ak-codex-goal
Guide a long-running goal with a verifiable stop condition; use Codex goal-mode features when available and portable Continuity semantics otherwise.
Install / Use
npx skills add anmh1205/angent --skill ak-codex-goalInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of ak-codex-goal
ak-codex-goal scores 61/100 on our quality scale, 4043rd of 4,607 Development & Engineering skills we index.
Its SKILL.md is 1.9 KB long, split into 5 sections and no code examples: moderately detailed.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- The repository was last updated today, so ak-codex-goal is actively maintained.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 80/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
ak-codex-goal compared with similar skills
All 4 of these similar skills score higher than ak-codex-goal; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| ak-codex-goal (this skill)by anmh1205 | 61 | 0 | today | SKILL.md |
| taste-skillby Leonxlnx | 100 | 97.0k | 1d ago | CLAUDE.md |
| ai-job-searchby MadsLorentzen | 100 | 46.9k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 41.9k | today | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 22d ago | SKILL.md |
Frequently asked questions
- How do I install ak-codex-goal?
- Run
npx skills add anmh1205/angent --skill ak-codex-goal. The install tabs above show the steps for each supported agent. - Which AI agents does ak-codex-goal work with?
- It is written for OpenAI Codex, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is ak-codex-goal safe to use?
- It declares no license and scores 80/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is ak-codex-goal still maintained?
- The repository was last updated today, so ak-codex-goal is actively maintained.
Skill content
View source on GitHubname: ak-codex-goal description: Guide a long-running goal with a verifiable stop condition; use Codex goal-mode features when available and portable Continuity semantics otherwise. license: MIT metadata: {port: angent-fallback, mode: adapted}
Goal Mode — Portable Fallback
This Skill generalizes the useful semantics of long-running Codex goal work without requiring Codex.
Goal contract
Define:
- durable objective;
- hard constraints;
- acceptance evidence;
- authorized effects;
- stop conditions;
- current frontier.
Runtime selection
If the active harness exposes a native durable-goal mode, use it.
Otherwise implement the same semantics through ANGENT Continuity:
- proactive frontier persistence;
- dependency-aware next action;
- periodic endpoint verification;
- no stop merely because a status report was produced.
Stop
Stop only at verified goal completion, a true blocker, required user decision, authority boundary or exhausted explicit budget.
Never reinterpret “autonomous goal” as permission for unauthorized external effects.
Stable 2.19.0 goal execution
Prefer actual Codex durable-goal support only when verified in the current runtime. In other harnesses, preserve the goal contract through Continuity without inventing a persistent background worker. Store objective, hard constraints, permitted effects, verifiable stop test, committed work, exact first unfinished step, active operations and dependency edges. On resume rebind the user-named workstream to live repository/provider state, rather than replaying a stale checkpoint.
Continue independent RUNNABLE units when one operation waits, and check only meaningful conditions. A progress response does not finish the goal; terminate only on verified endpoint, true blocker, explicit budget exhaustion or an authority/user decision boundary. No autonomous execution survives the host stopping unless a real scheduler exists.
Related Skills
taste-skill
97.0kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
46.9kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
41.9kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
