Anchor already keeps executor task specs lean — never the whole project, never a raw file dump, only the context a task actually needs. The fleet registry itself was the exception: the model-fleet MCP's list_fleet handed back every endpoint's base_url and model name whether or not the caller needed it, and there was no other way to get the same picture into a prompt. It's on the same diet as everything else now.

Picking which plan to work on has always been mechanical — priority, value, fit, dependencies, none of it needs judgment. But two real gaps sat under that mechanism: a plan quoting an example header inside a code fence could be misread as its own field, and one corrupt file could take down a whole polling loop. Both are fixed, and daemons get an explicit triage mode that makes the "no model needed" property visible instead of implicit.

An executor's reasoning, false starts, and quoted templates used to ride along with everything else in its reply — all the way back into the coordinator's own context, and from there into the next task's prompt. Only the structured footer does that now; the rest is archived to disk and discarded from context.

Mythos-core rule 6 has always told a model to stop after two failed fix attempts and hand the problem up. That only works if the model is still counting straight — and a resumed or re-invoked task starts a fresh context with no memory of the attempts a prior run already burned. The orchestrator now keeps that count itself.

Anchor's hard rule used to read: run /commit-prep before any commit. /review had been ignoring it for months.

If python server.py gave you ModuleNotFoundError: No module named 'mcp.server.fastmcp', this was us.

/local-models used to exist only after you scaffolded a project. It now lives in the Anchor checkout the same way /work does — so you can ask "what can this box run?" before a project exists — and is still copied into Claude and Grok projects. The probe is still this host only.

Anchor already stopped too-hard work with a first-line SUGGEST-ESCALATE. Premium sessions still burned credits on too-easy work with only a soft “say so and ask.”

Anchor’s fit check used to answer one question well: is this model strong enough? Mythos-core rule 11 and model-fitness.md sent weak-column and orchestration-class work up with SUGGEST-ESCALATE. That stopped silent overreach — but it did not catch the other failure mode: a model that is strong enough yet the wrong kind of product for the job.

A task that runs out of context used to fail the worst way available: a truncated answer, a confident "the rest is straightforward", or a silent stop that looks like success. Executors now emit a structured handoff as they approach their declared budget, and the orchestrator respawns a fresh context seeded with it.