DeepWorkPlan — Dailybot Addon
Connect the target repo to the developer's Dailybot team so that DWP work —
the full plan lifecycle — surfaces to humans as standup-style progress
reports. This is an opt-in addon; it is never required for a repo to
be AI-first, and it never blocks the actual work.
The rule that overrides everything: this addon DEFERS, it does not reinvent
The official Dailybot agent skill (currently 3.10.3) already owns
install, consent, auth, context detection, the writing style, and the
non-blocking guarantee. It exposes 14 coordinated capabilities (report,
ask, messages, email, chat, conversations, health, check-ins, kudos, teams,
forms, workflows, report channels, per-repo API keys) — but this addon's job is narrow: (1)
offer to install the Dailybot skill/CLI through their own consent flows,
and (2) wire the optional report sub-skill into DWP execute/plan
lifecycle. It MUST NOT duplicate, bypass, or weaken any Dailybot consent or
auth flow — it points at them. (Normative source: SPEC.md.)
Positioning guardrail (read before anything)
The core DeepWorkPlan methodology has ZERO Dailybot dependency. It is
vendor-neutral, MIT, and agent-agnostic. A repo with zero addons — including
this one — is fully conformant. This addon adds team visibility for developers
who already use Dailybot; declining it leaves a fully AI-first repo. Never
present Dailybot as a precondition for DWP, and never auto-install it for
everyone.
Read these first (all relative inside the skill)
SPEC.md — the normative (RFC-2119) contract: what is installed
(all opt-in), how auth is deferred, how the report step is wired, the
never-block rule, and the vendor-neutral guardrail.
templates/INTEGRATION.md — reasoning guidance
(NOT copy-paste): detect-if-already-installed, how to wire the optional
report step into DWP execution, and the consent / never-block rules.
../README.md — the addon mechanism (opt-in, reconcile-don't-clobber, contract).
When this runs
- From
onboard Phase 7b — after the core AI-first scaffolding, onboard
offers this addon alongside devcontainer; if accepted it reads this SKILL and
runs the flow below.
- Directly —
/deepworkplan-addon-dailybot on an already-onboarded repo to
add the Dailybot integration.
Trust boundary (write scope)
allowed-tools includes write-capable Edit, Write, and Bash. Everything
this addon may write is enumerated below; anything not listed does not happen.
Writes (only after the developer accepts the relevant step):
- The Dailybot skill install itself (tag-pinned, consent-gated — Step 1) into
the agent's skills directory and
skills-lock.json.
- A short reporting note in the repo's DWP execution docs (
AGENTS.md section
and/or docs/AI_AGENT_COLLAB.md), merged — never over an existing section.
- Optionally, a credential-free repo identity (
.dailybot/profile.json or the
example template) and the harness hook config (Step 3b, shown verbatim
before writing, merged into existing config files).
It MUST NOT: prompt for or store credentials (auth belongs to the Dailybot
skill's shared/auth.md consent flow), write a key field into any committed
file, install anything unpinned or unprompted, block any DWP flow when Dailybot
is absent/unreachable, or imply the core methodology needs Dailybot.
The flow
Step 0 — Consent + recommend-only-if-relevant
- Confirm relevance. Offer this addon only when it makes sense: the
developer or team already uses Dailybot, or explicitly asks for team
reporting. In trust/auto mode you MAY recommend it only on that signal —
do not auto-install for everyone. If the developer declines, stop cleanly;
the repo stays baseline-conformant.
- Detect existing setup (reconcile-don't-clobber). Before installing
anything, check what is already present (see
templates/INTEGRATION.md):
- Dailybot skill already installed at the agent's skills dir
(
~/.<agent>/skills/dailybot/)?
dailybot CLI already on PATH (command -v dailybot)?
- A repo identity already committed (
.dailybot/profile.json or
.dailybot_example/profile.json)?
- An existing report step already wired into the repo's DWP
execute notes?
- Harness hook configs already carrying
dailybot hook entries
(.claude/settings.json, .agents/settings.json, .cursor/hooks.json, …)?
If a piece already exists, do not redo it — record it and only fill gaps.
Step 1 — Offer the Dailybot skill + CLI install (OPT-IN, defer consent)
Present the install paths and let the developer choose; never run an installer
without their explicit acceptance — and where the Dailybot skill's own consent
flow applies, defer to it rather than prompting yourself.
Dailybot agent skill (the recommended path — it brings the consent/auth
flow and the full 14-capability pack; currently 3.10.3):
npx --yes skills add DailybotHQ/agent-skill@v3.10.3 --skill dailybot -y
(cross-agent, recommended — pinned to a published tag so the exact
content is reproducible; both --yes and -y are required in non-TTY
contexts), or
- OpenClaw native:
openclaw skills install dailybot (registry-managed,
records its own pin), or
npx --yes skills update dailybot -y when already installed.
Always pin and verify. Installs are developer-consented, pinned to a
tag, and recorded (source + content hash) in the repo's skills-lock.json
by the skills CLI. Do not offer unpinned clone-and-run variants of a
skill repo — executing whatever a remote default branch currently holds is
an unverifiable fetch-and-execute dependency (the shape Snyk W012 / Socket
flag), with no version, no checksum, and no rollback path.
Dailybot CLI (the underlying bridge, from
DailybotHQ/cli; minimum >= 3.7.0
for the whole skill pack; the skill installs it on first use via its own
SHA-256-verified consent flow — you generally do not install it separately,
but these are the supported paths if asked):
- Package-manager paths (preferred — pinned + checksum-verified by the
package registry):
pip install 'dailybot-cli>=3.7.0' (Python 3.10+), or
brew install dailybothq/tap/dailybot (macOS).
- Vendor's verified installer flow (macOS / Linux / Windows) — the
Dailybot skill's
shared/auth.md
documents a three-step download → verify checksum → execute flow with the
SHA-256 sidecar (and optional cosign signature). Follow it exactly; do not
substitute a one-line remote-installer pipe.
Do not reimplement the verified installer, and never pipe a remote
installer to a shell. If the Dailybot skill is being installed, let its
shared/auth.md flow drive the CLI install + checksum verification. Only
surface the raw package-manager commands when the developer explicitly wants
the CLI without the skill.
Step 2 — Auth: DEFER to the Dailybot skill's own consent flow
Do not prompt for email, OTP, or API keys yourself, and do not store any
credential. Authentication is owned by the Dailybot skill's
shared/auth.md:
dailybot login (email OTP) or DAILYBOT_API_KEY / dailybot config key=....
Point the developer at that flow; the skill handles login, profile, and the
HTTP fallback. If they decline auth, skip reporting — never block.
Step 3 — Wire the plan lifecycle events into DWP execution
This is the integration value. Reasoning guidance is in
templates/INTEGRATION.md — adapt it to the repo; do not copy verbatim.
- Add a short, clearly-optional note to the repo's DWP execution docs (e.g. the
generated
AGENTS.md reporting section and/or docs/AI_AGENT_COLLAB.md)
describing the four lifecycle events (SPEC §5.1) that fire when the
Dailybot skill is installed:
- Kickoff (SHOULD, regular) — when a plan is materialized and approved,
report what is being built and why ("Starting: …").
- Significant task (MAY, regular) — a feature/bug fix/major refactor
completes; intermediate setup tasks are never reported.
- Blocked (SHOULD, regular with
blockers) — the plan halts on a stop
condition and state.json.blocked is populated (typical of unattended
runs): the team sees what is stuck and what it needs in the standup
instead of discovering a silent overnight halt.
- Completion (SHOULD, the only milestone) — via the dailybot
report sub-skill (dailybot agent update ... --milestone --json-data ...), describing what was built, never "completed a plan."
- Where the plan carries the machine-readable state layer
(
../../spec/PLAN_STATE.md), derive the --json-data payload from
state.json: completed from completed tasks (phrased as outcomes),
in_progress from the current task, blockers from state.json.blocked.
- Every event MUST be best-effort and conditional: it fires only if the
Dailybot skill/CLI is present and authenticated, and it MUST NOT block
create or execute if Dailybot is absent, unauthenticated, or unreachable —
warn once and continue (see SPEC §Never-block).
- Optionally commit a repo identity so every contributor/agent signs reports the
same way:
.dailybot/profile.json (or the gitignore-friendly
.dailybot_example/profile.json template) — never with a key field
(credentials in that file are a hard error per the CLI). The same file MAY
carry the committed report policy the hooks honor:
"report": {"min_interval_minutes": 30, "nudge": true} ("nudge": false
is the soft opt-out that keeps manual reporting available). For
research/docs-heavy repos, "mode": "continuous" nudges non-commit work
sooner — see the Dailybot skill's report/hooks.md § Per-repo controls.
Step 3b — Offer deterministic hook enforcement (OPT-IN, defer to the Dailybot skill)
The lifecycle wiring above is prompt-layer: it relies on the model remembering
to report. With dailybot-cli >= 3.7.0 (included in the current 3.10.3
skill pack), the Dailybot skill ships deterministic hook enforcement
(report/hooks.md): harness lifecycle hooks (dailybot hook session-start | activity | post-commit | stop | dismiss) backed by a local per-repo report
ledger, so the harness itself detects unreported work and reminds the agent at
end of turn — even in long unattended sessions where prompt instructions decay.
This is the strongest version of the visibility this addon exists for.
- Offer it (consent-gated, show the exact config before writing) when
dailybot --version reports >= 3.7.0: commit the repo-level hook config —
Claude Code .claude/settings.json (or .agents/settings.json where
.claude → .agents), Cursor .cursor/hooks.json (or via .cursor → .agents),
other harnesses per the
table in the Dailybot skill's report/hooks.md — so every contributor and
fresh container gets autonomous reporting on clone; the only per-person step
left is dailybot login.
- Defer the mechanics. The hook templates, output formats, anti-noise
gates, and uninstall path are owned by the Dailybot skill's
report/hooks.md
and report/triggers.md
— point at them; do not duplicate or hand-roll the JSON beyond merging it in.
Merge into existing config files, never overwrite (§Reconcile).
- The two layers compose — no double-reporting. A successful
dailybot agent update (any lifecycle event from Step 3) resets the hook
ledger, so the hooks stay silent after a lifecycle report; they act as the
deterministic backstop when a lifecycle event was missed. A hook reminder
mid-plan is answered with either a lifecycle-appropriate report or
dailybot hook dismiss — never ignored, never blocking.
- Degrade gracefully. CLI below 3.7.0 → skip this step (the Step 3 wiring
stands alone) and mention
dailybot upgrade once. The dailybot hook
commands are local-only and always exit 0, so installing them cannot violate
the never-block rule; they also respect .dailybot/disabled.
Step 4 — Validate (SPEC §Validation)
Run the validation checklist and report: whether the skill/CLI is present (skill
>= 3.10.3 recommended, CLI >= 3.7.0), that auth was deferred (not
reinvented), that the report step is wired as optional + non-blocking,
whether hook enforcement was offered/installed, the identity source if any, and
any deferred items.
If nothing could be installed here (sandbox/CI), say why — do not silently skip,
and do not fail the onboarding.
Failure-mode guardrails
- Never required, never blocking. If declined — or if Dailybot is missing,
unauthenticated, or unreachable — stop/continue cleanly. The repo stays
baseline-conformant and
execute is never blocked by reporting.
- Defer auth, never store secrets. No email/OTP/API-key prompting here; no
credential written to any file. Point at the Dailybot skill's
shared/auth.md.
- Verified install only. Never recommend piping a remote installer to a
shell (any variant of "fetch from the network and execute in one line").
Point at the Dailybot skill's checksum-verified
shared/auth.md flow, or at
a package manager (pip, brew) that pins versions and verifies integrity.
- Reconcile, don't clobber. An existing skill/CLI/identity/report step is
preserved; only fill gaps. Any destructive change needs explicit approval.
- Vendor-neutral. Never imply DWP needs Dailybot. This addon is purely
additive team visibility for teams already on Dailybot.
1---2name: deepworkplan-addon-dailybot-43description: Optional DeepWorkPlan addon that connects an AI-first repo to the developer's Dailybot team — installing (with consent) the Dailybot agent skill (DailybotHQ/agent-skill, currently 3.10.3) and/or the Dailybot CLI (DailybotHQ/cli, >= 3.7.0), wiring the plan lifecycle into best-effort agent updates - kickoff when a plan starts, significant task completions, a blocked report when an unattended run halts, and a milestone on plan completion - with payloads derived from the plan's state layer, and optionally committing the Dailybot skill's deterministic hook enforcement (dailybot hook lifecycle hooks) so the agent harness itself reminds agents about unreported work. Opt-in, never required, never blocks the work, reconciles existing setups instead of clobbering them, and defers all auth to the Dailybot skill's own consent flow. Use when the developer or team already uses Dailybot and wants DWP progress visible to humans.4version: "2.17.0"5documentation_url: https://deepworkplan.com6user-invocable: true7allowed-tools: Bash, Read, Grep, Glob, Edit, Write8metadata:9 source: https://skillmd.com/skills/dailybothq/deepworkplan-addon-dailybot-410 openclaw:11 emoji: 📡12 homepage: https://deepworkplan.com13 requires:14 anyBins:15 - git16---1718# DeepWorkPlan — Dailybot Addon1920Connect the target repo to the developer's **Dailybot team** so that DWP work —21the full plan lifecycle — surfaces to humans as standup-style **progress22reports**. This is an **opt-in addon**; it is **never** required for a repo to23be AI-first, and it **never blocks** the actual work.2425> ## The rule that overrides everything: this addon DEFERS, it does not reinvent26>27> The official **Dailybot agent skill** (currently **3.10.3**) already owns28> install, consent, auth, context detection, the writing style, and the29> non-blocking guarantee. It exposes **14 coordinated capabilities** (report,30> ask, messages, email, chat, conversations, health, check-ins, kudos, teams,31> forms, workflows, report channels, per-repo API keys) — but **this addon's job is narrow**: (1)32> **offer** to install the Dailybot skill/CLI through their own consent flows,33> and (2) **wire** the optional **report** sub-skill into DWP `execute`/plan34> lifecycle. It MUST NOT duplicate, bypass, or weaken any Dailybot consent or35> auth flow — it points at them. (Normative source: [`SPEC.md`](SPEC.md).)3637## Positioning guardrail (read before anything)3839The **core DeepWorkPlan methodology has ZERO Dailybot dependency.** It is40vendor-neutral, MIT, and agent-agnostic. A repo with **zero addons** — including41this one — is fully conformant. This addon adds *team visibility* for developers42who already use Dailybot; declining it leaves a fully AI-first repo. Never43present Dailybot as a precondition for DWP, and never auto-install it for44everyone.4546## Read these first (all relative inside the skill)4748- [`SPEC.md`](SPEC.md) — the normative (RFC-2119) contract: what is installed49 (all opt-in), how auth is deferred, how the report step is wired, the50 never-block rule, and the vendor-neutral guardrail.51- [`templates/INTEGRATION.md`](templates/INTEGRATION.md) — reasoning guidance52 (NOT copy-paste): detect-if-already-installed, how to wire the optional53 report step into DWP execution, and the consent / never-block rules.54- `../README.md` — the addon mechanism (opt-in, reconcile-don't-clobber, contract).5556## When this runs5758- From **`onboard` Phase 7b** — after the core AI-first scaffolding, `onboard`59 offers this addon alongside devcontainer; if accepted it reads this SKILL and60 runs the flow below.61- **Directly** — `/deepworkplan-addon-dailybot` on an already-onboarded repo to62 add the Dailybot integration.6364## Trust boundary (write scope)6566`allowed-tools` includes write-capable `Edit`, `Write`, and `Bash`. Everything67this addon may write is enumerated below; anything not listed does not happen.6869**Writes (only after the developer accepts the relevant step):**7071- The Dailybot skill install itself (tag-pinned, consent-gated — Step 1) into72 the agent's skills directory and `skills-lock.json`.73- A short reporting note in the repo's DWP execution docs (`AGENTS.md` section74 and/or `docs/AI_AGENT_COLLAB.md`), merged — never over an existing section.75- Optionally, a credential-free repo identity (`.dailybot/profile.json` or the76 `example` template) and the harness hook config (Step 3b, shown verbatim77 before writing, merged into existing config files).7879**It MUST NOT:** prompt for or store credentials (auth belongs to the Dailybot80skill's `shared/auth.md` consent flow), write a `key` field into any committed81file, install anything unpinned or unprompted, block any DWP flow when Dailybot82is absent/unreachable, or imply the core methodology needs Dailybot.8384## The flow8586### Step 0 — Consent + recommend-only-if-relevant871. **Confirm relevance.** Offer this addon only when it makes sense: the88 developer or team **already uses Dailybot**, or explicitly asks for team89 reporting. In trust/auto mode you MAY recommend it **only** on that signal —90 do **not** auto-install for everyone. If the developer declines, stop cleanly;91 the repo stays baseline-conformant.922. **Detect existing setup (reconcile-don't-clobber).** Before installing93 anything, check what is already present (see `templates/INTEGRATION.md`):94 - Dailybot skill already installed at the agent's skills dir95 (`~/.<agent>/skills/dailybot/`)?96 - `dailybot` CLI already on PATH (`command -v dailybot`)?97 - A repo identity already committed (`.dailybot/profile.json` or98 `.dailybot_example/profile.json`)?99 - An existing report step already wired into the repo's DWP `execute` notes?100 - Harness hook configs already carrying `dailybot hook` entries101 (`.claude/settings.json`, `.agents/settings.json`, `.cursor/hooks.json`, …)?102 If a piece already exists, **do not redo it** — record it and only fill gaps.103104### Step 1 — Offer the Dailybot skill + CLI install (OPT-IN, defer consent)105Present the install paths and let the developer choose; **never run an installer106without their explicit acceptance** — and where the Dailybot skill's own consent107flow applies, defer to it rather than prompting yourself.108109- **Dailybot agent skill** (the recommended path — it brings the consent/auth110 flow and the full 14-capability pack; currently **3.10.3**):111 - `npx --yes skills add DailybotHQ/agent-skill@v3.10.3 --skill dailybot -y`112 (cross-agent, recommended — **pinned to a published tag** so the exact113 content is reproducible; both `--yes` and `-y` are required in non-TTY114 contexts), or115 - OpenClaw native: `openclaw skills install dailybot` (registry-managed,116 records its own pin), or117 - `npx --yes skills update dailybot -y` when already installed.118119 > **Always pin and verify.** Installs are developer-consented, pinned to a120 > tag, and recorded (source + content hash) in the repo's `skills-lock.json`121 > by the `skills` CLI. Do not offer unpinned clone-and-run variants of a122 > skill repo — executing whatever a remote default branch currently holds is123 > an unverifiable fetch-and-execute dependency (the shape Snyk W012 / Socket124 > flag), with no version, no checksum, and no rollback path.125- **Dailybot CLI** (the underlying bridge, from126 [`DailybotHQ/cli`](https://github.com/DailybotHQ/cli); minimum **`>= 3.7.0`**127 for the whole skill pack; the skill installs it on first use via its own128 SHA-256-verified consent flow — you generally do **not** install it separately,129 but these are the supported paths if asked):130 - **Package-manager paths (preferred — pinned + checksum-verified by the131 package registry)**:132 - `pip install 'dailybot-cli>=3.7.0'` (Python 3.10+), or133 - `brew install dailybothq/tap/dailybot` (macOS).134 - **Vendor's verified installer flow** (macOS / Linux / Windows) — the135 Dailybot skill's136 [`shared/auth.md`](https://github.com/DailybotHQ/agent-skill/blob/main/skills/dailybot/shared/auth.md)137 documents a three-step `download → verify checksum → execute` flow with the138 SHA-256 sidecar (and optional cosign signature). Follow it exactly; do not139 substitute a one-line remote-installer pipe.140141> **Do not reimplement the verified installer, and never pipe a remote142> installer to a shell.** If the Dailybot skill is being installed, let *its*143> `shared/auth.md` flow drive the CLI install + checksum verification. Only144> surface the raw package-manager commands when the developer explicitly wants145> the CLI without the skill.146147### Step 2 — Auth: DEFER to the Dailybot skill's own consent flow148Do **not** prompt for email, OTP, or API keys yourself, and do **not** store any149credential. Authentication is owned by the Dailybot skill's150[`shared/auth.md`](https://github.com/DailybotHQ/agent-skill/blob/main/skills/dailybot/shared/auth.md):151`dailybot login` (email OTP) or `DAILYBOT_API_KEY` / `dailybot config key=...`.152Point the developer at that flow; the skill handles login, profile, and the153HTTP fallback. If they decline auth, skip reporting — never block.154155### Step 3 — Wire the plan lifecycle events into DWP execution156This is the integration value. Reasoning guidance is in157`templates/INTEGRATION.md` — adapt it to the repo; do not copy verbatim.158159- Add a short, clearly-optional note to the repo's DWP execution docs (e.g. the160 generated `AGENTS.md` reporting section and/or `docs/AI_AGENT_COLLAB.md`)161 describing the **four lifecycle events** (SPEC §5.1) that fire when the162 Dailybot skill is installed:163 1. **Kickoff** (SHOULD, regular) — when a plan is materialized and approved,164 report *what is being built and why* ("Starting: …").165 2. **Significant task** (MAY, regular) — a feature/bug fix/major refactor166 completes; intermediate setup tasks are never reported.167 3. **Blocked** (SHOULD, regular with `blockers`) — the plan halts on a stop168 condition and `state.json.blocked` is populated (typical of unattended169 runs): the team sees *what is stuck and what it needs* in the standup170 instead of discovering a silent overnight halt.171 4. **Completion** (SHOULD, the only **milestone**) — via the dailybot172 `report` sub-skill (`dailybot agent update ... --milestone --json-data173 ...`), describing **what was built**, never "completed a plan."174- Where the plan carries the machine-readable state layer175 (`../../spec/PLAN_STATE.md`), derive the `--json-data` payload from176 `state.json`: `completed` from completed tasks (phrased as outcomes),177 `in_progress` from the current task, `blockers` from `state.json.blocked`.178- Every event MUST be **best-effort and conditional**: it fires only if the179 Dailybot skill/CLI is present and authenticated, and it **MUST NOT block**180 `create` or `execute` if Dailybot is absent, unauthenticated, or unreachable —181 warn once and continue (see SPEC §Never-block).182- Optionally commit a repo identity so every contributor/agent signs reports the183 same way: `.dailybot/profile.json` (or the gitignore-friendly184 `.dailybot_example/profile.json` template) — **never** with a `key` field185 (credentials in that file are a hard error per the CLI). The same file MAY186 carry the committed report policy the hooks honor:187 `"report": {"min_interval_minutes": 30, "nudge": true}` (`"nudge": false`188 is the soft opt-out that keeps manual reporting available). For189 research/docs-heavy repos, `"mode": "continuous"` nudges non-commit work190 sooner — see the Dailybot skill's `report/hooks.md` § Per-repo controls.191192### Step 3b — Offer deterministic hook enforcement (OPT-IN, defer to the Dailybot skill)193The lifecycle wiring above is prompt-layer: it relies on the model remembering194to report. With `dailybot-cli` **>= 3.7.0** (included in the current **3.10.3**195skill pack), the Dailybot skill ships **deterministic hook enforcement**196(`report/hooks.md`): harness lifecycle hooks (`dailybot hook session-start |197activity | post-commit | stop | dismiss`) backed by a local per-repo report198ledger, so the harness itself detects unreported work and reminds the agent at199end of turn — even in long unattended sessions where prompt instructions decay.200This is the strongest version of the visibility this addon exists for.201202- **Offer it** (consent-gated, show the exact config before writing) when203 `dailybot --version` reports **>= 3.7.0**: commit the repo-level hook config —204 Claude Code `.claude/settings.json` (or `.agents/settings.json` where205 `.claude → .agents`), Cursor `.cursor/hooks.json` (or via `.cursor → .agents`),206 other harnesses per the207 table in the Dailybot skill's `report/hooks.md` — so every contributor and208 fresh container gets autonomous reporting on clone; the only per-person step209 left is `dailybot login`.210- **Defer the mechanics.** The hook templates, output formats, anti-noise211 gates, and uninstall path are owned by the Dailybot skill's212 [`report/hooks.md`](https://github.com/DailybotHQ/agent-skill/blob/main/skills/dailybot/report/hooks.md)213 and [`report/triggers.md`](https://github.com/DailybotHQ/agent-skill/blob/main/skills/dailybot/report/triggers.md)214 — point at them; do not duplicate or hand-roll the JSON beyond merging it in.215 Merge into existing config files, never overwrite (§Reconcile).216- **The two layers compose — no double-reporting.** A successful217 `dailybot agent update` (any lifecycle event from Step 3) resets the hook218 ledger, so the hooks stay silent after a lifecycle report; they act as the219 deterministic backstop when a lifecycle event was missed. A hook reminder220 mid-plan is answered with either a lifecycle-appropriate report or221 `dailybot hook dismiss` — never ignored, never blocking.222- **Degrade gracefully.** CLI below 3.7.0 → skip this step (the Step 3 wiring223 stands alone) and mention `dailybot upgrade` once. The `dailybot hook`224 commands are local-only and always exit 0, so installing them cannot violate225 the never-block rule; they also respect `.dailybot/disabled`.226227### Step 4 — Validate (SPEC §Validation)228Run the validation checklist and report: whether the skill/CLI is present (skill229**>= 3.10.3** recommended, CLI **>= 3.7.0**), that auth was deferred (not230reinvented), that the report step is wired as **optional + non-blocking**,231whether hook enforcement was offered/installed, the identity source if any, and232any deferred items.233If nothing could be installed here (sandbox/CI), say why — do not silently skip,234and do not fail the onboarding.235236## Failure-mode guardrails237238- **Never required, never blocking.** If declined — or if Dailybot is missing,239 unauthenticated, or unreachable — stop/continue cleanly. The repo stays240 baseline-conformant and `execute` is never blocked by reporting.241- **Defer auth, never store secrets.** No email/OTP/API-key prompting here; no242 credential written to any file. Point at the Dailybot skill's `shared/auth.md`.243- **Verified install only.** Never recommend piping a remote installer to a244 shell (any variant of "fetch from the network and execute in one line").245 Point at the Dailybot skill's checksum-verified `shared/auth.md` flow, or at246 a package manager (`pip`, `brew`) that pins versions and verifies integrity.247- **Reconcile, don't clobber.** An existing skill/CLI/identity/report step is248 preserved; only fill gaps. Any destructive change needs explicit approval.249- **Vendor-neutral.** Never imply DWP needs Dailybot. This addon is purely250 additive team visibility for teams already on Dailybot.