OpenAI says GPT-6 Astra works better when developers stop using long skill descriptions and blanket reading requirements.
The company advises tying instructions tightly to specific tasks and defining clearly when a job is finished. Eric Provencher, a writer for OpenAI, notes that instructions piled up over time can consume context or cause the model to stop work too early. He recommends reviewing skills,
AGENTS.md
, and task prompts whenever switching models.
More capable models need less hand-holding. This aligns with earlier advice from OpenAI on model transitions.
Vague skill descriptions lead to wrong picks
Skill descriptions are prompts stored as Markdown files that can include resources and scripts. Provencher says they work best for specific workflows or applications. Their names and descriptions go into the model’s context so Codex can pick the right skill for a given task.
Too many skills force Codex to truncate descriptions, stripping out information it needs to choose correctly. Conflicting descriptions or overly broad scope can also load instructions the model doesn’t need. Provencher recommends keeping scope descriptions short and precise. A skill for Postgres schema migrations should only fire when creating or modifying a migration or when checking its rollout.
If a skill covers multiple workflows, its main document should briefly point to the right supplementary docs and scripts. That way the model only reads what it actually needs, since every extra read eats context and pushes it closer to summarisation.
Detailed step-by-step sequences can also slow down newer models, since they handle nuance and ambiguity better on their own. But shared skills apply to every contributor’s agents, so teams need to be careful. What works for Sol or Luna might already be too restrictive for someone running Astra.
Mandatory reading before every change wastes context
The rules in
AGENTS.md
that govern repository work need regular reviews too. Requiring the model to read multiple documents or a full project overview before every change is overkill for a typo fix. Astra can figure out what it needs on its own.
Instead of forcing it to read
architecture.md
,
database.md
, and
deployment.md
every time, Provencher suggests pointing to those docs selectively. Architecture info when working on service boundaries. Database docs when changing schemas. Deployment notes when shipping. The docs also need to stay current.
Explicit permissions can also cut down on repeated confirmation requests for safe operations. For local tests using throwaway data with no production access,
AGENTS.md
can explicitly allow the agent to run tests, fix errors caused by the requested change, and re-run affected tests without asking again.
Astra needs a clear goal, not a checklist
If earlier models went rogue and you locked things down with strict approval rules, it is time to revisit those when switching to Astra. OpenAI credits the model with better judgment, but it can also interpret old restrictions so literally that it stops even when you want it to keep going. Known, safe workflows should be explicitly allowed.
Even without restrictions, Astra may stop earlier than GPT-5.6 Sol. Provencher notes this. He recommends defining upfront what “done” means. If the agent should implement something, run it, check the results, and fix errors, all of that needs to be in the prompt. A requirement to check in after the first implementation sets an earlier stopping point.
OpenAI recently published detailed prompting tips for GPT-6 Astra, and these skill and project instruction recommendations build on that guidance.
What it means
Developers must stop treating advanced models like junior programmers. Teams should audit their
AGENTS.md
files to remove mandatory reads for simple fixes. Skill descriptions must be scoped to single actions rather than broad categories. Clear definitions of completion prevent the model from halting mid-task.
