holycodex 0.16.1 → 0.16.2-dev.61.1

package/README.md

@@ -1,31 +1,24 @@
 # HolyCodex CLI
 
-## What?
-
-The published `holycodex` package installs and removes HolyCodex through
-Codex's native plugin management. It also records the selected route plan,
-service tier, and optional capability selections in the owned configuration.
-
-## Why?
-
-Native Codex plugin management owns installed assets and native subagent
-execution. The CLI is a small, typed configuration boundary around that
-platform surface.
-
-## How?
+The `holycodex` package is the public command-line entry point for installing,
+inspecting, and removing HolyCodex through Codex's native plugin management.
 
 ```sh
 bunx holycodex install
+bunx holycodex doctor
 bunx holycodex remove
 ```
 
-`--plan` selects routing only. `--tier` is independent and controls service
-handling without changing routes or authority. Optional selections are
-`--work`, `--frontend`, `--security`, and `--computer-use`; explicit
-selections and additional plugins fail closed when unavailable. Omitted
-Frontend and Security defaults may be recorded as missing or uncertain on a
-first install and retried on reinstall. `--json` emits one machine-readable
-result.
+Use `--yes` when no interactive terminal is available. `--plan` selects native
+Root and specialist routing only. `--tier` independently selects service
+handling (`standard`, `fast`, or `fast-all`). The canonical plans are `go`,
+`plus-low`, `plus`, `plus-high`, `pro-5x`, and `pro-20x`.
+
+Frontend and Security are selected by default; Work and Computer Use are
+opt-in. Selected capabilities must install and verify or installation fails.
+Use `--json` for one validated machine-readable envelope. Human output reports
+the version, plan, tier, selected capabilities, and actionable warnings without
+printing the internal installation record.
 
 The development entry point is:
 
@@ -38,7 +31,9 @@ Command syntax and response contracts are owned by [CLI.md](../../docs/CLI.md).
 ## Contribute
 
 Use Bun through `mise`, keep changes within the assigned package seam, and run
-the relevant validation before handoff.
+the relevant local validation before handoff. Never place environment secrets
+or raw environment values in tracked files, package output, logs, CI artifacts,
+or uploads.
 
 ## License
 

package/dist/assets/plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "holycodex",
-  "version": "0.16.1",
+  "version": "0.16.2",
   "description": "Root-directed capabilities and deterministic installed assets for HolyCodex.",
   "author": {
     "name": "David Basile Filho",

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

@@ -4,8 +4,8 @@ description: Use once after code or manifest implementation when Root needs adve
 ---
 
 Use this skill once after implementation or manifest work. Inspect the actual
-result to a fixed point before Root judges readiness. Apply [testing quality](../testing-quality.md)
-when judging new or modified tests.
+integrated result to a fixed point before Root judges readiness. Apply
+[testing quality](../testing-quality.md) when judging new or modified tests.
 
 Owner: Reviewer. Boundary: inspect the assigned diff, callers, contracts,
 tests, compatibility, and artifact. Repair only reviewer-owned defects inside
@@ -13,9 +13,11 @@ scope, verify each repair, and repeat until no assigned defect remains. Root
 retains architecture, product, scope, trust, interface, external-state, and
 final readiness decisions.
 
-Use the existing implementation before adding code, prefer standard-library
-or native behavior, trace callers before judging a shared root cause, and
-flag speculative abstractions or oversized diffs.
+Use existing code and project conventions before adding code; prefer
+standard-library or native behavior; trace callers before judging a shared root
+cause; and flag speculative abstractions, pointless file splits, oversized or
+unmergeable diffs, unclear dependency direction, and unnecessary tests.
+Check that temporary/generated output is absent and Git/VCS remains Root-only.
 
 Completion: no reviewer-owned defect remains, verification evidence is
 recorded, and every residual risk or Root decision is explicit.

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

@@ -1,11 +1,16 @@
 ---
 name: commit
-description: Use when Root assigns a local commit after the exact scope is settled; verify scope, commit it, and report identity.
+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: Worker. Boundary: verify status and commit only the assigned local
-scope. Preserve unrelated work; remote version-control mutation remains
-approval-gated.
+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.
 
-Completion: the commit identity and post-commit status are reported, or an
-exact reproducible blocker is returned.
+Completion: Root reports the commit identity and post-commit status with
+redacted evidence, or returns an exact reproducible blocker. Never print secret
+values.

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 assigns a local commit, verify the exact scope, create only that commit, and report identity and status."
+  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."
 policy:
   allow_implicit_invocation: false

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

@@ -11,6 +11,12 @@ 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.

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

@@ -7,12 +7,24 @@ Implement only the assigned seam. Inspect required callers and tests, preserve
 typed boundaries and portability, edit only approved files, and make one
 bounded clarity pass.
 
-Reuse existing code, prefer standard-library or native behavior, trace every
-caller before repairing a shared root cause, and keep the diff minimal and
-bounded. Do not add speculative abstractions.
+Prefer existing project conventions and standard-library or native behavior.
+Trace every caller before repairing a shared root cause. Reuse an existing
+boundary when it has real callers or clear near-term value; do not add
+speculative abstractions or split a cohesive file without a concrete benefit.
+Keep the smallest correct, independently mergeable diff with deliberate error
+handling and sensible dependency direction. Git/VCS work remains Root-only.
+
+Before checking a change, discover the repository's own formatter, linter,
+typecheck, and validation commands from its package scripts, task config, and
+contributor guidance. Run the smallest relevant local command first, then
+broaden only when the changed boundary or release gate requires it; report
+which commands were unavailable instead of inventing replacements.
 
 When implementation changes tests, apply [testing quality](../testing-quality.md)
-before adding or retaining them. Escalate material choices.
+before adding or retaining them: protect a meaningful stable behavior at the
+least brittle observable boundary, and avoid tests for implementation detail.
+Remove temporary or incidental generated output before handoff. Escalate
+material choices.
 
 Owner: Worker. Boundary: preserve repository-native ownership, dependency
 direction, trust checks, and acceptance behavior; do not broaden scope or

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

@@ -3,12 +3,21 @@ name: refactor
 description: Use when Root has decided one seam needs restructuring; preserve behavior, ownership, and interfaces.
 ---
 
-Reuse existing code and prefer standard-library or native behavior. Trace
-callers before changing a shared root cause, keep the diff minimal and
-bounded, and avoid speculative abstractions.
+Prefer existing project conventions and standard-library or native behavior.
+Trace callers before changing a shared root cause. Reuse an existing boundary
+when it has real callers or clear near-term value; avoid speculative
+abstractions and splitting a cohesive file without a concrete benefit. Keep
+the smallest correct, independently mergeable diff with coherent dependency
+direction. Git/VCS work remains Root-only.
+
+Discover the repository-specific formatter, linter, typecheck, and validation
+commands from its package scripts, task config, and contributor guidance. Run
+the smallest relevant local proof first and broaden only when the changed
+boundary or release gate requires it; do not invent unavailable commands.
 
 Owner: Worker. Boundary: change only the assigned seam; preserve ownership,
 dependency direction, public behavior, and interfaces.
 
-Completion: changed files are inspected and behavior-locked checks are clean,
-with any residual risk or blocker explicit.
+Completion: changed files are inspected, focused behavior-locked checks are
+clean, temporary/generated output is removed, and any residual risk or blocker
+is explicit.

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

@@ -8,15 +8,19 @@ 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 smoke test, identify:
+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.
-
-A smoke test consumes the shipped artifact through one supported outer boundary with minimal realistic setup. It answers whether the artifact can start and perform its smallest supported job. It does not duplicate the suite, reproduce packaging logic, crawl file inventories, or accumulate historical implementation assertions.
+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.
 

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

@@ -1,6 +1,6 @@
 ---
 name: writing-for-agents
-description: Use when authoring or reviewing prompts, skills, profiles, delegations, handoffs, or agent-facing repository instructions; make them independently actionable with low context load.
+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.
 ---
 
 # Writing for agents
@@ -13,6 +13,11 @@ Treat each instruction as an interface with one contract:
 
 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.

package/dist/assets/plugin/skills/writing-for-agents/agents/openai.yaml

@@ -1,6 +1,6 @@
 interface:
   display_name: "Writing for agents"
   short_description: "Design compact, independently actionable agent instructions."
-  default_prompt: "When Root assigns agent-instruction work, write or review steering with clear behavior, reason, authority, evidence, escalation, and completion."
+  default_prompt: "When Root prepares a delegation or agent-facing instruction, ensure this skill is loaded and applied in the current context, then write or review a compact contract with behavior, authority, evidence, escalation, and completion."
 policy:
   allow_implicit_invocation: true