codex-sdd:continue

A controller for continuing an active OpenSpec workflow, a step-by-step method for planning and delivering software changes.

In plain words
What is it for?
Resuming work, implementing planned tasks, running checks, recording evidence, and handling review or validation points.
Why use it?
It chooses the next workflow step from the current state instead of requiring you to remember separate commands.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/skyloevil/codex-sdd/continue
Any agent
npx skills add skyloevil/codex-sdd --skill continue
Clone the repo
git clone --depth 1 https://github.com/skyloevil/codex-sdd

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 483 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.00483
Opus 5 $0.00013 $0.00242
Sonnet 5 $0.00005 $0.00097
Haiku 4.5 $0.00003 $0.00048

Measured yesterday against content hash 0379dfa4a1d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-sdd:continue 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 yesterday.

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.

skills/continue/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec Continue

Context

Continue is the high-level entry point for a smooth Codex App workflow. It uses the state machine to decide what should happen next, instead of requiring the user to remember propose/plan/implement/validate/archive commands.

Workflow

  1. Call openspec_get_goal.
  2. If there is an active change but no useful loop objective, call openspec_create_goal using the change proposal/next action as the objective and the acceptance criteria as successCriteria.
  3. Call openspec_continue_loop and follow the returned decision.
  4. If decision.kind is ask_human, summarize the pending review, the gate, and the risk. Wait for approval before calling openspec_resolve_human_review.
  5. If decision.kind is act, read tasks with openspec_read_artifact, implement the referenced task, call openspec_record_iteration, run focused checks, call openspec_record_validation_evidence, then call openspec_update_task only after evidence exists or the user explicitly accepts a pending validation state.
  6. If decision.kind is validate, call openspec_validate, run relevant checks, record evidence, fix drift, and request/resolve the validation gate when clean.
  7. If decision.kind is run_hook, execute or ask for the required hook based on its policy, then call openspec_record_hook_result.
  8. If decision.kind is archive, call openspec_archive_change.
  9. If decision.kind is complete or blocked, report the final loop state.

Human Gates

Confirm at scope, design, validation, archive, and before destructive work: file deletion, public API changes, database schema changes, broad refactors, or external-system writes.

Automatically request a human review with openspec_request_human_review when requirements are ambiguous, validation repeatedly fails, required hooks fail, or a step would perform destructive changes, public API changes, database schema changes, security-sensitive changes, or external-system writes.

Read the full file on GitHub · 43 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. yesterday First seen · 43 lines · 25 tokens per session scan A 0379dfa4a1d3

Subscribe to this mod's changes

codex-sdd:continue is a skill published in the GitHub repository skyloevil/codex-sdd (1 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 483 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

codexkit-repository-maintenance

Use when maintaining or improving the GameStudio-CodexKIT source repository, including CI, governance, catalog, generators, adapters, packaging, documentation, versioning, or release readiness.

hoatv2211/GameStudio-CodexKIT · 45 tokens

unity-ui-art-and-motion-production

Use when new or revised Unity UI visuals, icons, panels, 9-slice sprites, component states, HUD or menu layouts, popup motion, screen transitions, or flattened UI screenshot decomposition must be produced through Figma and integrated into uGUI, NGUI, or UI Toolkit; not for UI debugging, localization-only work…

hoatv2211/GameStudio-CodexKIT · 83 tokens

game-screenshot-showcase-and-store-packaging

Use when a Unity team needs approved PlayMode screenshots, immutable capture evidence, reviewed showcase slides, or report-only store screenshot packaging without auto-upload, signing, or submission.

hoatv2211/GameStudio-CodexKIT · 44 tokens

studio-project-scaffold

Use when running gamestudio init, status, or uninit, or bootstrapping a new or adopted game repository with AGENTS.md, HANDOFF.md, .agents/CONTRACT.md, project governance, a subsystem registry, or a per-project adapter report, plan digest, named reviewer, backup root, generated agent overlay, apply, uninstall, and…

hoatv2211/GameStudio-CodexKIT · 85 tokens

using-game-studio-skills

Use when starting any GameStudio-CodexKIT task or when a model runner is unavailable and someone requests a confidence-based PASS.

hoatv2211/GameStudio-CodexKIT · 33 tokens

skill-authoring-and-audit

Use when creating or revising a GameStudio-CodexKIT skill, resolving ambiguous skill triggers, auditing provenance or lifecycle maturity, or deriving reusable capabilities from session history.

hoatv2211/GameStudio-CodexKIT · 41 tokens