agent-tuning
SkillAI & modelsUse when changing agent model or effort configuration, adapter mappings, or eval candidate profiles.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the agent-tuning skill
What this skill tells your AI
The instructions your AI receives, as published by kunchenguid/no-mistakes in .agents/skills/agent-tuning/SKILL.md and read by ahel’s review.
Unified Agent Tuning (internal/agentcfg)
agentcfgis the single owner of the harness-neutral model/effort surface and of the mapping down to each harness's native mechanism (claude/copilot--effort, codex-m+-c model_reasoning_effort, grok--reasoning-effort, pi--thinking, opencode's session-messagemodel/variant, acpx--modelforcursor/acp:<target>). Add a harness there, not in an adapter or in eval.rovodevandantigravityare deliberately declared unmappable, so a request for them is a config error rather than a flag that is silently ignored.agent.NewWithOptionsis the one funnel: it validatesOptions.Profileand splices the mapped args after the operator's rawagent_args_overrideargs, so both the pipeline (cfg.AgentProfileFor) and eval replay (Candidate.Profile()) reach every harness by the same path. Never re-derive a model or effort flag at a call site.- Precedence is fixed: a raw
agent_args_overrideflag that already pins a knob natively wins and the mapped value is not emitted, which is what keeps every pre-agent_configconfiguration byte-identical and stops a harness receiving one knob twice.agent_configis global-only for the same reason asagent_args_override. - Eval candidates are
agent,model=<model>[,effort=<level>](the previousagent+modelspelling is refused with a migration message), effort is part of the persisted candidate identity, andagentNeutralGlobalConfigstripsagent,agent_args_override, andagent_configso a replay never inherits the capturing machine's pins. - Keep eval replay identity comparison centralized in
agentcfg.ServedMatchesRequested; do not compare an adapter's reported model directly at call sites. The user-facing normalization semantics and candidate guidance live indocs/src/content/docs/reference/eval.md. - Regressions:
internal/agentcfg,internal/agent/profile_test.go,internal/config/config_agent_config_test.go,internal/daemon/pipeline_agent_profile_test.go,TestParseCandidate*,TestReplayPinsCandidateModelAndEffortOnTheHarness,TestCaptureStripsEveryHarnessPinFromThePinnedConfig,TestServedMatchesRequested,TestReplayPiModelIdentityComparison.
Signals
- GitHub stars
- 8k
- Forks
- 855
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
agent-tuning- Source
- github.com/kunchenguid/no-mistakes