Plan
codewhale-hq/Codewhale
Turn a sufficiently understood task into an ordered implementation plan with dependencies and verification.
Build every remaining planned feature serially in explicit Continuous Mode, with one local branch, verification cycle, commit, archive, and local merge per feature.
$ npx skills add aiblueprinthq/ai-blueprint --skill continuous -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install aiblueprinthq/ai-blueprint continuous --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/aiblueprinthq/ai-blueprint.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/continuous .claude/skills/continuous && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "continuous" agent skill from https://github.com/aiblueprinthq/ai-blueprint/tree/main/.agents/skills/continuous into .claude/skills/continuous/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/aiblueprinthq/ai-blueprint/tree/main/.agents/skills/continuousType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add aiblueprinthq/ai-blueprint --skill continuous -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install aiblueprinthq/ai-blueprint continuous --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiblueprinthq/ai-blueprint.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/continuous .agents/skills/continuous && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "continuous" agent skill from https://github.com/aiblueprinthq/ai-blueprint/tree/main/.agents/skills/continuous into .agents/skills/continuous/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aiblueprinthq/ai-blueprint --skill continuous -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install aiblueprinthq/ai-blueprint continuous --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiblueprinthq/ai-blueprint.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/continuous .cursor/skills/continuous && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "continuous" agent skill from https://github.com/aiblueprinthq/ai-blueprint/tree/main/.agents/skills/continuous into .cursor/skills/continuous/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/aiblueprinthq/ai-blueprint.git --path .agents/skills/continuous--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add aiblueprinthq/ai-blueprint --skill continuous -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install aiblueprinthq/ai-blueprint continuous --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiblueprinthq/ai-blueprint.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/continuous .gemini/skills/continuous && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "continuous" agent skill from https://github.com/aiblueprinthq/ai-blueprint/tree/main/.agents/skills/continuous into .gemini/skills/continuous/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install aiblueprinthq/ai-blueprint continuousInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add aiblueprinthq/ai-blueprint --skill continuous -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/aiblueprinthq/ai-blueprint.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/continuous .github/skills/continuous && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "continuous" agent skill from https://github.com/aiblueprinthq/ai-blueprint/tree/main/.agents/skills/continuous into .github/skills/continuous/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aiblueprinthq/ai-blueprint --skill continuous -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install aiblueprinthq/ai-blueprint continuous --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiblueprinthq/ai-blueprint.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/continuous .opencode/skills/continuous && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "continuous" agent skill from https://github.com/aiblueprinthq/ai-blueprint/tree/main/.agents/skills/continuous into .opencode/skills/continuous/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
continuousBuild every remaining planned feature serially in explicit Continuous Mode, with one local branch, verification cycle, commit, archive, and local merge per feature.
Continuous is an agent skill from aiblueprinthq/ai-blueprint. Build every remaining planned feature serially in explicit Continuous Mode, with one local branch, verification cycle, commit, archive, and local merge per feature. Stop on decisions or blockers and never push or deploy. Use only for /continuous, $continuous, or a direct Continuous Mode request.
Its SKILL.md is about 4.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: A file-backed, spec-driven AI coding workflow framework for building real software while staying in control. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 96222b7. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Continuous loads about 4.7k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 2,559 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from aiblueprinthq/ai-blueprint at commit 96222b7, republished under its MIT licence (© aiblueprinthq). 2,559 words, ~4,671 tokens.
.claude/skills/continuous/SKILL.md (or your agent's skills folder).Context reuse: Reuse any required file already loaded in project instructions or the current session. Read it again only if absent, changed, or exact current bytes or line references are needed.
First action: Before project inspection, preflight, or any other tool call,
publish running to blueprint/.state/run.json using the dashboard activity
contract in AGENTS.md.
Where this sits in the workflow:
/status -> [continuous] -> final review packet
(ready) (feature loop, (local main only,
local history) never pushed)Continuous Mode is an explicit opt-in loop for completing planned features without pausing at normal review prompts. It preserves the same file-backed state, small steps, verification, findings ledger, branches, archives, and one clean main commit per feature that a careful human workflow would produce.
A direct Continuous request authorizes these local actions for this run:
It does not authorize push, deploy, publish, send, remote changes, destructive actions, database resets, irreversible migrations, finding acceptance, failed check waivers, or product decisions. It always stops before those actions.
Before selecting an item or requiring a live active spec, inspect pending
completion using the installed Complete skill and
../complete/reference/completion-recovery.md. Use its read-only candidate screen
first: settled clean default-branch history needs no historical transient objects
for a new run. An actual completion candidate or an explicit request to resume
interrupted completion requires full recovery proof, using this run's scoped Git
authority and
qualityGates.continuous. Do not repeat archival or a work commit/merge. Missing,
conflicting, or unprovable recovery evidence stops before next-feature work. An
active feature with no completion candidate resumes implementation normally; its
ordinary resume does not require an archive or completion proof.
With no argument after pending completion has been reconciled:
blueprint/context/current-feature.md.blueprint/build-plan.md.continuous.maxFeatures completed features have been counted.resume explicitly resumes the active feature or its pending completion.
A feature number or name may set
the starting item only when no different work item is active. After that item,
continue with the next unchecked leaf items in normal build-plan order.
Continuous Mode handles planned features only. If the active work is a fix or rollback, stop and point to its normal reviewed workflow. Never overwrite active work to make the requested target fit.
Read:
AGENTS.mdblueprint/config.jsonblueprint/project-plan.mdblueprint/build-plan.mdblueprint/context/project-overview.mdblueprint/context/current-feature.mdblueprint/context/findings.mdblueprint/context/coding-standards.mdblueprint/context/ai-interaction.mdA missing config means built-in defaults. If it exists but is invalid, stop and
point to /doctor.
Start only when the state is safe:
/overview behavior and include that change
with the first feature. Stop when refreshing it needs a product decision.open or fixed.Verify command, when declared, are usable.Do not fetch, pull, install dependencies, start an unauthorized server, alter remote settings, or clean unrelated work during preflight. A known-behind default branch is a stop, not permission to pull.
Record the starting default-branch commit. This bounds the optional final integration audit and the final report.
The initial blueprint/.state/run.json record required by AGENTS.md must
already show command continuous and status running before preflight begins.
After preflight passes, enrich it with boundary local-only, the current
feature, and completed-feature progress against the smaller of the remaining
queue or configured limit. Update it when
a feature starts, after every passing build step, after each quality gate, and
after each local main commit. On a stop, set status blocked with
/continuous resume when resuming is safe. At the end of the queue or limit,
set status completed and retain the final progress. Activity reporting must
never weaken or block the workflow itself.
Repeat this section serially. Never have two feature branches or specs active at once.
When resuming, keep the active spec and continue from its first unchecked build step.
For a new item, apply the /feature behavior to the selected build-plan leaf,
write blueprint/context/current-feature.md, and self-review the spec before
coding. Correct missing unhappy paths, oversized steps, undefined contracts,
scope drift, vague done-whens, missing design references, and missing testing
plans.
Do not invent an unanswered product, data, architecture, auth, billing, or visual
decision. Stop with the exact decision needed.
Follow the proportional-engineering contract in AGENTS.md throughout this run.
Use the exact **Branch:** frozen in the spec, including its **Build attempt:**
suffix when applicable; do not derive a new branch or attempt from the title.
Validate it against git.featureBranchPrefix and Feature's history rules, then
create it from the current local default branch. When resuming, require the
existing branch and active spec to agree; keep Complete's legacy attempt handling
for older specs rather than renaming a reviewed branch.
If switching would strand unrelated work or the default branch changed in a way that makes the active branch unsafe to integrate, stop. Never stash, reset, or discard work automatically.
Build the spec in order, one small diff at a time. Continuous Mode does not pause
for workflow.stepReview; its explicit invocation replaces those review
prompts with self-review plus the final packet.
For each step:
Verify command when present. Otherwise run the
documented build and existing relevant tests.verification.logicTests and verification.uiEvidence.workflow.checkpointCommits is enabled, create a conventional local
checkpoint commit containing that passing step and its checked spec state.
When disabled, keep the work uncommitted until feature completion.Never collapse an oversized step into an unreadable diff. Split the step in the spec and continue. A dependency install, new service, destructive operation, or decision outside the approved plans is a hard stop.
Use qualityGates.continuous, not the regular or Autopilot gates:
manual skips automatic audit; when-sensitive runs
/audit current for authentication, authorization, payments, secrets,
personal or user data, migrations, destructive operations, external side
effects, security boundaries, or unusually broad changes; always audits
every feature.manual skips automatic independent review;
when-sensitive requires a fresh reviewer for the same sensitive categories
as Audit; always requires a fresh reviewer for every feature. A passing
independent receipt satisfies the Audit gate for that feature.manual skips automatic /check; when-behavioral runs it
when a done-when needs observed runtime behavior such as a click, request, CLI
command, download, background job, or multi-screen flow; always checks
every feature.qualityGates.continuous.tryGuide): use /check guide.
manual skips automatic generation; when-user-facing
generates a guide for UI, navigation, copy, public API or CLI, output, or
another workflow a person directly uses; always generates one for every
feature.Run required gates in this order: check, review, then try guide. Use independent
review instead of a builder-session audit when both are selected. manual means
the capability remains available later but is not automatic during this run.
A try guide is instructions for human review, never proof it was performed.
When a gate cannot run, stop instead of recording a pass. Existing P0/P1 ledger blockers always apply even when audit is manual.
Validate audit findings before editing. Repair confirmed P0 and P1 findings only
when the repair stays within feature scope, needs no user decision, and does not
remove or change shipped behavior. Use continuous.maxRepairAttempts as the
maximum attempts for the same failing check or finding; 0 disables automatic
repair.
After a repair, rerun affected verification and acceptance evidence, then
re-audit the repaired area. Move fixed to closed only when the audit
confirms the defect is gone and no worse issue was introduced.
Report P2 and P3 findings. Fix only small defects directly caused by the current
feature and clearly required by project standards. Never mark a finding
accepted for the user or suppress a failing check.
Any P0 or P1 left open or fixed stops the loop before completion.
When independent review is selected, ensure application code is in a clean
immutable checkpoint. First rerun final verification and the selected Check
gate and set the spec status to verified. Include the exact spec when tracked;
an intentionally ignored spec uses Audit's local Spec snapshot contract
without changing visibility. This review checkpoint is covered by Continuous
Mode's scoped local lifecycle authority even when step checkpoint commits are
disabled. Then follow
/audit independent current. With review.independentExecution: "automatic",
spawn and wait for the isolated reviewer and validate its normal receipt before
continuing. With manual, or when automatic capability cannot prove isolation,
identity, model, completion, or access to the same local spec/snapshot, set
activity to ready and stop with the manual handoff. Continuous Mode never
performs its own independent review. On /continuous resume, continue only with
a current passed receipt. For
changes-requested, repair within the configured attempt limit, obtain a new
checkpoint, and review the whole new target again.
A local-spec-only revision may reuse the same approved product HEAD after normal
spec and verification gates, with a new snapshot/request and full fresh review.
Do not create an empty commit for ignored spec changes.
The request records Requested execution; the receipt records Actual execution. Require the execution and reviewer-context pairing defined by the
project-local review contract before continuing the feature loop.
A pending request without Requested execution is legacy manual-only. Never add
execution fields or run a subagent against it.
Apply the /complete safety, logging, and archive behavior without asking the
normal commit and local-merge prompts, because the explicit Continuous request
already authorized those local actions.
For the finished feature:
**Status:** is verified. When an independent
receipt exists, do not rewrite the reviewed spec before archival.landing as local-merge even when project configuration selects
pull-request landing for the regular workflow.
Fully prepare the archive with the exact verified spec, resolved findings,
original passing receipt, and any generated ## Manual try guide section.Never merge a partial or failing feature. Never push the default branch.
Count the feature toward continuous.maxFeatures only after its local main
commit succeeds. On resume, reconcile the unique proven archive/default-commit
pairs already completed in this run before incrementing; cleanup or a repeated
resume never counts the same completion twice. If the run boundary or count
cannot be recovered for an explicit resume, stop for clarification instead of
resetting the count and exceeding the requested limit. A new invocation starting
from a clean default branch records that current tip as its new run boundary;
already-completed work at or before it does not count toward the new run or
require reconstruction of an older run's count.
After the loop reaches its feature limit or the end of the build plan, run this
step only when continuous.finalIntegrationAudit is true.
Audit the combined default-branch diff from the recorded starting commit through
the current HEAD, focusing on cross-feature contracts, integration seams,
security boundaries, regression risk, and missing tests. Record findings in the
ledger.
For a confirmed P0 or P1 introduced by this run, automatic repair may use one dedicated configured fix branch and the same repair-attempt limit only when no product decision or scope expansion is required. Spec, verify, archive, locally squash-merge, and delete that fix branch like normal Blueprint fix work. Re-audit the repair before closing the finding.
Otherwise stop with the finding open. Do not hide it, widen into general hardening, or present the run as fully ready.
A successful stop occurs when:
continuous.maxFeatures successful features were completed.A blocked stop occurs immediately for:
On a mid-feature stop, preserve the feature branch, checked steps, commits, and
working tree exactly as they stand. Do not merge or delete it. A later
/continuous resume picks up from that state.
On any stop, report:
workflow.stepReview does not pause Continuous Mode.workflow.checkpointCommits controls step checkpoints, not the required
feature-level local history.Follow blueprint/context/ai-interaction.md. Keep progress updates concise and
feature-oriented. The final packet must be readable without the intermediate
updates.
© aiblueprinthq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/continuous of aiblueprinthq/ai-blueprint.
Open the folder on GitHubat commit 96222b7
Continuous next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Continuous this skillaiblueprinthq/ai-blueprint | 463 | — | ~4.7k | Automated safety check: Pass | MIT | |
| Plancodewhale-hq/Codewhale | 41k | — | ~213 | Automated safety check: Pass | MIT | |
| Planningn8n-io/n8n | 207k | — | ~2.5k | Automated safety check: Pass | Custom licence | |
| Planasgeirtj/system_prompts_leaks | 69k | — | ~5.1k | Automated safety check: Pass | CC0-1.0 | |
| Review Planpenpot/penpot | 61k | — | ~841 | Automated safety check: Pass | MPL-2.0 | |
| Make A Planpenpot/penpot | 61k | — | ~1.6k | Automated safety check: Pass | MPL-2.0 |
codewhale-hq/Codewhale
Turn a sufficiently understood task into an ordered implementation plan with dependencies and verification.
n8n-io/n8n
ONLY for coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema/migration across tasks, or the user explicitly asked to review a plan first.
asgeirtj/system_prompts_leaks
On an explicit planning request, always call readskill for this skill before answering.
penpot/penpot
Plan review flow — evaluate an implementation plan before it is executed, delegating the review to a subagent that follows the plan-review-criteria skill.
penpot/penpot
Planning flow — research the subject of this session, produce an implementation plan with the planner skill, resolve open questions with the user in plain language, and save the final plan to…
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
aiblueprinthq/ai-blueprint
Adopt Blueprint into an existing brownfield codebase by surveying shipped behavior and generating plans, standards, commands, adapter choices, and visibility setup.
aiblueprinthq/ai-blueprint
Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook.
aiblueprinthq/ai-blueprint
Run a Blueprint health and context check covering setup, adapters, commands, visibility, plans, overview freshness, configuration, dashboard state, and workflow drift.
aiblueprinthq/ai-blueprint
Turn the next, named, or numbered build-plan feature into a buildable current-feature.md spec with small steps and done-when criteria.
aiblueprinthq/ai-blueprint
Onboard a fresh or early scaffold after Blueprint is overlaid by tuning commands, standards, adapters, visibility, and context loading.
aiblueprinthq/ai-blueprint
Validate and normalize project-plan.md and build-plan.md, then generate the durable project-overview.md used by agents.
Build every remaining planned feature serially in explicit Continuous Mode, with one local branch, verification cycle, commit, archive, and local merge per feature. Continuous is an agent skill from aiblueprinthq/ai-blueprint. Build every remaining planned feature serially in explicit Continuous Mode, with one local branch, verification cycle, commit, archive, and local merge per feature.
Run `npx skills add aiblueprinthq/ai-blueprint --skill continuous -a claude-code`. Or copy the skill folder (.agents/skills/continuous in aiblueprinthq/ai-blueprint) into .claude/skills/continuous in your project. Claude Code loads it when a task matches its description.
Run `npx skills add aiblueprinthq/ai-blueprint --skill continuous -a codex`. Or copy the skill folder (.agents/skills/continuous in aiblueprinthq/ai-blueprint) into .agents/skills/continuous in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiblueprinthq/ai-blueprint --skill continuous -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/continuous, .gemini/skills/continuous, .github/skills/continuous and .opencode/skills/continuous in your project.
SKILL.md names no scripts, command-line tools or credentials: Continuous is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Continuous is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.7k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Continuous: Plan (codewhale-hq/Codewhale, 41k stars), Planning (n8n-io/n8n, 207k stars), Plan (asgeirtj/system_prompts_leaks, 69k stars) and Review Plan (penpot/penpot, 61k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
aiblueprinthq (a GitHub organization) maintains it in aiblueprinthq/ai-blueprint, which has 463 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.
Source: aiblueprinthq/ai-blueprint on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.