@event4u/agent-config 9.8.0 → 9.9.0

package/docs/end-to-end-walkthroughs.md

@@ -1,165 +0,0 @@
-# End-to-end walkthroughs
-
-Four cycle-by-cycle traces of the engine commands — backend ticket,
-free-form prompt, UI track, and a blocked path. Each walkthrough cites
-a checked-in **golden transcript** under [`tests/golden/baseline/`](../tests/golden/baseline/);
-the transcripts are regenerated by `node node_modules/.bin/tsx tests/golden/capture.ts` and
-diffed in CI, so the cycle counts and directive names below stay
-in sync with the engine's actual behavior.
-
-> Behavior demos (autonomy, commit policy, hard floor, verification)
-> live in [`showcase.md`](showcase.md). This file is the cycle-trace
-> companion: input → directives → outcome.
-
----
-
-## 1. Backend ticket → ship — `/implement-ticket`
-
-**Anchor:** [`tests/golden/baseline/GT-1/`](../tests/golden/baseline/GT-1/) ·
-[`tickets/gt-1-happy.json`](../tests/golden/sandbox/tickets/gt-1-happy.json)
-
-**Input** — a ticket payload with three concrete acceptance criteria:
-
-```text
-GT-1-MULT — Add multiply(a, b) to the toy calculator
-AC: signature multiply(a: int, b: int) -> int returning the product;
-    edge cases multiply(0, n)=0, multiply(-2, 3)=-6;
-    pytest test_multiply_returns_product in tests/test_calculator.py.
-```
-
-**Trace** — five cycles, exit code `0` on the last:
-
-| Cycle | Directive | What the agent does |
-|---|---|---|
-| c1 | `create-plan` | Builds the three-step plan (impl, test, run) |
-| c2 | `apply-plan` | Edits `src/calculator.py` and `tests/test_calculator.py` |
-| c3 | `run-tests` | `pytest` — `4 passed` (targeted scope) |
-| c4 | `review-changes` | Four judges (bug, security, test-coverage, code-quality) — `success` |
-| c5 | _(none)_ | Engine emits the delivery report, exits `0` |
-
-**Outcome** — verified delivery report at
-[`GT-1/delivery-report.md`](../tests/golden/baseline/GT-1/delivery-report.md):
-plan, changes, test verdict, judge findings, suggested next command
-(`/commit`).
-
-**Anchored in:** [`commands/implement-ticket.md`](../dist/agent-src/commands/implement-ticket.md)
-(eight-step contract) · [`work_engine/dispatcher.py`](../dist/agent-src/templates/scripts/work_engine/dispatcher.py)
-(`STEP_ORDER`).
-
----
-
-## 2. Free-form prompt → ship — `/work`
-
-**Anchor:** [`tests/golden/baseline/GT-P1/`](../tests/golden/baseline/GT-P1/) ·
-[`prompts/gt-p1-high.txt`](../tests/golden/sandbox/prompts/gt-p1-high.txt)
-
-**Input** — one line, no AC, no ticket:
-
-```text
-Add modulo(a, b) to src/calculator.py — return a % b for ints
-```
-
-**Trace** — six cycles. The extra cycle vs. GT-1 is the
-`refine-prompt` step that reconstructs the prompt into AC + assumptions
-+ confidence band before any plan runs:
-
-| Cycle | Directive | Effect |
-|---|---|---|
-| c1 | `refine-prompt` | High confidence — AC reconstructed, no halt |
-| c2 | `create-plan` | Two-step plan |
-| c3 | `apply-plan` | Edits `src/calculator.py` |
-| c4 | `run-tests` | targeted pass |
-| c5 | `review-changes` | judges green |
-| c6 | _(none)_ | delivery report, exit `0` |
-
-**Outcome** — `success`. The same dispatcher and judges as GT-1; only
-the input envelope (`input.kind="prompt"` vs `"ticket"`) differs.
-
-**Anchored in:** [`commands/work.md`](../dist/agent-src/commands/work.md) ·
-[`skills/refine-prompt/SKILL.md`](../dist/agent-src/skills/refine-prompt/SKILL.md)
-· [`docs/contracts/adr-prompt-driven-execution.md`](contracts/adr-prompt-driven-execution.md).
-
----
-
-## 3. UI improvement → review-loop ship — `/work` (UI track)
-
-**Anchor:** [`tests/golden/baseline/GT-U2/`](../tests/golden/baseline/GT-U2/) ·
-[`diffs/gt-u2-improve-diff.diff`](../tests/golden/sandbox/diffs/gt-u2-improve-diff.diff)
-
-**Input** — a Blade diff that adds a `<label>` and a heading change to
-`resources/views/contact.blade.php`. The input shape (a diff, not a
-prompt) routes the engine onto the **UI track** instead of the
-generic implement loop.
-
-**Trace** — six cycles, none of them `create-plan` / `apply-plan` /
-`run-tests`. The UI track has its own directive set:
-
-| Cycle | Directive | Effect |
-|---|---|---|
-| c1 | `existing-ui-audit` | Inventory existing components / tokens before any new design |
-| c2 | `ui-design-brief` | Brief for the proposed change |
-| c3 | _(none — `_no_directive`)_ | Engine threads forward to the apply step |
-| c4 | `ui-apply-plain` | Apply the diff |
-| c5 | `ui-design-review-plain` | Design review judge |
-| c6 | _(none)_ | delivery report, exit `0` |
-
-**Outcome** — `success`. The audit-first ordering is enforced by the
-[`ui-audit-gate`](../dist/agent-src/rules/ui-audit-gate.md) rule: any
-non-trivial UI change without `state.ui_audit` halts before design.
-
-**Anchored in:** [`docs/ui-track-mental-model.md`](ui-track-mental-model.md) ·
-[`rules/ui-audit-gate.md`](../dist/agent-src/rules/ui-audit-gate.md) ·
-[`skills/existing-ui-audit/SKILL.md`](../dist/agent-src/skills/existing-ui-audit/SKILL.md).
-
----
-
-## 4. Blocked on ambiguity — `/implement-ticket` halts
-
-**Anchor:** [`tests/golden/baseline/GT-2/`](../tests/golden/baseline/GT-2/) ·
-[`tickets/gt-2-ambiguity.json`](../tests/golden/sandbox/tickets/gt-2-ambiguity.json)
-
-**Input** — a ticket whose AC list contains a vague entry:
-
-```text
-GT-2-DIV — divide(a, b)
-AC: ... vague acceptance criteria at position(s) 2 ...
-```
-
-**Trace** — one cycle, exit code `1`:
-
-| Cycle | Directive | Effect |
-|---|---|---|
-| c1 | _(none)_ | Engine refuses to plan; surfaces refine prompt |
-
-**Halt surface** — the engine does not write a plan, does not edit any
-file, and emits a numbered-options block (verbatim from
-[`GT-2/halt-markers.json`](../tests/golden/baseline/GT-2/halt-markers.json)):
-
-```text
-> Ticket GT-2-DIV is missing: vague acceptance criteria at position(s) 2.
-> 1. Run `/refine-ticket GT-2-DIV` and re-invoke `/implement-ticket`
-> 2. Provide the missing details in chat — I'll merge them into the ticket
-> 3. Abandon this ticket — too vague to implement
-```
-
-**Outcome** — `halt_unhandled`; the run is recorded as **blocked** in
-the outcome-aware telemetry (`outcomes: ["blocked"]`, see
-[P2 #9](../agents/roadmaps/road-to-1-15-followups.md#phase-9--outcome-aware-telemetry-p2-9)).
-No work is committed, no auto-guess is taken.
-
-**Anchored in:** [`rules/ask-when-uncertain.md`](../dist/agent-src/rules/ask-when-uncertain.md)
-· [`rules/non-destructive-by-default.md`](../dist/agent-src/rules/non-destructive-by-default.md)
-· [`skills/refine-ticket/SKILL.md`](../dist/agent-src/skills/refine-ticket/SKILL.md).
-
----
-
-## Reproducing these locally
-
-```bash
-node node_modules/.bin/tsx tests/golden/capture.ts --scenarios GT-1 GT-P1 GT-U2 GT-2
-```
-
-Each scenario writes a fresh `transcript.json`, `delivery-report.md`,
-and `halt-markers.json` under `tests/golden/baseline/<id>/`. CI diffs
-the regenerated output against the committed baseline; drift fails the
-build via the `roadmap-progress-check` and `golden-replay` tasks.

package/docs/enforcement-by-host.md

@@ -1,51 +0,0 @@
-# Enforcement by host — how governance is applied, per tool
-
-Governance in this package is applied two ways, and which one a host gets
-depends on what that host exposes. We say so plainly rather than imply
-"deterministic everywhere".
-
-- **Compile-time (every host).** Rules and Iron Laws are compiled into each
-  host's native instruction format at projection time (`.cursorrules`,
-  `.windsurfrules`, `copilot-instructions.md`, `GEMINI.md`, Claude/Augment
-  native rule dirs). This is the universal layer — it works on all projection
-  targets. It is **model-cooperative**: the agent is instructed, strongly, but
-  the host does not hard-block the call.
-- **Runtime hooks (hook-capable hosts only).** On hosts that expose a tool
-  lifecycle (`PreToolUse` / `PostToolUse` / `Stop`), a small set of guards can
-  **deterministically block** a call (e.g. `block_no_verify`). This is a
-  superset on top of the compile-time layer, not a replacement.
-
-| Host | Compile-time rules | Runtime hook enforcement |
-|---|---|---|
-| Claude Code (plugin) | ✅ | ✅ native hooks |
-| Cline (MCP) | ✅ | ✅ where the MCP host exposes lifecycle |
-| Cursor | ✅ `.cursorrules` | — static only |
-| Windsurf | ✅ `.windsurfrules` | — static only |
-| Copilot | ✅ `copilot-instructions.md` | — static only |
-| Gemini | ✅ `GEMINI.md` | — static only |
-| Augment | ✅ native rules | — no public hook API |
-
-**Why we lead with compile-time, not hooks.** Runtime hooks reach only a
-minority of supported hosts. Building the governance story on hooks would make
-it a two-tier experience — strong on Claude, absent on Cursor/Windsurf/Copilot.
-So the universal lever is the compile-time layer; runtime hooks are an opt-in
-**bonus** on the hosts that can run them, never the floor.
-
-The ADR-124 code-graph nudge is a case in point: on hook-capable hosts the
-default-off `code-graph` PreToolUse hook surfaces "query the graph first" once
-per session; on instruction-file hosts the same intent rides the always-loaded
-[`external-code-graph-interop`](../src/rules/external-code-graph-interop.md)
-rule and the [`code-intelligence`](../src/skills/code-intelligence/SKILL.md)
-skill — the capability degrades gracefully, it does not disappear.
-
-**Where MCP fits.** MCP is a *transport* surface, not a third enforcement layer.
-On a host that runs MCP servers, MCP is one path by which a tool lifecycle (and
-therefore the runtime-hook column above) can become available — but MCP presence
-does not by itself add enforcement. Which hosts consume which surface is tracked
-authoritatively, per artifact type, in
-[`capability-matrix.md`](capability-matrix.md) (derived from the projection
-dispatcher, drift-checked in CI) — we do not restate per-host surface facts here,
-to avoid drift between two hand-maintained tables.
-
-See also the artifact-projection view: [`capability-matrix.md`](capability-matrix.md)
-(its `hooks` row already shows hooks are native to the Claude plugin only).

package/docs/examples/agent-user.example.md

@@ -1,22 +0,0 @@
----
-version: 1
-identity:
-  name: "Mathias"
-  nickname: "Matze"
-language: "de"
-role:
-  - founder
-  - engineer
-style:
-  pace: "pragmatic"
-voice_sample: |
-  Mach das einfach. Wenn unklar, frag im Council. Tokenverbrauch ist ok,
-  aber stell mir keine Fragen — entscheide oder frag die AIs.
-last_updated: "2026-05-15"
----
-
-# Notes
-
-Pragmatic shipper. Prefers terse replies, real diffs, and named
-trade-offs over hedged options. Council-first for anything that looks
-like a contract decision.

package/docs/experiences/agency.md

@@ -1,49 +0,0 @@
-# 🏛 The `agency` experience
-
-> Set `profile.id: agency` (wizard, or `agent-config use --profile=agency`).
-> **Preset default: `strict`.**
-
-## Who it's for
-
-The multi-client delivery shop — refine a fuzzy client ask into an estimated,
-AC-tight ticket; turn a phase into a roadmap; ship per client without losing
-decision provenance.
-
-## First three tasks
-
-1. **Refine the client ask** — `/refine-ticket` rewrites the ticket and surfaces the top-5 risks.
-2. **Size and split** — `estimate-ticket` sizes and breaks the work down.
-3. **Anchor the trade-off** — `decision-record` writes an ADR before code starts.
-
-## First commands
-
-`/work` · `/implement-ticket` · `/refine-ticket` · `/feature` · `/roadmap`
-
-## Packs that activate
-
-`engineering-base` + `gtm-marketing` + `product-basic` + `ops-people`
-(+ `meta`, always on) — the broadest profile, for a shop that does delivery,
-positioning, and account work.
-
-## Flows that apply
-
-All four — [discovery → implementation → review → delivery](../flows.md) — run
-per client engagement. The `strict` preset keeps the gates tight across accounts.
-
-## What is NOT loaded
-
-No `finance-advanced`, no `ai-video`, no `founder-strategy`. Delivery-shop
-surface, not a CFO or studio one.
-
-## Example
-
-> *"Client wants 'a better dashboard' by next sprint."* → `/refine-ticket`
-> rewrites it AC-tight with top-5 risks; `estimate-ticket` splits it;
-> `decision-record` captures the charting-library trade-off before code.
-
-## See also
-
-[Profile (deep)](../profiles.md#profile-agency) ·
-[Role guide](../getting-started-by-role.md#consultant-advisory-freelance-fractional) ·
-[Flows](../flows.md) ·
-key skills: `refine-ticket` · `estimate-ticket` · `decision-record` · `doc-coauthoring` · `perf-feedback-craft`.

package/docs/experiences/content_creator.md

@@ -1,49 +0,0 @@
-# ✍️ The `content_creator` experience
-
-> Set `profile.id: content_creator` (wizard, or
-> `agent-config use --profile=content_creator`). **Preset default: `balanced`.**
-
-## Who it's for
-
-Writers, ghostwriters, marketers — draft in someone else's voice, plan a quarter
-of content, ship a launch, render a cinematic AI video.
-
-> **Domain-soundness status (honest).** These skills are forged on TS/PHP; their embedded domain heuristics are **not independently validated**. Until a skill passes a sourced `evals/domain-truth.json` fixture (`./scripts-run src/scripts/domain_soundness_status`), treat its domain correctness as a general-purpose scaffold, not proven practice. The safety floor bounds *liability*, not *correctness*.
-
-## First three tasks
-
-1. **Write in a voice** — `/ghostwriter` against a public-figure voice profile, or `/post-as` for your own (`.agent-user.md`).
-2. **Lock the brand frame** — `voice-and-tone-design` + `messaging-architecture` before any copy ships.
-3. **Render a video** — `/video:from-script` drives script → character-locked image → motion+audio → render → stitch (`AIV_DRYRUN=true` cost-safety default).
-
-## First commands
-
-`/work` · `/post-as` · `/ghostwriter` · `/optimize-prompt` · `/video:from-script` · `/video:storyboard` · `/video:scene` · `/video:stitch`
-
-## Packs that activate
-
-`gtm-marketing` + `ai-video` (+ `meta`, always on).
-
-## Flows that apply
-
-[Discovery](../flows.md) drives content planning (editorial calendar, messaging).
-The engineering flows (implementation / review / delivery) do not apply — the work
-is pack-skill-driven (voice, messaging, video), not a code journey.
-
-## What is NOT loaded
-
-No `engineering-base` (no `/implement-ticket`, `/review-changes` code judges),
-no `finance-*`, no `founder-strategy`. The surface is content + video.
-
-## Example
-
-> *"Draft a launch post in our founder's voice."* → `/post-as:me` writes against
-> `.agent-user.md`; `voice-and-tone-design` + `messaging-architecture` hold the
-> brand frame; `release-comms` shapes the announcement.
-
-## See also
-
-[Profile (deep)](../profiles.md#profile-content_creator) ·
-[Role guide](../getting-started-by-role.md#creator-writer-marketer-indie-content-shop) ·
-[Flows](../flows.md) ·
-key skills: `voice-and-tone-design` · `messaging-architecture` · `editorial-calendar` · `release-comms` · `character-consistency`.

package/docs/experiences/developer.md

@@ -1,49 +0,0 @@
-# 👩‍💻 The `developer` experience
-
-> Set `profile.id: developer` (the wizard's first question, or
-> `agent-config use --profile=developer`). **Preset default: `balanced`.**
-
-## Who it's for
-
-The IC engineer — implement a ticket end-to-end, fix CI red, self-review before
-the PR. Stack-aware across Laravel · Symfony · Next.js · React · Node.
-
-## First three tasks
-
-1. **Implement a ticket** — `/implement-ticket` refines it, plans, edits, tests, verifies.
-2. **Fix a red build** — `/fix:ci` reads the failure and drives it green.
-3. **Self-review the diff** — `/review-changes` dispatches five judges (bug, security, tests, quality, architecture).
-
-## First commands
-
-`/work` · `/implement-ticket` · `/review-changes` · `/fix` · `/commit`
-
-## Packs that activate
-
-`engineering-base` (+ `meta`, always on). Language/framework packs (laravel, php,
-react, …) overlay per session from the project's detected stack.
-
-## Flows that apply
-
-All four — this is the home profile for the developer journey:
-**[discovery](../flows.md) → implementation → review → delivery**.
-
-## What is NOT loaded
-
-No `gtm-marketing`, `ai-video`, `finance-*`, or `founder-strategy` packs — no
-ghostwriter, video, DCF, or fundraising surfaces. The profile stays focused on
-shipping code.
-
-## Example
-
-> *"Implement PROJ-412."* → `/implement-ticket` refines acceptance criteria,
-> plans the change, edits with `minimal-safe-diff`, runs the suite via
-> `test-driven-development`, and stops on fresh green evidence
-> (`verify-completion-evidence`) — then `/review-changes` before you open the PR.
-
-## See also
-
-[Profile (deep)](../profiles.md#profile-developer) ·
-[Role guide](../getting-started-by-role.md#developer-the-original-audience) ·
-[Flows](../flows.md) ·
-key skills: `developer-like-execution` · `verify-completion-evidence` · `minimal-safe-diff` · `systematic-debugging` · `test-driven-development`.

package/docs/experiences/finance.md

@@ -1,50 +0,0 @@
-# 💼 The `finance` experience
-
-> Set `profile.id: finance` (wizard, or `agent-config use --profile=finance`).
-> **Preset default: `strict`.**
-
-## Who it's for
-
-The CFO / fractional finance / FP&A lead — build a DCF, stress-test the plan,
-frame the runway call. Every output carries the finance safety floor (no final
-invest/raise verdict; assumptions + sensitivity + confidence band).
-
-> **Domain-soundness status (honest).** These skills are forged on TS/PHP; their embedded domain heuristics are **not independently validated**. Until a skill passes a sourced `evals/domain-truth.json` fixture (`./scripts-run src/scripts/domain_soundness_status`), treat its domain correctness as a general-purpose scaffold, not proven practice. The safety floor bounds *liability*, not *correctness*.
-
-## First three tasks
-
-1. **Value it** — `dcf-modeling` walks WACC / terminal-value / 5-year-hold reasoning.
-2. **Cut the scenarios** — `scenario-modeling` produces base / upside / downside.
-3. **Frame the runway** — `runway-cognition` shapes the fundraise-vs-cut-vs-grow decision.
-
-## First commands
-
-`/work` · `/council` · `/challenge-me`
-
-## Packs that activate
-
-`finance-basic` + `finance-advanced` (+ `meta`, always on).
-
-## Flows that apply
-
-[Discovery](../flows.md)-style modeling and framing dominate. The engineering
-flows (implementation / review / delivery) do not apply — finance work is
-pack-skill-driven and gated by the `finance-safety-floor` rule.
-
-## What is NOT loaded
-
-No `engineering-base`, no `ai-video`, no `gtm-marketing`, no `founder-strategy`.
-Pure finance surface.
-
-## Example
-
-> *"What's our runway if growth halves?"* → `runway-cognition` frames the shape;
-> `scenario-modeling` cuts base/downside; output ends with the mandatory
-> *"Not investment advice — figures are model output, sensitivity stated"* footer.
-
-## See also
-
-[Profile (deep)](../profiles.md#profile-finance) ·
-[Role guide](../getting-started-by-role.md#finance--ops-cfo-controller-ops-lead-founder-finance) ·
-[Flows](../flows.md) ·
-key skills: `dcf-modeling` · `forecasting` · `scenario-modeling` · `unit-economics-modeling` · `runway-cognition`.

package/docs/experiences/founder.md

@@ -1,49 +0,0 @@
-# 🚀 The `founder` experience
-
-> Set `profile.id: founder` (wizard, or `agent-config use --profile=founder`).
-> **Preset default: `fast`.**
-
-## Who it's for
-
-The solo / early-stage founder — sharpen a fuzzy idea, rank what to build, write
-the why-now slide, get a neutral second opinion.
-
-> **Domain-soundness status (honest).** These skills are forged on TS/PHP; their embedded domain heuristics are **not independently validated**. Until a skill passes a sourced `evals/domain-truth.json` fixture (`./scripts-run src/scripts/domain_soundness_status`), treat its domain correctness as a general-purpose scaffold, not proven practice. The safety floor bounds *liability*, not *correctness*.
-
-## First three tasks
-
-1. **Sharpen the idea** — `/challenge-me` runs a grill-style interview that turns a vague plan into a copyable pitch.
-2. **Rank the backlog** — `rice-prioritization` orders what to build next.
-3. **Get a second opinion** — `/council` polls external AIs for a neutral read on a plan or decision.
-
-## First commands
-
-`/work` · `/feature` · `/challenge-me` · `/council`
-
-## Packs that activate
-
-`founder-strategy` + `product-basic` + `finance-basic` (+ `meta`, always on).
-
-## Flows that apply
-
-[Discovery](../flows.md) is the home flow — idea → plan → estimate → refine.
-Implementation applies when the founder builds; review/delivery are light until
-there is a team. Strategy/finance work is pack-skill-driven.
-
-## What is NOT loaded
-
-No `engineering-base` by default (added per session if the founder codes), no
-`ai-video`, no `gtm-marketing`, no `finance-advanced`. Lean, fast-preset surface.
-
-## Example
-
-> *"Should we build the team-seats feature next?"* → `/challenge-me` interviews
-> to 95% confidence and emits a copyable pitch; `rice-prioritization` ranks it
-> against the backlog; `vision-articulation` frames the why-now.
-
-## See also
-
-[Profile (deep)](../profiles.md#profile-founder) ·
-[Role guide](../getting-started-by-role.md#founder-early-stage-operator-wearing-every-hat) ·
-[Flows](../flows.md) ·
-key skills: `rice-prioritization` · `vision-articulation` · `fundraising-narrative` · `runway-cognition`.

package/docs/experiences/ops.md

@@ -1,49 +0,0 @@
-# 🛡 The `ops` experience
-
-> Set `profile.id: ops` (wizard, or `agent-config use --profile=ops`).
-> **Preset default: `strict`.**
-
-## Who it's for
-
-RevOps, support, SRE-adjacent — threat-model a change before it ships, command
-the incident when it breaks, build the dashboard that catches it next time.
-
-> **Domain-soundness status (honest).** These skills are forged on TS/PHP; their embedded domain heuristics are **not independently validated**. Until a skill passes a sourced `evals/domain-truth.json` fixture (`./scripts-run src/scripts/domain_soundness_status`), treat its domain correctness as a general-purpose scaffold, not proven practice. The safety floor bounds *liability*, not *correctness*.
-
-## First three tasks
-
-1. **Threat-model first** — `/threat-model` enumerates abuse cases and trust boundaries before the first line of code.
-2. **Command the incident** — `incident-commander` frames severity and the post-mortem.
-3. **Build the signal** — `dashboard-design` chooses the right RED / USE / Golden-Signal panel.
-
-## First commands
-
-`/work` · `/threat-model` · `/review-changes` · `/fix`
-
-## Packs that activate
-
-`engineering-base` + `founder-strategy` (+ `meta`, always on).
-
-## Flows that apply
-
-[Implementation](../flows.md), **review** (threat-model is the front door), and
-**delivery** apply; discovery is lighter. The `strict` preset keeps the
-security/quality gates tight.
-
-## What is NOT loaded
-
-No `ai-video`, no `gtm-marketing`, no `finance-*`. Engineering + reliability
-surface, not a studio or CFO one.
-
-## Example
-
-> *"We're adding a public webhook endpoint."* → `/threat-model` enumerates abuse
-> cases + trust boundaries first (per `security-sensitive-stop`); `/review-changes`
-> dispatches the security judge; `logging-monitoring` keeps PII out of the stream.
-
-## See also
-
-[Profile (deep)](../profiles.md#profile-ops) ·
-[Role guide](../getting-started-by-role.md#finance--ops-cfo-controller-ops-lead-founder-finance) ·
-[Flows](../flows.md) ·
-key skills: `incident-commander` · `dashboard-design` · `logging-monitoring` · `threat-modeling` · `launch-readiness`.

package/docs/featured-commands.md

@@ -1,27 +0,0 @@
-# Featured Commands
-
-A curated subset of the 124 active commands. Full set lives in
-[`dist/agent-src/commands/`](../dist/agent-src/commands/) — see also
-[`docs/catalog.md`](catalog.md) for the complete index.
-
-## For developers
-
-| Command | What it does |
-|---|---|
-| [`/implement-ticket`](../dist/agent-src/commands/implement-ticket.md) | Drive a Jira / Linear ticket end-to-end through refine → plan → implement → test → verify |
-| [`/work`](../dist/agent-src/commands/work.md) | Same end-to-end loop for a free-form prompt — confidence-band gated |
-| [`/fix ci`](../dist/agent-src/commands/fix.md) | Fetch CI failures from GitHub Actions and fix them |
-| [`/review-changes`](../dist/agent-src/commands/review/changes.md) | Self-review local changes before creating a PR (five judges) |
-| [`/pr:create`](../dist/agent-src/commands/pr/create.md) | Create a GitHub PR with Jira-linked description |
-
-## For everyone
-
-| Command | What it does |
-|---|---|
-| [`/research`](../dist/agent-src/commands/research.md) | Survey / benchmark / competitive scan scaffolder — picks objects, defines fields |
-| [`po-discovery`](../dist/agent-src/skills/po-discovery/SKILL.md) | Shape a fuzzy product ask into a refined backlog item — problem framing, AC tightening |
-| [`/ghostwriter:write`](../dist/agent-src/commands/ghostwriter/write.md) | Draft in a public-figure voice profile (mandatory disclosure footer) |
-| [`/challenge-me`](../dist/agent-src/commands/challenge-me.md) | Interactive grill-style interview that sharpens a fuzzy plan into a copyable pitch |
-| [`/fundraising-narrative`](../dist/agent-src/skills/fundraising-narrative/SKILL.md) | Shape a capital-raise pitch — why-now / why-us / why-this framing |
-
-→ [Browse all 124 active commands](../dist/agent-src/commands/)