* `do-in-worktrees` → [`prompts/do-in-worktrees.md`](prompts/do-in-worktrees.md)
+* Standalone judge → judge prompt in [`prompts/do-and-judge.md`](prompts/do-and-judge.md)
 
 ### 5. Report
 
 Follow the output format below. Never merge a diff without reporting
 the judge verdict.
 
+### 6. Emit telemetry
+
+After every auto-dispatched run, write one telemetry line to
+`agents/runtime/state/audit/YYYY-MM.jsonl` (current UTC month — use
+`new Date().toISOString().slice(0, 7)` for the filename). Standard
+audit-log-v1 object with `input_kind: "orchestration"` and an
+`orchestration` sub-object per
+[`orchestration-telemetry.md`](../../agent-src/contexts/execution/orchestration-telemetry.md).
+
+Minimal emit (fill what is observable; `token_delta_provenance: "estimated"` if
+host usage metadata is unavailable):
+
+```json
+{"schema_version":1,"id":"<ulid>","ts":"<iso>","work_id":"<work_id>","phase":"implement","outcome":"success","confidence_band":"high","risk_class":"low","input_kind":"orchestration","type":"phase","orchestration":{"task_size_estimate":<int>,"spawn_count":<int>,"tiers":[...],"token_delta":<int>,"token_delta_provenance":"estimated","wall_clock_ms":<int>,"outcome":"DONE","verify_mode":"deterministic"}}
+```
+
+Skip emit when `subagents.enabled: false` or `spawn_count == 0` (in-session run).
+
 ## Gotcha
 
 * **Identical model both sides** — same blind spots. The Iron Law
@@ -358,10 +377,10 @@ the judge verdict.
 
 | Task                                 | Skill / command                      |
 |--------------------------------------|--------------------------------------|
-| Configuration reference              | [`subagent-configuration`](../../contexts/subagent-configuration.md) |
-| Do-and-judge loop                    | [`/do-and-judge`](../../commands/do-and-judge.md) |
-| Stepwise plan with judge gates       | [`/do-in-steps`](../../commands/do-in-steps.md) |
-| Standalone judge on an existing diff | [`/judge`](../../commands/judge.md)  |
+| Configuration reference              | [`subagent-configuration`](../../agent-src/contexts/execution/subagent-configuration.md) |
+| Do-and-judge loop                    | Inline — see [`prompts/do-and-judge.md`](prompts/do-and-judge.md) |
+| Stepwise plan with judge gates       | Inline — see [`prompts/do-in-steps.md`](prompts/do-in-steps.md) |
+| Standalone judge on an existing diff | Inline — see judge prompt in [`prompts/do-and-judge.md`](prompts/do-and-judge.md) |
 | External / networked second opinion  | [`ai-council`](../ai-council/SKILL.md) |
 | Verifying completeness               | [`verify-before-complete`](../verify-before-complete/SKILL.md) |
 | What a subagent owns vs never owns   | [`subagent-boundary`](../../../docs/contracts/subagent-boundary.md) |

package/dist/agent-src/skills/subagent-orchestration/prompts/README.md

@@ -22,6 +22,17 @@ Every prompt cites the status taxonomy in
 ends with the **return-envelope** instruction so the subagent's reply
 validates against `tests/test_subagent_status_schema.py`.
 
+## Prompt-cache discipline
+
+When dispatching sibling subagents (e.g. `do-in-parallel` with N independent
+slices), **reuse a stable system-prompt prefix** across all siblings. Keep
+task-invariant text (role declaration, constraints, status enum, return-envelope
+instruction) in the prefix; put only the slice-specific `TASK:` and
+`CONTEXT FILES:` in the variable section. This maximises host-side prompt-cache
+hits (Anthropic `cache_control: ephemeral`) across the cohort — the prefix is
+cached after the first sibling and served from cache for the rest, cutting
+input-token cost proportionally to cohort size.
+
 ## Loading
 
 `tests/test_subagent_prompt_loading.py` asserts that every mode named

package/dist/agent-src/skills/subagent-orchestration/prompts/do-in-steps.md

@@ -60,3 +60,11 @@ already mitigated, DONE. Otherwise DONE_WITH_CONCERNS.
 A step that returns BLOCKED stops the chain. The orchestrator does not
 "jump ahead" or re-order — it surfaces the BLOCKED envelope to the user
 and waits.
+
+## Dependency gate
+
+Every step after the first declares its parent (the preceding step). A
+step MUST NOT dispatch before its parent's return passed the judge —
+deterministic reference: `sliceDispatchAllowed()` in
+`src/scripts/_lib/subagent_steering.ts`, contract in
+[`subagent-steering § Ordered-slice dependency gate`](../../../contexts/execution/subagent-steering.md).

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

@@ -258,6 +258,35 @@ When reporting debug findings to the user:
 5. **Fix** — the minimal change
 6. **Regression test** — the test that catches this bug returning
 
+## Knowledge capture (`mistake_made` event)
+
+Root cause traces to a `agents/knowledge/` page followed while
+implementing (documented convention wrong, API-shape page stale,
+procedure incomplete) → append a `mistake_made` event to the
+knowledge intake — never rewrite the page mid-task (see
+[`knowledge-pages`](../../templates/contexts/knowledge-pages.md)):
+
+```bash
+./scripts-run src/scripts/emit_knowledge_event \
+    --type mistake_made \
+    --error-category "<one or two words>" \
+    --context-source "<agents/knowledge/... path, or 'null' if no page was followed>" \
+    --correction "<what the fix actually was>" \
+    --recurrence-key "<stable slug for this class of mistake>"
+```
+
+Verify the append landed: check the command's exit code (0 =
+appended), then `grep <recurrenceKey> agents/knowledge/intake/events-*.jsonl`
+finds the new line.
+
+**Live contradiction exception.** Followed page DEMONSTRABLY wrong
+right now (observed ≠ documented, not a one-off) → hybrid immediate-fix
+case instead — surface the correction, ask before continuing (see
+[`knowledge-pages`](../../templates/contexts/knowledge-pages.md) §
+Contested entries). Approved → isolated fix commit. Declined →
+`./scripts-run src/scripts/append_contested` on that page, then still
+emit the `context_stale` event above for the consolidation pass.
+
 ## Gotchas
 
 * Reading half a stack trace and jumping to a fix — the actual cause is

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

@@ -16,8 +16,8 @@ packs:
 
 
 > **Grounded corpus (Tier-1 consultation):** ground surface → threats →
-> controls before enumerating from memory — `python3
-> <skills-root>/corpus-grounding/scripts/ground.py ground --manifest
+> controls before enumerating from memory — `./scripts-run
+> <skills-root>/corpus-grounding/scripts/ground ground --manifest
 > <skills-root>/threat-modeling/data/manifest.json "<surface description>"`
 > returns surface class, ATT&CK/CWE-cited threats, required controls, and
 > negative tests, with confidence + evidence-gap. Propose grounded

package/dist/agent-src/skills/typography-system/SKILL.md

@@ -54,7 +54,7 @@ degrades gracefully: with no brand layer, only stage 1 runs.
    `fontSize`, `fontWeight`, `lineHeight`.
 5. **Verify** — confirm both chosen fonts exist on Google Fonts (check the
    `Google Fonts URL` column in the CSV); run
-   `python3 <skills-root>/design-tokens/scripts/tokens.py validate --dir src/`
+   `./scripts-run <skills-root>/design-tokens/scripts/tokens validate --dir src/`
    to confirm no hardcoded font-size or font-family values remain outside the
    token file; exit code 0 is the evidence.
 
@@ -72,7 +72,7 @@ style, not the other way around.
    evidence gap):
 
    ```bash
-   python3 <skills-root>/corpus-grounding/scripts/ground.py search \
+   ./scripts-run <skills-root>/corpus-grounding/scripts/ground search \
      --manifest <skills-root>/brand/data/manifest.json \
      "<archetype + sector>" --domain typography --json
    ```

package/dist/agent-src/skills/verify-completion-evidence/SKILL.md

@@ -2,6 +2,8 @@
 model_tier: medium
 name: verify-completion-evidence
 description: "Use when claiming 'done', suggesting a commit, push, or PR — runs the evidence gate so completion claims come from fresh output in this message, not memory or earlier runs."
+personas:
+  - production-validator
 domain: quality
 workspaces:
   - engineering

package/dist/agent-src/skills/wireframe/SKILL.md

@@ -0,0 +1,118 @@
+---
+model_tier: inherit
+name: wireframe
+description: "Explore a flow or layout with 3+ disposable lo-fi greyscale wireframes on a named axis, before any hi-fi work. Use when the user wants to sketch directions or explore structure."
+domain: product
+personas: []
+workspaces:
+  - engineering
+packs:
+  - frontend-design
+trust:
+  level: professional
+install:
+  removable: true
+execution:
+  type: manual
+---
+
+# Wireframe
+
+Produce low-fidelity wireframes or storyboards to explore a flow, layout, or
+information hierarchy before committing to hi-fi design. Wireframes are
+**disposable** — their value is the breadth of options and the decision they
+produce, not the fidelity of any one artifact.
+
+## When to use
+
+- The user wants to "explore options", "sketch something out", "see a few
+  directions" for a screen, flow, navigation pattern, or hierarchy.
+- The design problem is open enough that hi-fi work would be wasted — the
+  structure question is not yet settled.
+
+**When NOT to use:** styled, production-viable alternatives on a settled
+structure → [`design-variations`](../design-variations/SKILL.md) (hi-fi,
+branded, recommendation-bearing). A single refined implementation →
+[`fe-design`](../fe-design/SKILL.md) + stack executor.
+
+## Procedure
+
+1. **Confirm the goal.** What is explored (screen / multi-screen flow /
+   navigation / hierarchy / interaction model), the imagined user's goal,
+   constraints (mobile/desktop, non-negotiable elements), the count
+   (3 minimum, 5–6 ceiling), and the **axis of variation**. If the axis is
+   open, propose 2–3 (e.g. single-page form vs multi-step wizard vs
+   progressive disclosure) and ask which to explore.
+2. **Hold the lo-fi conventions** so the output reads as wireframe, not as
+   broken hi-fi:
+   - greyscale only — black, white, 2–3 grays; no brand color;
+   - system sans-serif — no type personality yet;
+   - labeled boxes for content areas ("headline", "image", "feature card");
+   - striped placeholders with monospace size labels for imagery (the
+     honest-placeholder pattern in
+     [`fe-design § Craft details`](../fe-design/SKILL.md));
+   - short label-style skeleton copy ("Headline goes here / one sentence on
+     the value prop") — never Lorem ipsum (per `output-discipline`), never
+     final copy.
+3. **Sketch ≥3 variations** on the named axis — layout (centered / split /
+   grid), information density, flow structure (single page / multi-step /
+   progressive disclosure), CTA placement, navigation pattern. Write each
+   variation's distinguishing structure down BEFORE sketching it — left
+   unspecified, variations converge on near-identical layouts. Order
+   by-the-book → off-distribution; at least one genuinely novel bet.
+4. **Annotate** — 2–4 numbered callouts per variation naming what is
+   interesting and its trade-off ("fastest path, but heavy first
+   impression"), placed next to the variation, not in a separate doc.
+5. **Capture the decision** after the user picks: chosen variation (or
+   hybrid), what attracted them, what they explicitly rejected, new
+   constraints surfaced. This capture is the brief for the hi-fi follow-up.
+6. **Hand off** — [`design-variations`](../design-variations/SKILL.md) for
+   styled options on the chosen structure, or
+   [`design-intelligence`](../design-intelligence/SKILL.md) +
+   [`fe-design`](../fe-design/SKILL.md) for a single hi-fi direction. In an
+   existing codebase the hi-fi step still passes `existing-ui-audit` per the
+   `ui-audit-gate` rule.
+
+## Output format
+
+1. **One file** (HTML or annotated markdown/SVG canvas) with ≥3 greyscale
+   variations side-by-side — flows as small storyboards (3–5 screens each);
+   no brand color, no styled typography, no real imagery.
+2. **Per-variation annotations** — 2–4 callouts naming the structural bet and
+   its trade-off, inline next to the variation.
+3. **Decision-capture block** (after user pick) — chosen direction,
+   attractions, explicit rejections, new constraints; framed as the hi-fi
+   brief.
+4. **No recommendation ranking** — wireframes surface trade-offs; the pick
+   belongs to the user (contrast: `design-variations` closes with a
+   recommendation).
+
+## Do NOT
+
+- Do NOT apply brand color, brand type, or real imagery — that pulls focus to
+  aesthetics before structure is settled.
+- Do NOT polish — wireframes are disposable thinking artifacts.
+- Do NOT write final copy or Lorem ipsum — label-style skeleton copy only.
+- Do NOT let variations converge — write each variation's structure down
+  before sketching.
+- Do NOT skip decision capture — an exploration round without a recorded
+  decision has to be re-litigated in the hi-fi round.
+- Do NOT embed system internals (paths, skill/tool names) in the artifact —
+  Q13 in [`design-antipatterns.md`](../../../docs/guidelines/design-antipatterns.md).
+
+## Gotcha
+
+- This is the one context where rough, hand-drawn-feeling shapes (rectangles,
+  lines, simple icons) are acceptable — everything sits at the same low
+  fidelity, so nothing reads as a failed asset (the V4/imagery antipatterns
+  apply to hi-fi, not here).
+- The wireframe file tends to get promoted into hi-fi by incremental edits —
+  don't. Start the hi-fi artifact fresh from the decision capture; the
+  wireframe's greyscale skeleton hard-codes non-decisions.
+
+## See also
+
+- [`design-variations`](../design-variations/SKILL.md) — hi-fi options on the chosen structure.
+- [`design-intelligence`](../design-intelligence/SKILL.md) — grounded direction selection for the hi-fi follow-up.
+- [`fe-design`](../fe-design/SKILL.md) — production heuristics + honest-placeholder pattern.
+- [`existing-ui-audit`](../existing-ui-audit/SKILL.md) — mandatory pre-step once hi-fi work lands in a codebase.

package/dist/agent-src/skills/wireframe/evals/triggers.json

@@ -0,0 +1,17 @@
+{
+  "skill": "wireframe",
+  "last_eval": "2026-07-06",
+  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers lo-fi structure/flow exploration. Should-not-trigger covers near-miss neighbors: design-variations (hi-fi options), fe-design (single implementation), design-review (review existing), design-intelligence (direction selection).",
+  "queries": [
+    {"q": "sketch a few rough directions for the onboarding flow", "trigger": true},
+    {"q": "wireframe the sign-up: single page vs multi-step wizard", "trigger": true},
+    {"q": "explore some layout ideas for the dashboard before we style it", "trigger": true},
+    {"q": "I'm not sure about the information hierarchy — sketch some low-fi options", "trigger": true},
+    {"q": "storyboard three ways the checkout flow could work", "trigger": true},
+    {"q": "show me 3 styled design options for the hero section", "trigger": false, "note": "hi-fi options → design-variations"},
+    {"q": "build the settings page component", "trigger": false, "note": "single implementation → fe-design / stack executor"},
+    {"q": "review this mockup for problems", "trigger": false, "note": "review of existing design → design-review"},
+    {"q": "pick a visual direction and font pairing for the app", "trigger": false, "note": "direction selection → design-intelligence / typography-system"},
+    {"q": "generate a moodboard image of the landing page", "trigger": false, "note": "image generation → image-provider-routing"}
+  ]
+}

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

@@ -43,7 +43,28 @@ made by the user directly or by the agent on request, following the
 # This file is git-ignored. Each developer has their own settings.
 # Run scripts/install to create this file, then /onboard for first-run setup.
 
-# --- Cost profile ---
+# --- Discipline profile (successor knob, opt-in until the evidence gates pass) ---
+#
+# The ONE runtime knob for the discipline-rule tier (ADR-110; council
+# verdicts 2026-07-07). Measured on claude-haiku-4-5, docs/benchmark.md
+# § Cost-factor sweep:
+#
+# off       = kernel only (~1x tokens) — for hosts with a MEASURED null
+#             lift (src/config/host-capabilities.yml).
+# essential = kernel + the lift-carrying rules (~3.3x, keeps the weak-host
+#             discipline lift; the full load's residual is not significant).
+# full      = every rule tier (~11.7x). EXPERIMENTAL opt-in only.
+# auto      = resolve per session against host-capabilities.yml
+#             (measured-null model -> off, otherwise -> essential).
+#
+# When set, this key WINS over the legacy rule_loading_tier below
+# (mapping when absent: minimal->off, balanced->essential, full->full).
+# The installer fills it per preset (minimal->off, balanced->essential,
+# full->full — behaviour-preserving); `auto` is the evidence-gated flip
+# target (roadmap Phase 4).
+discipline_profile: essential
+
+# --- Cost profile (legacy knob — superseded by discipline_profile) ---
 #
 # Master switch that controls which rule tiers load each session.
 # See `docs/customization.md` for the authoritative description and

package/dist/agent-src/templates/agents/agent-project-settings.example.yml

@@ -39,7 +39,7 @@ schema_version: 1
 # CI guard: a release bump of `package.json` must update this value
 # in lockstep — see scripts/check_template_pin_drift.py (road-to-
 # portable-runtime-and-update-check P3.3).
-agent_config_version: "7.4.0"
+agent_config_version: "8.0.0"
 
 # --- Project identity ---
 project:

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

@@ -8,7 +8,7 @@
 2. Copy the template below
 3. Replace all `{placeholders}` with actual content
 4. Remove all `<!-- comments -->` when done
-5. Run: `python3 scripts/skill_linter.py .agent-src.uncondensed/commands/{command-name}.md`
+5. Run: `./scripts-run src/scripts/skill_linter src/agent-src/commands/{command-name}.md`
 6. Sync: `task sync` (regenerates `dist/agent-src/` and `.augment/`)
 7. Generate Claude symlink: `task generate-tools` (or manually create symlink)
 
@@ -99,7 +99,7 @@ Before considering a command complete:
 - [ ] **Steps**: numbered sub-headings (`### 1.`, `### 2.`, ...)
 - [ ] **Source of truth**: works on `.agent-src.uncondensed/`, not `dist/agent-src/` or `.augment/`
 - [ ] **No auto-apply**: presents findings, asks before destructive changes
-- [ ] **Linter passes**: `python3 scripts/skill_linter.py` reports 0 FAIL
+- [ ] **Linter passes**: `./scripts-run src/scripts/skill_linter` reports 0 FAIL
 - [ ] **English only**: all content in English
 - [ ] **Synced**: `dist/agent-src/commands/` has the same file
 - [ ] **Claude symlink**: `.claude/skills/{name}/SKILL.md` → `../../../dist/agent-src/commands/{name}.md`

package/dist/agent-src/templates/contexts/knowledge-pages.md

@@ -0,0 +1,116 @@
+# Knowledge Pages — lifecycle-typed sibling directories
+
+Templates for the four typed directories added beside the existing
+anti-hallucination knowledge cards (`agents/knowledge/<source>.md`,
+[`knowledge-card.md`](knowledge-card.md)). **Existing cards stay untouched
+by this template** — sibling addition, not a migration.
+
+## The four directories
+
+| Directory | Lifecycle stage | Holds |
+|---|---|---|
+| `agents/knowledge/sessions/` | Episodic | What happened — consolidated session learnings, one file per topic or date |
+| `agents/knowledge/concepts/` | Semantic | What is true — project facts: coding standards, module structure, API shapes, domain terms |
+| `agents/knowledge/procedures/` | Procedural | How to — step-by-step knowledge on the way to becoming a skill (`skill-candidates.md` lives here) |
+| `agents/knowledge/decisions/` | Decision record | Small decisions not big enough for a full ADR |
+
+`agents/knowledge/INDEX.md` catalogs all five surfaces (cards + the four
+directories), one line per page — generated by
+`src/scripts/generate_knowledge_index.ts`. **Retrieval protocol: index
+first, `grep` keywords second, read the specific file third.** Never
+enumerate every knowledge file directly — no search infrastructure by
+design.
+
+## Storage location IS the sharing policy
+
+Personal, cross-project knowledge → the ADR-100 user-global store
+(`~/.event4u/agent-config/knowledge/`, via `knowledge_global_cli.ts`) —
+never these project-local directories. Team knowledge → here, in the
+consumer repo, so the whole team benefits via git. Promotion to global
+requires cross-project evidence via the existing manual promotion path —
+never automatic.
+
+**Enforced at commit time.** A pre-commit gate
+(`src/scripts/check_knowledge_sharing.ts`) refuses a commit staging a
+`visibility: private` page under `agents/knowledge/` (belongs in the
+global store) or a gitignored `agents/memory/intake/` file staged by
+accident. Warns — never blocks — on 5+ new knowledge files in one
+commit, for a second look.
+
+## Entry micro-schema — `date + what + why`
+
+Every entry (especially in `sessions/`) states, at minimum:
+
+```markdown
+- 2026-07-05: <what happened / was learned> — <why it matters>
+```
+
+Keep entries short; longer explanation goes in the page body below the
+entry list, not stuffed into one line.
+
+## Page frontmatter — optional, warn-linted only (v1)
+
+None of these fields are mandatory in v1 (schema-as-contract deferred
+until real team usage data exists). When present, warn-linted for shape
+only:
+
+```yaml
+---
+type: concept            # concept | procedure | session | decision
+scope: project            # user | project | global
+visibility: team           # private | project | team
+review_after: "YYYY-MM-DD" # optional scheduled re-check date
+contested: []              # append-only array — see "Contested entries" below
+---
+```
+
+## Contested entries — never silently resolved
+
+A live contradiction between documented and observed reality gets an
+**append-only** `contested:` entry, never a silent rewrite:
+
+```yaml
+contested:
+  - timestamp: "2026-07-15T14:23:11Z"
+    trigger: context_stale
+    evidence: "profile.test.ts:45 expected {success, payload}"
+    session: "<session id or chat-history pointer>"
+```
+
+Resolution is always human — via the `team-knowledge:consolidate` gate,
+or an isolated, this-turn-approved fix commit. ≥2 unresolved `contested`
+entries on one page → flagged by the knowledge lint for consolidation
+attention.
+
+## Page size budget
+
+Keep pages ≤ 200 lines. Split by sub-topic before that limit — a
+too-broad page defeats index-first scanning just as much as too many
+tiny pages do.
+
+## What this substrate is — honest framing
+
+A **governed second-brain substrate**: working-memory continuity across
+compactions + sessions (hot-context cache, dispatcher-wide, 7 platforms),
+deterministic where safe (dedup, recurrence, index regen, fold rollups,
+scale tripwires), human-gated where meaning is at stake (consolidate
+gate, promotion, contested flow). It is **not** self-organizing
+intelligence — governed files; the learning loop is human-reviewed by
+design.
+
+**External viewers — read-only, on purpose.** Any Markdown tool (incl.
+Obsidian) can VIEW `agents/knowledge/` — but edits outside
+`/team-knowledge consolidate` silently desync `INDEX.md` + recurrence
+counters at next session start; exactly the failure the gate prevents.
+No `.obsidian/` config shipped, deliberately (council claude-sonnet-4-5
++ gpt-4o, 2026-07-07 — converged 2/2 reject: out-of-gate edits are an
+unguardable dual-write; an editable vault re-creates the
+knowledge-as-truth model the 2026-07-05 verdict rejected).
+
+## See also
+
+- [`knowledge-card.md`](knowledge-card.md) — the existing anti-hallucination
+  card template (unchanged, unaffected by this addition).
+- [`context-document`](../../../skills/context-document/SKILL.md) —
+  structured, on-demand codebase-area documentation (different, manual
+  surface; complements rather than duplicates these pages).

package/dist/agent-src/templates/hooks/pre-commit-frontmatter

@@ -9,7 +9,7 @@
 #
 # To run manually:
 #   ./agent-config hooks:install-frontmatter
-#   python3 scripts/lint_artefact_frontmatter.py
+#   ./scripts-run src/scripts/lint_artefact_frontmatter
 #
 # To uninstall:
 #   rm .git/hooks/pre-commit