ai-blueprint: Skill for Claude Code

.agents/skills/continuous/SKILL.md

continuous is a skill for Claude Code, Codex from aiblueprinthq/ai-blueprint. It costs 59 tokens per session (3,798 once invoked), scanned A, original, MIT.

An opt-in workflow that completes every remaining feature in a build plan one at a time. It uses local branches, checks, archives, and commits while keeping the default branch local.

In plain words
What is it for?
Selecting the next unfinished feature, implementing and checking it, committing it locally, merging it into the default branch, removing the merged branch, and continuing through the plan.
Why use it?
It removes repeated pauses between planned features and preserves a clear history of what was built. It also resumes from the next unchecked item when possible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is aiblueprinthq/ai-blueprint's own configuration. It tells Claude Code and Codex how to work on ai-blueprint itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-blueprint configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aiblueprinthq/ai-blueprint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aiblueprinthq/ai-blueprint/main/.agents/skills/continuous/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aiblueprinthq/ai-blueprint

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for continuous

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiblueprinthq/ai-blueprint/continuous/github.svg)](https://agentmods.dev/skills/aiblueprinthq/ai-blueprint/continuous)
Your own site
<a href="https://agentmods.dev/skills/aiblueprinthq/ai-blueprint/continuous"><img src="https://agentmods.dev/badge/skills/aiblueprinthq/ai-blueprint/continuous/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for continuous

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiblueprinthq/ai-blueprint/continuous"><img src="https://agentmods.dev/badge/skills/aiblueprinthq/ai-blueprint/continuous.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 231
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.03798
Opus 5 $0.00030 $0.01899
Sonnet 5 $0.00012 $0.00760
Haiku 4.5 $0.00006 $0.00380

Measured today against content hash 41ff97afc0b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

continuous scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/continuous/SKILL.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

continuous - complete the build plan one local feature at a time

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:

  • create and switch local feature branches
  • create configured checkpoint commits on those branches
  • create required immutable independent-review checkpoints
  • create the final local feature commit
  • squash-merge a completed feature into the local default branch
  • delete the merged local feature branch
  • repeat with the next unchecked build-plan item

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.

Input and target selection

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.

Read the full file on GitHub · 371 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · +32 lines 41ff97afc0b9
  2. 2d ago Changed · +11 lines a7eb4da7a811
  3. 6d ago Changed · +19 lines · -79 tokens per session 5b9283f2a2be
  4. 10d ago First seen · 309 lines · 138 tokens per session scan A e66df983429f

Subscribe to this mod's changes

continuous is a skill published in the GitHub repository aiblueprinthq/ai-blueprint (384 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 3,798 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.