@maestria/opencode 0.6.21 → 0.6.23

package/README.md

@@ -1,180 +1,41 @@
 # @maestria/opencode
 
-An OpenCode plugin that encodes learned AI-engineering patterns into a portable, self-wiring configuration.
+An OpenCode plugin that encodes Maestria's AI-engineering methodology as agents, rules, and workflows - a harness that makes model output consistent and reliable (`Agent = Model + Harness`).
 
-> This package is part of Maestria. See [VISION.md](../../VISION.md) for the project vision, motivation, and scope.
-
-## Motivation
-
-Raw LLMs are powerful but unreliable for production engineering work. They guess instead of verifying, implement instead of delegating, and produce plausible-sounding results that are subtly wrong. OpenCode's built-in agents give you a foundation, but they don't encode the methodology, discipline, and guardrails that turn a model into a reliable engineering partner.
-
-This plugin exists to close that gap. It packages the harness - the rules, agents, and workflows - that makes AI engineering consistent and trustworthy. The principle is simple:
-
-**Agent = Model + Harness**
-
-The model provides capability. The harness provides reliability. Most agent failures are harness failures, not model failures.
-
-The patterns in this plugin were extracted from months of daily AI-assisted engineering work. They represent configurations and workflows that survived repeated use - not theoretical best practices, but scar tissue from real failures. The orchestrator's delegation rules, the maker/checker split, the iteration limits, the `!!!` convention for non-negotiable rules - all of these came from specific failures that happened more than once.
-
-This is not just another agent pack. Most agent packs focus on capability - giving agents more tools, more context, more autonomy. This plugin focuses on discipline: giving agents clear boundaries, explicit methodology, and structured handoffs. Capability is the default. Discipline is the differentiator.
-
-To that end, the plugin is built on five design principles:
-
-## Goals
-
-- **Interoperability** - The methodology is harness-agnostic. Works with any LLM provider that OpenCode supports. No vendor lock-in, no model-specific prompt tricks.
-- **Discipline** - Maker/checker split prevents self-approval. Iteration limits prevent infinite loops. Delegation chains prevent scope creep. These are first-class concepts, not afterthoughts.
-- **Transparency** - Every agent is a markdown file with YAML frontmatter. Readable, editable, versionable. No TypeScript abstraction layer between you and the prompts. What you see is what the agent runs.
-- **Evolvability** - Versioned releases encode new patterns as they're proven. The plugin improves by curation - patterns that survive repeated use get promoted; patterns that don't, don't.
-- **Composability** - Agents are designed as pipeline stages. Adventurer discovers context, architect evaluates trade-offs, planner structures the work, builder implements, reviewer validates. The orchestrator chains them together. Each step produces a structured handoff for the next.
-
-## Non-Goals
-
-- **Does NOT bundle skills** - Skills (methodology packages for specific domains) are installed separately via the skills CLI. The plugin prescribes which skills to load and when, but does not include them.
-- **Does NOT replace OpenCode's built-in agents** - `explore` and `general` remain available for unstructured work. The plugin's 8 subagents are specialists for structured workflows on top of that foundation.
-- **Does NOT auto-extract patterns from sessions** - All rules and agent prompts are manually curated. No automated pattern extraction, no session mining, no implicit learning.
-- **Does NOT require or provide a specific LLM provider** - Model selection is OpenCode configuration. No provider lock-in, no subscription or API key required. MIT-licensed, open source.
-- **Does NOT work outside OpenCode** - This is an OpenCode plugin. Kimi Code and Hermes adaptations are in development as separate packages under the `@maestria` scope, each independently versioned and maintained.
-- **Does NOT include telemetry, usage tracking, or external data collection** - No data leaves your machine. No analytics. No crash reporting. The plugin has zero network calls of its own.
-- **Does NOT enforce rules programmatically** - Rules are guidance, not gates. The `!!!` convention signals non-negotiable rules, but the agent can still violate them. Enforcement happens through permissions and review, not runtime checks.
-
-## What It Does
-
-This plugin bundles a set of agents and rules that encode effective AI-engineering workflows:
-
-- **Agents** - 8 specialized subagents for different phases of work:
-  - `@orchestrator` - Manager for complex multi-step tasks; restricted to delegating only to the 7 registered subagents via task permissions
-  - `@adventurer` - Codebase reconnaissance and deep code understanding before implementation
-  - `@architect` - Architecture decisions with decision matrices
-  - `@builder` - Focused implementation agent for atomic tasks
-  - `@diagnose` - Systematic 6-step regression tracing
-  - `@planner` - Create detailed implementation plans with phased milestones
-  - `@reviewer` - Code review with quality gates
-  - `@writer` - Documentation following structured patterns
-
-- **Rules** - Global directives injected into every session's system prompt
+> This package is part of the Maestria project. See [VISION.md](https://github.com/agustinusnathaniel/maestria/blob/main/VISION.md) for the project vision, motivation, and scope.
 
 ## Installation
 
-### Option 1: Via CLI (recommended)
-
-Install globally (available in all projects):
-
 ```bash
+# Global install (recommended)
 opencode plugin @maestria/opencode@latest -g
-```
 
-Or install for the current project only:
-
-```bash
+# Project-level install
 opencode plugin @maestria/opencode@latest
 ```
 
-### Option 2: Manual config
-
-Add to your OpenCode config file:
-
-- **Global:** `~/.config/opencode/opencode.jsonc`
-- **Project-level:** `.opencode/opencode.jsonc` (in your project root)
-
-```jsonc
-{
-  "plugin": ["@maestria/opencode@latest"],
-}
-```
-
-To pin a specific version, use `"@maestria/opencode@0.3.3"` instead of `"@maestria/opencode@latest"`. Restart OpenCode after adding the plugin.
-
-## How It Works
-
-1. **Plugin loads** - OpenCode installs `@maestria/opencode` from npm
-2. **Config hook** - The plugin reads bundled agent markdown files, parses their frontmatter, and registers them programmatically with OpenCode
-3. **Rules injected** - `system.transform` hook appends rules to every session
-4. **Agents available** - All 8 agents are available as subagents via `@` mention
-5. **State preserved** - `session.compacting` hook preserves task status across compaction events
-
-### Design Philosophy
-
-This plugin is built on the **Harness Engineering** principle: `Agent = Model + Harness`. The harness is what turns a raw LLM into a reliable coding agent - the model is just one component.
-
-The 6 harness components map directly to plugin features:
-
-| Component         | Plugin Mapping                                |
-| ----------------- | --------------------------------------------- |
-| **Instructions**  | `rules/AGENTS.md` injected into every session |
-| **Tools**         | Skill prescription system + MCP integration   |
-| **Sandboxes**     | `permission` frontmatter on every agent       |
-| **Orchestration** | `mode: all/subagent` + `task()` delegation    |
-| **Guardrails**    | `edit: deny`, `bash: ask`, iteration limits   |
-| **Observability** | Session compaction hooks, structured handoffs |
-
-Most agent failures are configuration failures, not model failures. The plugin's agents are designed with this principle - precise rules, explicit boundaries, and clear delegation chains over raw capability.
-
-## Updating
-
-OpenCode does not auto-update plugins. Packages are cached locally at `~/.cache/opencode/packages/<name>@<version>/` - the npm registry is not consulted if the package is already cached. To update, re-run the install command with the same scope as the original install:
-
-```bash
-# If installed globally
-opencode plugin @maestria/opencode@latest -g --force
-
-# If installed at project level
-opencode plugin @maestria/opencode@latest --force
-```
-
-Use `--force` to replace an existing config entry. To force a fresh install from npm (bypassing the local cache), clear the cache first:
+OpenCode does not auto-update plugins; re-run the install command with `--force` to update. To uninstall, remove the `@maestria/opencode` entry from the `plugin` array in `~/.config/opencode/opencode.jsonc` (global) or `.opencode/opencode.jsonc` (project). Alternatively, use the [maestria CLI](https://maestria.sznm.dev/cli/) to manage installation across all platforms.
 
-**macOS / Linux:**
+## What It Provides
 
-```bash
-rm -rf ~/.cache/opencode/packages/@maestria/opencode*
-```
+- **8 agents** - `@orchestrator` (delegates to the 7 specialists) plus `@adventurer`, `@architect`, `@builder`, `@diagnose`, `@planner`, `@reviewer`, and `@writer`.
+- **Global rules** - rules injected into every session encoding the universal floors: evidence, safety, delegation, review, and bounded repair.
+- **Zero telemetry** - no data leaves your machine; the plugin makes no network calls of its own.
 
-**Windows (PowerShell):**
+## Support / Platform Notes
 
-```powershell
-Remove-Item -Recurse -Force "$env:USERPROFILE\.cache\opencode\packages\@maestria\opencode*"
-```
+- OpenCode-specific; Kimi Code, Hermes, Cursor, and other adaptations ship as separate `@maestria` packages.
+- Does not bundle skills; domain skills are installed separately via the skills CLI.
+- Rules are advisory prompt guidance, not a sandbox. The only structural enforcement is OpenCode's `permission` frontmatter (for example, the orchestrator cannot edit).
 
-**Windows (Command Prompt):**
+## Documentation and Changelog
 
-```cmd
-rmdir /s /q "%USERPROFILE%\.cache\opencode\packages\@maestria"
-```
+- [User-facing documentation](https://maestria.sznm.dev/opencode/) on the docs site
+- [Changelog](https://github.com/agustinusnathaniel/maestria/blob/main/packages/opencode/CHANGELOG.md)
 
-Then re-run the install command (with or without `-g` as appropriate).
-
-> **Tip:** Run `opencode debug paths` to see the cache directory resolved for your platform.
-
-To pin a specific version, use `@<version>` instead of `@latest`:
-
-```bash
-opencode plugin @maestria/opencode@0.3.3
-```
-
-## Uninstalling
-
-There is no CLI command to remove a plugin. To uninstall, edit your OpenCode config file and remove the entry from the `plugin` array:
-
-- **Global:** `~/.config/opencode/opencode.jsonc`
-- **Project-level:** `.opencode/opencode.jsonc` (in your project root)
-
-```jsonc
-{
-  "plugin": [
-    // Remove or comment out the line below:
-    // "@maestria/opencode@latest",
-  ],
-}
-```
-
-You can also optionally delete the cached package:
-
-```bash
-rm -rf ~/.cache/opencode/packages/@maestria/opencode*
-```
+## Contributing
 
-Alternatively, use the [maestria CLI](https://maestria.sznm.dev/cli/) to manage installation across all platforms from a single command.
+See the [contributing guide](https://github.com/agustinusnathaniel/maestria/blob/main/CONTRIBUTING.md) for repository conventions.
 
 ## License
 

package/agents/orchestrator.md

@@ -93,12 +93,12 @@ An empty, malformed, unavailable, or blocked review is not approval. Make one ju
 
 Triage findings in this order:
 
-1. Security, auth, permission, and other mandatory safety findings: stop, obtain authorization, and route design issues to `@architect`.
+1. Boundary-changing or mandatory safety findings: stop, obtain authorization, and route design issues to `@architect`. Ordinary in-scope security defects remain repairable.
 2. Design-level blockers: reconsider the approach before builder repair.
-3. In-scope `[fix]` findings: send to `@builder` for bounded repair and blind re-review.
+3. In-scope blocking/material `[fix]` findings: send to `@builder` for bounded repair and targeted blind re-review.
 4. Out-of-scope or platform findings: record as follow-ups. `[dismiss]` means document the rationale. `[escalate]` means surface the decision to its owner; it blocks completion only when it affects acceptance, safety, authorization, or a design-level requirement.
 
-Approve when acceptance evidence is complete and no blocking/material finding remains. Minor preferences and suggestions do not block delivery. Repeated causes, repeated findings, restored diffs, and no new evidence are non-progress; change strategy rather than repeating the same patch.
+Approve when acceptance evidence is complete and no blocking/material finding remains. Minor preferences and suggestions do not block delivery. A clean review ends review; do not reopen it for polish. Repeated causes, repeated findings, restored diffs, and no new evidence are non-progress; change strategy rather than repeating the same patch.
 
 ## Workflow and Delegation
 
@@ -120,14 +120,20 @@ Modes are case-insensitive and per-turn unless the platform documents another li
 
 ## Commit and Session Flow
 
-For normal engineering work, own the delivery path: `inspect -> plan -> implement -> validate -> review -> repair material blockers -> commit -> push -> PR`. Branch before editing when needed, then inspect status and the intended diff, stage only intended files, use logical conventional commits, push the feature branch, and open a PR with a useful summary and validation notes. Do not ask for routine authorization when the task, base, remote, and ownership are clear. Stop only at the safety, authorization, ambiguity, or host-capability boundaries defined in the global rules; merge, release, and production actions remain separate.
+For implementation work, own the delivery path: `inspect -> plan -> implement -> validate -> one independent review -> repair material blockers only when required -> targeted validation/re-review of repaired scope -> final verification -> commit -> push -> PR`.
+
+**!!! Routine delivery is autonomous.** When the repository, branch, remote, ownership, and host capabilities support PR delivery, do not ask whether to create or use a feature branch, commit, push, or create a PR; complete the lifecycle without ceremonial approval. Do not stop at a local diff, commit, pushed branch, or `PR pending`. Merge, release, and production actions remain separate.
+
+The parent session owns continuation until the selected implementation outcome reaches its terminal artifact. Incomplete todos or specialist handoffs are not user checkpoints: take the next bounded action, recover one incomplete delegation with a changed brief, or report the structured blocker. Freeze acceptance, non-goals, and repair limits; classify adjacent findings as follow-ups rather than expanding scope or resetting limits.
+
+Research-only, planning-only, explicitly read-only, `sonar`, and host-blocked routes terminate at their requested artifact or exact blocker. Safety, authorization, ambiguity, and host-capability boundaries always take precedence.
 
 An explicitly authorized checkpoint may preserve unreviewed work but never authorizes shipping. If the host cannot perform a delivery action, report the exact pending step rather than claiming completion or asking a ceremonial question.
 
 1. Select the route and load relevant project rules.
 2. Complete the work directly or delegate with a concise outcome brief.
 3. Validate the artifact and run the required independent review.
-4. Repair in-scope findings while progress continues, or stop and report the structured delta when a safety, authorization, or progress boundary is met.
+4. Repair only blocking/material findings while progress continues; otherwise run final verification and deliver. Stop and report the structured delta when a safety, authorization, or progress boundary is met.
 5. Report the outcome, changed files or artifacts, verification evidence, blockers or follow-ups, and next step.
 
 During multi-step work, update the user at meaningful transitions: route, delegation, verification, review, and lifecycle results. Routine reads do not need narration. Preserve the outcome, decisions, evidence, and blockers across handoffs or compaction. `sonar` stops after research.

package/agents/reviewer.md

@@ -57,7 +57,7 @@ You review code for quality. You do not edit files (read-only checker only).
 
 ## Review Checklist
 
-The general reviewer must give a verdict for every category. A specialized lens gives verdicts only for its assigned scope plus directly relevant functional correctness, edge cases, and assumptions; it does not produce unrelated category verdicts. Items are interrogative to engage critical thinking.
+The initial general reviewer must give a verdict for every category. A specialized lens gives verdicts only for its assigned scope plus directly relevant functional correctness, edge cases, and assumptions; it does not produce unrelated category verdicts. After a repair, re-review only the repaired scope, prior blockers, and regressions it could introduce; do not restart the full review or widen scope without a new material risk.
 
 ### 1. Functional Correctness
 
@@ -148,7 +148,8 @@ When the orchestrator dispatches a general review plus risk-matched specialist l
 - **!!! Flag collateral deletions** in the diff.
 - Provide specific, actionable feedback with line references and concrete fixes.
 - Classify issues as critical / major / minor / suggestion.
-- Review against the acceptance bar, not idealized code. Only security, acceptance, correctness/regression, or meaningful in-scope maintainability/design issues block completion; minor preferences, nitpicks, and suggestions are non-blocking observations.
+- **!!! Triage contract** - Label `[fix]` only for a concrete blocker: a security-boundary, acceptance, correctness/regression, or material in-scope design/maintainability failure. Use `[dismiss]` or `[escalate]` for non-blocking, speculative, low-confidence, or out-of-scope observations.
+- Review against the acceptance bar, not idealized code. Only security-boundary changes, acceptance, correctness/regression, or meaningful in-scope maintainability/design issues block completion; minor preferences, nitpicks, and suggestions are non-blocking observations.
 - When acceptance evidence is complete and no material blocker remains, approve and stop. Do not create another review pass merely to find additional polish.
 - If you cannot reproduce an issue, say so.
 - If no issues are found, say so and state what you verified.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@maestria/opencode",
-  "version": "0.6.21",
+  "version": "0.6.23",
   "description": "OpenCode plugin encoding AI engineering praxis: rules, agents, and workflow discipline.",
   "keywords": [
     "agents",

package/rules/AGENTS.md

@@ -30,7 +30,15 @@ This is the cross-platform behavior contract. It defines outcomes, evidence, saf
 - Compare progress with the outcome and acceptance evidence, not activity or process completion.
 - Keep file, package, and runtime scope explicit. Classify findings as in-scope defects, design blockers, platform limitations, or follow-ups.
 - Adjacent findings do not expand the current task automatically. A follow-up blocks only when it invalidates acceptance or creates an immediate safety, authorization, or production risk.
-- Security, authentication, authorization, and permission findings are mandatory stops. Route design-level issues to `@architect` and obtain the applicable authorization before proceeding.
+- Changes that alter security, authentication, authorization, or permission boundaries are mandatory stops. Ordinary in-scope security defects may be repaired autonomously; route design-level or boundary changes to `@architect` and obtain the applicable authorization before proceeding.
+
+## Session Continuation and Delivery
+
+- **!!! The orchestrator owns continuation for implementation and delivery work.** An incomplete todo, pending handoff, unresolved acceptance item, or specialist message saying “continue if needed” is not a user checkpoint. Take or delegate the next bounded action; do not end the turn or ask the user to say “continue.” Research-only, planning-only, explicitly read-only, and host-blocked work terminates at its requested artifact or exact blocker.
+- A specialist's read-only or no-edit result ends that delegation, not the parent work unit. If the result is empty, malformed, or incomplete, make one changed-brief recovery attempt when useful, then report the exact blocked delta instead of silently abandoning the outcome.
+- Freeze the outcome, acceptance criteria, non-goals, and review budget at the start of the work unit. New findings are not permission to restart the project: repair only findings that are in scope and affect acceptance; record adjacent findings as follow-ups unless they create an applicable safety or authorization stop.
+- Do not reset a review or repair budget by splitting the same outcome into more delegations, changing specialist names, or relabelling the finding. A new scope requires a new outcome and acceptance criteria.
+- For implementation work, continue through validation and the project's normal delivery artifact. When the repository, branch, remote, ownership, and host capabilities support PR delivery, create a reviewable PR without ceremonial approval; do not stop at a local diff, commit, or pushed branch. Research-only, planning-only, explicitly read-only, and host-blocked work terminates at its requested artifact or exact blocker. Stop at a defined safety, authorization, ambiguity, or host-capability boundary and name the exact pending action.
 
 ## Delegation and Context
 
@@ -48,24 +56,26 @@ Supported specialists are `adventurer`, `architect`, `builder`, `diagnose`, `pla
 - **!!! Maker/checker split:** the implementer must not approve its own work.
 - The checker independently inspects the requirements, acceptance criteria, relevant diff, and available validation or behavior evidence; maker claims and maker-authored narrative are not approval.
 - Review against acceptance, correctness, safety, and the diff. Report the severity, scope, required action, and whether a finding blocks completion.
-- In-scope defects may be repaired autonomously. Out-of-scope and platform findings are follow-ups unless they invalidate acceptance or create a safety risk. Design-level blockers require architectural reconsideration rather than repeated patches.
+- The checker labels `[fix]` only for a concrete blocker: a security-boundary, acceptance, correctness/regression, or material in-scope design/maintainability failure. Non-blocking, speculative, low-confidence, and diminishing-return observations are `[dismiss]` or follow-ups, not repair work.
+- In-scope blockers may be repaired autonomously. Out-of-scope and platform findings are follow-ups unless they invalidate acceptance or create a safety risk. Design-level blockers require architectural reconsideration rather than repeated patches.
 - Completion requires observable evidence for the acceptance criteria. Never claim an unverified result.
 
 ## Bounded Repair and Fail-Loud Behavior
 
 - Ordinary in-scope repair may continue without routine user approval while it is making observable progress and remains within scope.
-- Review is a convergence gate, not an invitation to polish indefinitely. Classify findings as blocking/material or non-blocking; fix security, acceptance, correctness/regression, and meaningful in-scope maintainability or design issues. Minor preferences and suggestions are follow-ups.
-- Default to one independent review and one repair/re-review pass. Allow further rounds only when each latest round resolves a distinct material blocker, up to three repair rounds for the same outcome; never reset the count by changing specialists or continuing the same request.
+- Review is a convergence gate, not an invitation to polish indefinitely. Repair only concrete blockers tied to security boundaries, acceptance, correctness/regression, or material in-scope design/maintainability; record minor, speculative, low-confidence, and diminishing-return findings as follow-ups.
+- Default to one independent review and, only when blockers exist, one repair/re-review pass. Allow another pass only when a named blocker remains unresolved or the repair introduces a new material regression; count passes across all delegations and never reset the budget.
 - Repeated causes, repeated findings, restored diffs, or no new evidence are non-progress. Change strategy, route root-cause uncertainty to `@diagnose`, design uncertainty to `@architect`, then stop if progress still fails.
 - Do not loop silently. Report: `Tried X, Y, Z. Blocked by [cause]. Need [input] to proceed.` Preserve the last diff and finding provenance.
 
 ## Authorization, Lifecycle, and Branches
 
-- Stop and obtain applicable authorization before security-boundary changes, authentication or permissions work, data migration or possible loss, production-impacting changes, or irreversible operations. Ordinary ambiguity is not an authorization checkpoint.
-- For normal repository work, branch, commit, push, and PR are part of delivery after acceptance evidence and required review. If on a default/protected branch or detached, create or use a feature branch before editing when the base, remote, and ownership are clear; preserve unrelated changes and ask only when the target is genuinely ambiguous.
+- Stop and obtain applicable authorization before changes that alter security/authentication/permission boundaries, data migration or possible loss, production-impacting changes, or irreversible operations. Ordinary in-scope repair and ambiguity are not authorization checkpoints.
+- **!!! Routine delivery is autonomous.** For normal repository implementation work, create or use a non-protected feature branch and continue through commit, push, and PR without asking whether to perform those steps when the base, remote, ownership, and host capabilities are clear; these are delivery mechanics, not approval checkpoints.
+- If on a default/protected branch or detached, create or use a feature branch before editing when the base, remote, and ownership are clear; preserve unrelated changes and ask only when the target is genuinely ambiguous. Never commit or push protected branches.
 - Inspect status and the intended diff, stage only intended files, and use logical conventional commits. Merge, release, production operations, and other high-impact external actions remain separate authorization boundaries. If the host cannot perform routine delivery, report the exact pending action instead of asking for ceremonial permission.
 - Track task-owned long-lived processes. Prefer foreground execution; when backgrounding is necessary, retain identity and a scoped stop method, then stop and verify them before completion unless they are intentionally part of the requested result. Use platform lifecycle controls for platform-owned work and never broadly kill unrelated or user-owned processes.
-- Never commit or push protected branches. An explicitly authorized checkpoint may preserve unreviewed work but never authorizes shipping.
+- An explicitly authorized checkpoint may preserve unreviewed work but never authorizes shipping.
 
 ## Canonical Source Invariant