One repeatable pass that lands YOUR finished paths on `main` with a lintable, bindable subject — and refuses cleanly when a peer races you.

> Wraps the native `fak dev plan-audit` reconciler + the `plan_docs_glob` declared in > `.claude/project.yaml`. If a project keeps a *single* plan-state surface (the > plan docs themselves — no typed registry, no live-percent YAML), then `drift` > is structurally empty and the helper's `percent_co

Semver: `major.minor.patch`. Patch = bug fix, minor = new feature, major = breaking.

> **What this does.** An agent-first project lives or dies on a question no > human-facing scorecard asks: can an autonomous coding agent that lands in the > repo cold **discover** what fak is, **want** to adopt it, and **build** on it > without tripping over a missing affordance or an undocumented

One repeatable pass that makes a doc read like a person wrote it, not a model. Runs the doc-appeal scorecard (tools/doc_appeal_scorecard.py), turns each HARD defect into a required edit (em-dash flood, bold-emphasis...

Map the current "what is limiting us right now?" state across the running agent fleet and the live GitHub issue backlog. Runs fleet bottleneck detection plus issue triage, records the dominant system bottlenecks, open-work bottlenecks, and the durable process loop to run next. Use when the operator asks for bottlenecks, open-work constraints, fleet health, issue/backlog limits, or a durable ongoing process for keeping both visible.

Load and follow [`../../../.claude/skills/agent-readiness/SKILL.md`](../../../.claude/skills/agent-readiness/SKILL.md). This generated discovery adapter contains no maintained workflow body.

One repeatable RSI pass over claim reproducibility; run the claim-repro scorecard, retire unfalsifiable witness debt worst-first by adding the real artifact/test/path, re-measure, and commit only the claim-repro lane. Use when this named workflow matches the task.

Clear backed-up local repository work without sweeping up peers - inventory the dirty tree, remove proven generated junk, prioritize coherent slices, ship green partial/enabling work honestly, park or issue the...

One repeatable, evidence-backed pass that retires a bounded batch of maturity debt worst-first across the system's dedicated debt lanes. Inspects `fak debt-lanes`, targets the highest-carrying-cost hotspots (or compounding-interest core lanes), advances maturity with tests, integration, and benchmarks, re-measures with `--compare` to prove the denominator was level-set and total debt dropped, and commits by explicit path with `(fak <leaf>)`. Use when cleaning or retiring maturity debt across units of work.

One repeatable pass that keeps fak's growing namespace CRYSTAL-CLEAR - each similar-sounding concept (cache / vCache / KV cache / cachemeta / the provider prompt-cache; guard vs gate; the two witnesses) given one...

One repeatable pass that keeps the dojo's self-improving RSI loop actually CLOSING on our own billed usage - the real calibration history the dojo measures - instead of a plan-mode scaffold that never acts. Drives...

Plan and ship the next batch on one lane: run `dos-next-up`, acquire a lease with `dos arbitrate`, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with...

Run recurring `dos-dispatch` cycles, switching to `dos-replan` when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.

Refresh a plan portfolio from evidence: close shipped queue items, update cooldown state, and surface the few decisions an operator must make. Use after dispatch bursts, drained backlogs, or recurring findings.

Verify subagent or worker results before folding them into a synthesis. Use when another agent claims it shipped, created, found, or changed something and your next step would otherwise trust its return string.

Synchronize subagent changes to git on shared trunk across all lanes and all untracked WIP by default (or scoped via --lane/--paths). Enforces single-source-of-truth invariants, disjoint file-tree fencing via `dos arbitrate`, detached build-isolation worktrees, and atomic coordinator landing via `fak sweep --apply` or `fak commit --path`. Prevents index corruption, off-trunk drift, peer clobbering, and unverified worker self-reports.

Create or customize a fak-native agent harness from a user's needs. Use when someone asks to make their own harness, agent product, branded/local UI, provider or tool profile, or a "10-minute" / "weekend" harness...

Use when recent trajectories, notes, or refusals should become one evidence-backed harness improvement ticket and at most one guarded worker.

One repeatable pass that keeps fak's competitive story honest AND complete — graded industry-first, not from what fak happened to measure. Runs the industry scorecard (tools/industry_scorecard.py) over a modular data directory (tools/industry_scorecard.data/): a researched taxonomy of the dimensions the LLM-serving / agent-infra field competes on (vLLM/SGLang/TensorRT-LLM/llama.cpp), the current SOTA bar on each with a dated source, and fak's honest position — mostly named gaps. It drives two numbers, coverage (of the field) and parity-debt (honesty of the rows), and updates. Use when this named workflow matches the task.