holycodex 0.16.3 → 0.16.4-dev.77.1

package/dist/assets/plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "holycodex",
-  "version": "0.16.3",
+  "version": "0.16.4",
   "description": "Root-directed capabilities and deterministic installed assets for HolyCodex.",
   "author": {
     "name": "David Basile Filho",
@@ -26,7 +26,7 @@
       "Code Intelligence"
     ],
     "defaultPrompt": [
-      "Use HolyCodex to implement and verify this task."
+      "Activate HolyCodex capabilities for this task."
     ]
   }
 }

package/dist/assets/plugin/skills/code-review/SKILL.md

@@ -1,16 +1,9 @@
 ---
 name: code-review
-description: Use once after code or manifest implementation when Root needs adversarial review and bounded repair to a fixed point.
+description: Use after implementation when Root needs adversarial code review and bounded repair to a fixed point.
 ---
 
-Use this skill once after implementation or manifest work. Inspect the actual
-integrated result to a fixed point before Root judges readiness. Apply
-[testing quality](../testing-quality.md) when judging new or modified tests.
-
-Inspect the assigned diff, callers, contracts, tests, compatibility, and
-artifact. Repair defects inside the review surface, verify each repair, and
-repeat until the review reaches a fixed point.
-
-Flag speculative abstractions, pointless file splits, oversized changes,
-unclear dependency direction, and tests that protect implementation detail.
-Confirm incidental generated output is absent before stopping.
+Inspect the integrated implementation for correctness, safety, maintainability,
+compatibility, and mergeability. Check callers, contracts, tests, and generated
+artifacts. Repair defects inside the review surface. Flag implementation-detail
+tests and speculative abstractions when they affect the assigned change.

package/dist/assets/plugin/skills/code-review/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Code review"
   short_description: "Review one implementation result to a fixed point."
-  default_prompt: "After implementation, inspect the assigned result once, repair reviewer-owned defects to a fixed point, and return evidence for Root's readiness judgment."
+  default_prompt: "Open the code review workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/commit/SKILL.md

@@ -3,13 +3,29 @@ name: commit
 description: Use when Root owns a local commit after exact scope and proof are settled; verify scope, create the minimal commit, and report identity.
 ---
 
-Owner: Root. Boundary: perform all Git/VCS inspection and mutation. Verify the
-exact diff scope, required local proof, temporary/generated-artifact cleanup,
-and ignore coverage before staging. Preserve unrelated work and ensure
-environment secrets, credentials, and private release material are absent from
-the staged file list. Local commits need no user approval; every exact push,
-tag, merge, CI trigger, publication, or other remote mutation requires fresh
-user approval through native `request_user_input` immediately beforehand.
+Root uses this workflow after exact scope and local proof are settled. Verify
+the diff, generated-artifact cleanup, ignore coverage, and staged secret
+exclusions before creating the local commit.
+
+Require a passing Reviewer.code fixed-point result after implementation or a
+major codebase change before this VCS exception is used.
+
+After integration, Root commits the exact approved ref and gives its exact ref
+and SHA to `Worker.operations` for terminal CI observation.
+Discover the repository's actual development/release topology first; never
+assume GitHub, branch names, or that pending is success. Delegate fixes for
+failures, then repeat integration, commit, push, and observation until the
+repository gate is terminal green. If release is authorized, Root performs the
+repository's own release mechanism only after the development gate is terminal
+green, then delegates terminal release verification. If development and release
+share one pipeline, or the repository has no distinct release gate, record that
+topology and apply the repository's one available terminal gate. Fix failures
+through a new bounded Assignment and repeat the same review/VCS/observation
+cycle.
+
+Local commits need no user approval; every exact push, tag, merge, CI trigger,
+publication, or other remote mutation requires fresh user approval through
+native `request_user_input` immediately beforehand.
 
 Completion: Root reports the commit identity and post-commit status with
 redacted evidence, or returns an exact reproducible blocker. Never print secret

package/dist/assets/plugin/skills/commit/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Commit"
   short_description: "Create one local commit with exact scope proof."
-  default_prompt: "When Root owns a local commit, verify exact scope, required proof, ignore coverage, and secret exclusions, create only that commit, and report redacted identity and status."
+  default_prompt: "Open the commit workflow for this invocation."
 policy:
   allow_implicit_invocation: false

package/dist/assets/plugin/skills/compress/SKILL.md

@@ -1,10 +1,8 @@
 ---
 name: compress
-description: Use when Root assigns text that must be shortened; preserve meaning, constraints, technical terms, and voice.
+description: Use when assigned text must be shortened without changing its contract or voice.
 ---
 
-Owner: Worker. Boundary: remove repetition without changing requirements,
-technical terms, product voice, or required evidence.
-
-Completion: the compressed text is constraint-equivalent to the input and any
-unresolvable ambiguity is explicit.
+Shorten only the assigned text. Preserve meaning, constraints, technical terms,
+product voice, and required evidence. The result is complete when it is
+constraint-equivalent and any ambiguity that cannot be preserved is explicit.

package/dist/assets/plugin/skills/compress/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Compress"
   short_description: "Shorten assigned text without changing its contract or voice."
-  default_prompt: "When Root assigns text compression, produce one compact constraint-equivalent draft and identify preserved technical terms."
+  default_prompt: "Open the compression workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/context7-cli/SKILL.md

@@ -1,14 +1,8 @@
 ---
 name: context7-cli
-description: Use first when Root assigns a current library, framework, SDK, or API fact; use a network research route only for releases, dates, gaps, or corroboration.
+description: Use when a current library, framework, SDK, or API fact needs authoritative documentation.
 ---
 
-Use the current documentation route before relying on memory, because APIs
-and tool behavior change and repository evidence cannot establish currency.
-
-Owner: Librarian for research; Worker may use the assigned result. Boundary:
-gather sourced claims, versions, dates, conflicts, and coverage limits without
-editing the repository or deciding architecture.
-
-Completion: every requested current fact has an authoritative locator or an
-explicit coverage gap, and no unsupported external claim is used as proof.
+Use current authoritative documentation before relying on memory. Return the
+requested versions, behavior, dates, conflicts, and coverage limits with
+source locators. Do not turn an external fact into an architecture decision.

package/dist/assets/plugin/skills/context7-cli/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Context7 CLI"
   short_description: "Find assigned current library and API documentation first."
-  default_prompt: "When Root assigns a current library or API fact, use the documentation route first and return sourced evidence with coverage limits."
+  default_prompt: "Open the current documentation lookup workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/debugging/SKILL.md

@@ -1,22 +1,8 @@
 ---
 name: debugging
-description: Use when Root assigns a reproducible crash, wrong result, regression, hang, race, leak, or slowdown; isolate and prove the narrow repair.
+description: Use for a reproducible crash, wrong result, regression, hang, race, leak, or slowdown.
 ---
 
-Reproduce the defect before changing code. A stable red case distinguishes
-cause from symptom and makes the repair checkable.
-
-Owner: Worker within the assigned seam. Boundary: capture the smallest
-failing input and trace, form an evidence-backed cause, apply the narrow fix,
-and preserve unrelated behavior. Escalate competing causes or material
-redesign.
-
-Discover and use the repository-specific formatter, linter, typecheck, and
-validation commands before and after the repair. Start with the smallest
-relevant local proof and expand only when the defect crosses that boundary or
-the release gate requires it; report unavailable commands rather than
-inventing replacements.
-
-Completion: the failure is reproduced, the cause is supported by repository
-evidence, the fix and regression proof pass, and remaining uncertainty is
-recorded.
+Reproduce the defect before changing code. Capture the smallest failing input
+and trace, identify the evidence-backed cause, make the narrow repair, and prove
+the regression is gone. Escalate competing causes or a material redesign.

package/dist/assets/plugin/skills/debugging/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Debugging"
   short_description: "Reproduce and repair one observable defect."
-  default_prompt: "When Root assigns a reproducible defect, reproduce it, isolate its cause, make the narrow repair, and prove the regression is gone."
+  default_prompt: "Open the debugging workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/grill-me/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: grill-me
+description: Use when an unspecified choice has multiple reasonable outcomes that could materially change the work.
+---
+
+# Grill me
+
+Use this skill only for a material unresolved choice involving architecture,
+behavior, UX, compatibility, dependencies, cost, security, external effects,
+or another meaningful user-visible result. Infer obvious safe defaults and
+continue without questioning routine omissions.
+
+Before asking, finish authorized discovery and reversible preparation that can
+narrow the choice without deciding it. Ask only for the earliest unresolved
+choice required by the next executable phase. After the answer, continue the
+discovery and ask the next dependent question only if it remains material.
+Avoid questionnaires about later phases whose relevance may change.
+
+Persist the answer through the current Intent or Plan state model. Return to
+Root with the selected decision, its scope, and the evidence or dependency it
+unblocked; use `needs_root_input` when the choice remains unresolved.

package/dist/assets/plugin/skills/grill-me/agents/openai.yaml

@@ -0,0 +1,6 @@
+interface:
+  display_name: "Grill me"
+  short_description: "Ask only material, dependency-ordered clarification questions."
+  default_prompt: "Open the material-choice clarification workflow for this invocation."
+policy:
+  allow_implicit_invocation: true

package/dist/assets/plugin/skills/handoff/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: handoff
-description: Use when Root pauses or transfers work; produce one redacted resumable handoff.
+description: Use when a caller needs a redacted projection of current Intent state for resume or export.
 ---
 
-Owner: Worker. Boundary: retain scope, owner, permissions, decisions,
-evidence, blockers, remaining risk, and the exact next action; omit secrets
-and unchanged narration.
-
-Completion: one bounded, redacted handoff is ready for the receiving owner.
+Produce one compact projection of current Intent, Plan, and Assignment status,
+evidence, blockers, remaining risk, and the exact next action. Omit secrets,
+raw prompts, transcripts, and unchanged narration. Handoff is an export view;
+the semantic state remains authoritative.

package/dist/assets/plugin/skills/handoff/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Handoff"
-  short_description: "Produce one redacted handoff when assigned work pauses or transfers."
-  default_prompt: "When Root pauses or transfers work, write one redacted handoff containing scope, constraints, evidence, risks, and the next action."
+  short_description: "Export a redacted projection of current Intent state."
+  default_prompt: "Open the handoff workflow for this invocation."
 policy:
   allow_implicit_invocation: false

package/dist/assets/plugin/skills/operations/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: operations
+description: Use for exact-ref CI or release observation through terminal evidence.
+---
+
+Observe the exact approved ref and SHA after Root's VCS action. Discover
+whether the repository has separate development and release gates, one combined
+pipeline, or no formal separation. Report terminal green, terminal failure, or
+an exact unavailable or ambiguous blocker. Pending and running are not success.
+Do not rerun, cancel, approve, merge, push, tag, publish, deploy, or otherwise
+mutate external state.

package/dist/assets/plugin/skills/operations/agents/openai.yaml

@@ -0,0 +1,6 @@
+interface:
+  display_name: "Operations"
+  short_description: "Observe exact-ref CI or release state to terminal evidence."
+  default_prompt: "Open the terminal operations observation workflow for this invocation."
+policy:
+  allow_implicit_invocation: false

package/dist/assets/plugin/skills/plan/SKILL.md

@@ -1,13 +1,10 @@
 ---
 name: plan
-description: Use when Root faces unresolved architecture, scope, coordination, or material risk before work begins; produce the implementation-ready decision record.
+description: Use when unresolved architecture, scope, coordination, or material risk requires an implementation-ready Plan.
 ---
 
-Owner: Root. Boundary: identify alternatives, constraints, risks, route,
-acceptance evidence, exclusions, and recovery without dispatching
-implementation work before the plan gate opens. Specialists may supply facts
-but may not decide the outcome.
-
-Completion: Root has an implementation-ready plan naming scope, owners and
-seams, data and control flow, policy, recovery, tests, compatibility, the
-preferred shape, and a bounded proof route.
+Resolve the current material choices into an implementation-ready Plan with
+scope, owners, seams, data and control flow, policy, recovery, compatibility,
+acceptance evidence, and a bounded proof route. Keep planning proportional:
+trivial work can proceed without a Plan. Persist the canonical revision through
+the semantic Plan operation.

package/dist/assets/plugin/skills/plan/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Plan"
   short_description: "Resolve material scope and architecture choices before work."
-  default_prompt: "When Root faces an unresolved material choice, produce an implementation-ready plan covering scope, route, risk, and proof."
+  default_prompt: "Open the planning workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/plan-review/SKILL.md

@@ -1,11 +1,9 @@
 ---
 name: plan-review
-description: Use when Root has a complete plan that needs adversarial review; check feasibility, order, risk, and proof to a fixed point.
+description: Use when a complete Plan needs adversarial feasibility, order, risk, and proof review.
 ---
 
-Owner: Reviewer. Boundary: inspect the complete plan once to a fixed point;
-repair only reviewer-owned plan defects. Return material product or
-architecture choices to Root.
-
-Completion: the plan is complete with proof, blocked with evidence, or
-explicitly needs a Root decision.
+Inspect the complete Plan for feasibility, ordering, risk, and proof. Repair
+only reviewer-owned plan defects; return material product or architecture
+choices to Root. A Plan revision replaces the canonical revision through the
+semantic plan operation.

package/dist/assets/plugin/skills/plan-review/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Plan review"
   short_description: "Review one complete plan to a fixed point."
-  default_prompt: "When Root has a complete plan, inspect it once, repair reviewer-owned defects to a fixed point, and return structured proof."
+  default_prompt: "Open the plan review workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/programming/SKILL.md

@@ -1,11 +1,8 @@
 ---
 name: programming
-description: Use when Root has decided a seam and assigns bounded implementation, fixes, tests, or manifests with known acceptance behavior.
+description: Use when Root has decided a bounded implementation seam with known acceptance behavior.
 ---
 
-Implement the decided seam inside the assigned files. Inspect the callers and
-tests needed to preserve its behavior and typed boundaries, then add focused
-proof at the least brittle observable boundary. Discover the repository's own
-validation commands and run the smallest relevant check first; broaden when
-the changed boundary or release gate requires it. Inspect changed files and
-remove incidental generated output before stopping.
+Implement only the decided seam. Inspect its callers and typed boundaries
+before implementation, and add proof at the least brittle observable boundary
+when the acceptance behavior requires it.

package/dist/assets/plugin/skills/programming/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Programming"
   short_description: "Implement one decided seam with proportional proof."
-  default_prompt: "When Root assigns a decided seam, implement it, add focused proof, inspect changed files, and return structured evidence."
+  default_prompt: "Open the bounded programming workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/refactor/SKILL.md

@@ -1,11 +1,8 @@
 ---
 name: refactor
-description: Use when Root has decided one seam needs restructuring; preserve behavior, ownership, and interfaces.
+description: Use when one decided seam needs restructuring while preserving behavior and interfaces.
 ---
 
-Restructure only the decided seam. Trace its callers before changing a shared
-root cause, preserve public behavior and interfaces, and keep the smallest
-cohesive change. Discover the repository's own validation commands and run the
-smallest relevant behavior-locked check first; broaden when the changed
-boundary or release gate requires it. Inspect changed files and remove
-incidental generated output before stopping.
+Restructure only the decided seam. Trace callers before changing a shared root
+cause and preserve public behavior and interfaces. Verify the behavior boundary
+after the refactor.

package/dist/assets/plugin/skills/refactor/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Refactor"
   short_description: "Restructure one decided seam while preserving its contract."
-  default_prompt: "When Root assigns a seam refactor, preserve behavior and interfaces, inspect the changed files, and return focused proof."
+  default_prompt: "Open the bounded refactor workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/rules/SKILL.md

@@ -1,10 +1,8 @@
 ---
 name: rules
-description: Use when Root assigns a repository rule discovery, validation, or application failure; trace the owning rule path.
+description: Use when a repository rule needs discovery, validation, or diagnosis of an application failure.
 ---
 
-Owner: Worker. Boundary: inspect the owning rule loader and preserve
-deduplication, limits, caching, trust boundaries, and rule ownership.
-
-Completion: the rule path, policy, observed failure, and verification evidence
-are explicit, or the exact blocker is returned.
+Trace the owning rule loader and its limits, caching, trust boundary, and
+deduplication. State the observed failure, the owning policy, and the evidence
+that proves the rule path or exact blocker.

package/dist/assets/plugin/skills/rules/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Rules"
   short_description: "Trace one repository rule discovery or application failure."
-  default_prompt: "When Root assigns a rule failure, inspect the owning rule seam and return exact behavior, limits, and failure evidence."
+  default_prompt: "Open the repository rules workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/stop-slop/SKILL.md

@@ -1,38 +1,9 @@
 ---
 name: stop-slop
-description: Use when Root assigns prose to draft, edit, or review; remove predictable AI writing patterns while preserving the requested voice.
+description: Use when assigned prose should lose predictable AI writing patterns while preserving voice.
 ---
 
-Owner: Worker or Reviewer within the assigned prose surface. Boundary: edit
-only the assigned text, preserve meaning and product voice, and use the linked
-references for phrase, structure, and example branches when needed.
-
-# Stop Slop
-
-Remove predictable AI writing patterns from prose.
-
-## Core rules
-
-1. Cut filler phrases, emphasis crutches, and adverbs. See
-   [phrases](references/phrases.md).
-2. Break formulaic structures, binary contrasts, negative listings, dramatic
-   fragments, rhetorical setups, and false agency. See
-   [structures](references/structures.md).
-3. Use active voice and name the person doing the work.
-4. Replace vague declarations and lazy extremes with specific facts.
-5. Prefer "you" and concrete details over distant abstractions.
-6. Vary sentence length and paragraph rhythm. Avoid em dashes.
-7. State facts directly without softening or hand-holding.
-8. Rewrite pull-quote language as plain language.
-
-Before delivery, check for adverbs, passive voice, inanimate actors, vague
-claims, throat-clearing, binary contrasts, meta-joiners, em dashes, and repeated
-rhythm. Use [examples](references/examples.md) to calibrate edits.
-
-Completion: the assigned prose is direct, specific, constraint-equivalent,
-and reviewed against the relevant references; any deliberate voice tradeoff
-is recorded.
-
-## License
-
-MIT
+Edit only the assigned prose. Remove filler, formulaic structure, vague claims,
+passive voice, and repeated rhythm while preserving meaning and voice. Use the
+linked [phrase](references/phrases.md), [structure](references/structures.md),
+and [example](references/examples.md) references when needed.

package/dist/assets/plugin/skills/stop-slop/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Stop Slop"
   short_description: "Edit assigned prose to remove predictable AI patterns."
-  default_prompt: "When Root assigns prose editing, apply the concise rules and disclosed references while preserving meaning and voice."
+  default_prompt: "Open the assigned prose editing workflow for this invocation."
 policy:
   allow_implicit_invocation: true

package/dist/assets/plugin/skills/testing-quality.md

@@ -1,28 +1,12 @@
 # Testing quality
 
-Use this reference when Root, Worker, or Reviewer evaluates a test for a
-requested change.
-
-Owner: Worker or Reviewer within the assigned test surface. Boundary: protect
-stable behavior, contracts, invariants, safety properties, compatibility
-guarantees, and meaningful failure modes. Prefer observable and typed or
-public boundaries while leaving implementation choices free.
-
-Before adding a regression or package-verification test, identify:
-
-1. the stable behavior it protects;
-2. the real regression it catches;
-3. why a less brittle boundary cannot protect it.
-
-Remove or rewrite tests that freeze incidental counts, inventories, internal
-paths, prompt or skill sizes, exact non-contract wording, irrelevant call order,
-deleted names, broad repository shape, or one implementation strategy. Avoid
-large internal snapshots and static source inspection when a behavior check
-exists. Package-verification tests should consume the shipped artifact through
-one supported outer boundary with minimal realistic setup, proving a meaningful
-artifact behavior without duplicating the suite or crawling inventories.
-
-Use proportional proof. A test that constrains more design than meaningful regression risk should not exist.
-
-Completion: each retained test names the stable behavior and regression it
-protects, and the chosen boundary is no more brittle than necessary.
+Use this reference when assessing a test for a requested change. Identify the
+stable behavior, contract, invariant, compatibility guarantee, safety property,
+or meaningful failure mode it protects; the regression it catches; and why a
+less brittle boundary cannot protect it.
+
+Do not freeze incidental counts, inventories, internal paths, prompt or skill
+wording, irrelevant call order, broad repository shape, or one implementation
+strategy. Prefer observable typed or public boundaries. Package-verification
+tests should consume the shipped artifact through one supported outer boundary
+with minimal realistic setup, proving behavior without duplicating the suite.

package/dist/assets/plugin/skills/writing-for-agents/SKILL-MECHANICS.md

@@ -1,19 +1,9 @@
 # Skill mechanics
 
-This is the skill-specific branch of [writing-for-agents](SKILL.md): frontmatter, invocation choice, and router skills.
+Use a model-invoked skill when its description names a distinct model-facing
+branch. Keep the description trigger-first and short. Keep routing and
+invocation metadata in `agents/openai.yaml`; the body owns the behavior.
 
-## Invocation
-
-A **model-invoked** skill keeps a trigger-first `description` so an agent can select it and another skill can reach its shared reference. The always-loaded pointer spends context on every turn, so use one compact trigger per real branch and remove routing prose from the body.
-
-A **user-invoked** skill sets `disable-model-invocation: true`. Its description becomes a human-facing one-line summary with trigger lists removed. Use this when only a person should select the skill.
-
-Shared reference required by user-invoked skills belongs in a plain disclosed file that each can point to.
-
-## Splitting by invocation
-
-Split a model-invoked skill only when a distinct leading word should trigger it independently or another skill must reach it. The independent route must justify its permanent context pointer.
-
-## Router skills
-
-When many user-invoked skills exceed human cognitive load, add one user-invoked router that names them and their branches. A router can guide the person; it cannot autonomously invoke skills whose model invocation is disabled.
+Put uncommon mechanics in a linked reference only when a caller needs them.
+Keep each instruction in one source of truth and avoid copying body text into
+metadata or neighboring skills.

package/dist/assets/plugin/skills/writing-for-agents/SKILL.md

@@ -1,46 +1,35 @@
 ---
 name: writing-for-agents
-description: Use when Root prepares or reviews a subagent delegation, handoff, profile, skill, prompt, or agent-facing instruction; write a low-context independent contract. Before each dispatch ensure this skill is loaded and applied; reuse it until compaction, a new context, or an incomplete/unavailable load.
+description: Use when GPT-6 Astra Root writes or reviews a GPT-5.6 Luna specialist contract.
 ---
 
 # Writing for agents
 
-Treat each instruction as an interface with one contract:
-
-- **Owner:** the role permitted to act or decide.
-- **Boundary:** the exact scope, authority, constraints, and escalation point.
-- **Completion:** the observable outcome and proof that permit the agent to stop.
-- **Return:** the result Root needs to integrate: outcome or findings, changed
-  paths, verification, unresolved risk, and any requested decision.
-
-Write an objective, scope, retained constraints, evidence, exclusions, and the
-exact missing fact or material choice that returns to the owner. The receiver
-must be able to act, prove, and stop without reconstructing intent.
-
-Before any Root subagent dispatch, ensure this skill is fully loaded and applied
-in the current context. Reuse the loaded instructions for later dispatches
-while they remain complete; reload after compaction, a new context, or an
-incomplete/unavailable load.
-
-## Information design
-
-A **context pointer** names out-of-context material and front-loads the branches that load it. Keep one trigger per genuine branch; synonyms spend permanent context without improving routing.
-
-Budget two loads:
-
-- **Context load:** always-loaded descriptions and repository rules.
-- **Cognitive load:** material a person must remember and select.
-
-Place information by immediacy: in-file steps, in-file reference, then disclosed reference. Inline what every invocation needs. Put branch-specific mechanics behind a clear pointer. Co-locate each concept with its rules and caveats; split real invocation or sequence branches when one file sprawls or later steps cause premature completion.
-
-Each step needs a clear, demanding completion criterion. Sharpen a vague bound before splitting the sequence. Use leading words with useful pretrained meaning to compress repeated concepts. Prefer positive steering; keep prohibitions for hard guardrails and pair them with the target behavior.
-
-## Pruning
-
-Keep each meaning in one source of truth. Treat code, configuration, directory layout, and `--help` as authoritative environment lookups; document only reasons, gotchas, or contracts the environment cannot reveal. Delete stale caches, irrelevant branches, sediment, and instructions that do not change model behavior.
-
-Use architectural role names: Root owns material decisions, Workers implement bounded seams, Reviewers repair their assigned findings to fixed point, and other specialists follow their literal authority. Continuations carry changed constraints, evidence, decisions, and semantic delta instead of replaying accepted context.
-
-When the document is a skill, read [SKILL-MECHANICS.md](SKILL-MECHANICS.md) for invocation and frontmatter mechanics.
-
-Completion means the instruction routes at the right branch, names authority and exclusions, prevents premature completion, supplies checkable proof, and contains no duplicated or no-op policy.
+This skill helps GPT-6 Astra Root author instructions for GPT-5.6 Luna. First
+identify Luna's effective context: the generated Luna baseline, repository
+`AGENTS.md`, the selected native Role.task, loaded skills, and relevant config
+or metadata. Do not restate a directive already visible to that receiver.
+
+Give each Assignment only the delta Luna needs:
+
+- objective and exact scope;
+- relevant context and authority;
+- unique hard constraints and exclusions;
+- acceptance criteria and required evidence;
+- the material choice or blocker that must escalate;
+- the return payload and stopping condition.
+
+Place new policy at the narrowest owner: Root/session behavior in Root
+instructions, repository conventions in `AGENTS.md`, Luna-global constraints in
+the generated baseline, task-specific behavior in Role.task, and conditional
+workflow in a skill or a disclosed reference. Keep invocation metadata as
+routing metadata.
+
+State completion before optional procedure. Use positive, literal boundaries,
+and disclose uncommon branches progressively. Let Astra infer routine safe
+defaults and use its judgment to decide what Luna actually needs; do not add
+competence scaffolding, generic recipes, or a broad questionnaire.
+
+When a contract is complete, it is independently actionable for Luna, contains
+no same-receiver semantic duplicate, and identifies the evidence that lets Root
+integrate the result.