fix(prose): refresh top-level skill path references for flat layout

Re-point promise-theory reference links to ../../workflow-architect/SKILL.md
(one level deeper than SKILL.md), drop the bundles/ prefix from the
pace-plan evidence-ledger path, and refresh the stale eval-coverage.py
comment to describe only the flat <root>/<skill-name>/SKILL.md shape.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

pace-plan/EVIDENCE-LEDGER.md

@@ -14,7 +14,7 @@ Repair the issue #159 research defects and deliver a source-grounded, authority-
 - GitHub issue `magnus919/agent-skills#159` and existing issue comment `5086185139`.
 - `AGENTS.md`, `agent-skills/SKILL.md`, and skill-format references.
 - `spec-driven-development/SKILL.md`, SPEC and VERIFICATION templates, and quality gates.
-- `bundles/neckbeard/SKILL.md`, stage, authority, and evidence-ledger references.
+- `neckbeard/SKILL.md`, stage, authority, and evidence-ledger references.
 - `research-methodology/SKILL.md` and original assets from `HEAD`.
 - Directly extracted CISA/NCSWIC PACE PDF and its CISA publication page.
 - Existing skill, README, eval, validator, and generated-catalog patterns in this repository.

promise-theory/references/agent-coordination.md

@@ -134,7 +134,7 @@ This procedure is this skill's synthesis — **EXTRAPOLATION** — of the source
 
 - **Multi-agent debate and convergence** → [agent-council](../agent-council/SKILL.md). When you want to *run* structured multi-agent debate, agent-council is the operational tool: its panel debate is a promise exchange (each panelist offers positions, the moderator accepts/assesses, synthesis converges), and its convergence-aware iteration is an evaluation loop over the panel's promises. Use promise theory to *design* the exchange; use agent-council to *execute* it.
 - **Assessment layer** → [agent-evals-and-observability](../agent-evals-and-observability/SKILL.md) (also routed from `references/trust-and-verification.md`): verifying promises are kept via evals, traces, and guardrails.
-- **Workflow design as promise chains** → [workflow-architect](../bundles/workflow-architect/SKILL.md) (also routed from `references/patterns.md`): designing a workflow is designing a chain of promises.
+- **Workflow design as promise chains** → [workflow-architect](../../workflow-architect/SKILL.md) (also routed from `references/patterns.md`): designing a workflow is designing a chain of promises.
 - **Promise-keeping evidence** → [artifact-pyramids](../artifact-pyramids/SKILL.md) (also routed from `references/trust-and-verification.md`): structure evidence as summaries → analysis → evidence dossiers.
 - **The skill format itself** → [agent-skills](../agent-skills/SKILL.md); **script conventions** → [cli-builder](../cli-builder/SKILL.md).
 

promise-theory/references/patterns.md

@@ -149,7 +149,7 @@ Each is a renegotiation of the promise set, not a scolding. The breach is record
 - **Evaluate on a cadence** (pattern 4): the loop is what makes promises real.
 - **Plan breach as a recovery path** (pattern 5) and **redundancy for what must survive** (pattern 6).
 - **Calibrate trust deliberately** (pattern 7): the schedule is the operational face of the two-component model.
-- **Designing a whole workflow as a chain of promises?** Route to [workflow-architect](../bundles/workflow-architect/SKILL.md) — its guided workflow discovery and synthesis turn a sequence of phases, branching signals, and handoffs into a structured bundle; promise theory supplies the semantics of each handoff (offer → acceptance → assessment), workflow-architect supplies the workflow-building machinery. **EXTRAPOLATION** — the semantic mapping between the two skills is this skill's synthesis; both the promise model and the workflow-architect process are documented in their own sources.
+- **Designing a whole workflow as a chain of promises?** Route to [workflow-architect](../../workflow-architect/SKILL.md) — its guided workflow discovery and synthesis turn a sequence of phases, branching signals, and handoffs into a structured bundle; promise theory supplies the semantics of each handoff (offer → acceptance → assessment), workflow-architect supplies the workflow-building machinery. **EXTRAPOLATION** — the semantic mapping between the two skills is this skill's synthesis; both the promise model and the workflow-architect process are documented in their own sources.
 
 Also relevant: [agent-evals-and-observability](../agent-evals-and-observability/SKILL.md) for the assessment layer that pattern 4's loop calls on, and [artifact-pyramids](../artifact-pyramids/SKILL.md) for structuring the evidence the ledger accumulates.
 

scripts/eval-coverage.py

@@ -28,11 +28,10 @@ WARN_THRESHOLD = 25  # modified skills without evals get a warning
 FAIL_THRESHOLD = 50  # modified skills without evals fail CI
 
 # Pathspec that matches every tracked file under a canonical skill directory.
-# A canonical skill lives at <root>/<skill-name>/SKILL.md or
+# A canonical skill lives at <root>/<skill-name>/SKILL.md.  The glob
-# <root>/bundles/<bundle-name>/skills/<skill-name>/SKILL.md.  The glob
+# ``*/SKILL.md`` covers that shape.  We use the same glob for both ls-files
-# ``*/SKILL.md`` covers the first shape; ``bundles/*/skills/*/SKILL.md``
+# and diff so that modified-skill detection sees the same universe as
-# covers the second.  We use the same glob for both ls-files and diff so
+# find_skills().
-# that modified-skill detection sees the same universe as find_skills().
 SKILL_PATHSPEC = ":(glob)**/SKILL.md"