@fro.bot/systematic 3.1.0 → 3.2.1

package/HARNESSES.md

@@ -2,19 +2,19 @@
 
 This is the evidence registry for Systematic's harness-portability work. **Every tool or mechanism named here is backed by an in-repo path with line numbers, installed or cloned source, or an authoritative URL.** If the supplied research did not verify a capability, it is explicitly marked **UNVERIFIED**; absence of evidence is not evidence of absence.
 
-**Tiers.** Tier 1 means Systematic ships a controlled adapter: OpenCode and Pi. Tier 2 means the harness is documented for portability but has no Systematic adapter: Claude Code, Codex CLI, Gemini CLI, and GitHub Copilot.
+**Tiers.** Tier 1 means Systematic ships a controlled adapter: OpenCode, Pi, and Claude Code. Tier 2 means the harness is documented for portability but has no Systematic adapter: Codex CLI, Gemini CLI, and GitHub Copilot.
 
 ## Capability matrix
 
-The four capability rows use the vocabulary in the [OpenCode profile](skills/using-systematic/references/opencode-profile.md#L3-L8) and [Pi profile](skills/using-systematic/references/pi-profile.md#L3-L8).
+The four capability rows use the vocabulary in the [OpenCode profile](skills/using-systematic/references/opencode-profile.md#L3-L8), [Pi profile](skills/using-systematic/references/pi-profile.md#L3-L8), and [Claude Code profile](skills/using-systematic/references/claude-code-profile.md#L5-L10).
 
-| Capability | OpenCode (Tier 1) | Pi (Tier 1) | Claude Code (Tier 2) | Codex CLI (Tier 2) | Gemini CLI (Tier 2) | GitHub Copilot (Tier 2) |
+| Capability | OpenCode (Tier 1) | Pi (Tier 1) | Claude Code (Tier 1) | Codex CLI (Tier 2) | Gemini CLI (Tier 2) | GitHub Copilot (Tier 2) |
 |---|---|---|---|---|---|---|
-| Subagent delegation | `task`, including `subagent_type`, resume, and background execution [OC-1] | `systematic_delegate({agent, task})`; sequential, capped at 20 turns [PI-1] | `context: fork` for skills; `subagent_type` is **UNVERIFIED** [CC-1] | **UNVERIFIED** [U] | **UNVERIFIED** [U] | Built-in/custom agents [GH-1][GH-2] |
+| Subagent delegation | `task`, including `subagent_type`, resume, and background execution [OC-1] | `systematic_delegate({agent, task})`; sequential, capped at 20 turns [PI-1] | Name-based subagent dispatch (invoke a subagent by name in the prompt text); `context: fork` for skill-scoped forks; plugin agents ship in `agents/` [CC-1][CC-9] | **UNVERIFIED** [U] | **UNVERIFIED** [U] | Built-in/custom agents [GH-1][GH-2] |
 | Blocking user interaction | `question` [OC-2] | No native blocking tool; numbered-chat fallback [PI-2] | `AskUserQuestion` [CC-2] | `request_user_input`; blocking and root-thread-only [CX-1][CX-2] | `ask_user`; pauses until answers [GE-1][GE-2] | No dedicated tool name verified; plan-mode clarification and `--no-ask-user` are documented [GH-3][GH-4] |
 | Task tracking | `todowrite` [OC-3] | No native mechanism; visible list fallback [PI-2] | `TodoWrite` is deprecated/disabled by default; `TaskCreate`/`TaskGet`/`TaskList`/`TaskUpdate` replace it [CC-3][CC-4] | **UNVERIFIED** [U] | **UNVERIFIED** [U] | No `TodoWrite` equivalent verified; cloud-agent tasks/sessions API is documented [GH-5] |
-| Skill loading | Skills become commands and `systematic_skill` is registered [OC-4][OC-5] | `systematic_skill` adapter and Pi-native activation [PI-3][PI-4] | Skill tool, `SKILL.md`, and `.claude/skills/` [CC-5][CC-6] | **UNVERIFIED** [U] | **UNVERIFIED** [U] | `SKILL.md` skills [GH-6] |
-| Skills-file support | `SKILL.md` is loaded by the Systematic skill path [OC-4] | `pi.skills` ships `./skills`, including `SKILL.md` discovery [PI-4][PI-5] | `SKILL.md` and `.claude/skills/` [CC-5][CC-6] | **UNVERIFIED** [U] | **UNVERIFIED** [U] | `SKILL.md` [GH-6] |
+| Skill loading | Skills become commands and `systematic_skill` is registered [OC-4][OC-5] | `systematic_skill` adapter and Pi-native activation [PI-3][PI-4] | Native Skill tool with `SKILL.md` discovery (`~/.claude/skills/`, `.claude/skills/`, plugin `skills/`); Systematic ships no `systematic_skill` tool on Claude Code [CC-5][CC-6][CC-9] | **UNVERIFIED** [U] | **UNVERIFIED** [U] | `SKILL.md` skills [GH-6] |
+| Skills-file support | `SKILL.md` is loaded by the Systematic skill path [OC-4] | `pi.skills` ships `./skills`, including `SKILL.md` discovery [PI-4][PI-5] | `SKILL.md` and `.claude/skills/`; the plugin bundle is built and identifier-translated in CI from `skills/`, never committed [CC-5][CC-6][CC-9] | **UNVERIFIED** [U] | **UNVERIFIED** [U] | `SKILL.md` [GH-6] |
 
 `[U]` means the capability was not checked in the supplied research pack. It is not a claim that the capability does not exist.
 
@@ -32,9 +32,13 @@ The package manifest exposes the extension and skills at `package.json:17-23`, w
 
 Pi does not consume `disabled_skills` or Systematic's OpenCode configuration, and its skill loading has no OpenCode-style permission gate `docs/src/content/docs/guides/pi-harness.mdx:39-47` [PI-6]. Those are deliberate honesty boundaries, not implied parity.
 
-## Claude Code — Tier 2 documented portability target
+## Claude Code — Tier 1 shipped adapter
 
-Claude Code documents `AskUserQuestion` [CC-2], current task tracking through `TaskCreate`/`TaskGet`/`TaskList`/`TaskUpdate`, and the deprecated `TodoWrite` [CC-3][CC-4]. Its skill model includes the skill tool, `SKILL.md`, `~/.claude/skills/`, and `.claude/skills/` [CC-5][CC-6]. Skills may run with `context: fork`; a public-docs verification of a `subagent_type` parameter was not found, so that name remains **UNVERIFIED** [CC-1]. Systematic ships no Claude Code adapter or profile.
+Claude Code's profile records name-based subagent dispatch, `AskUserQuestion`, task tracking through `TaskCreate`/`TaskGet`/`TaskList`/`TaskUpdate`, and native Skill/`SKILL.md` discovery [CC-P]. Systematic builds a self-contained plugin bundle in CI from `skills/` and `agents/` via `scripts/build-claude-code-plugin.ts`: it flattens agent personas, composes an output style from the using-systematic body plus the Claude Code profile, emits a declarative `SessionStart` hook, and translates every internal identifier (`ce:<name>`, `systematic:<category>:<name>`) into Claude Code's plugin-namespaced form (`systematic:<skill-dir>`, `systematic:<agent-stem>`), gated by an integrity check that fails the build on any leftover source-namespace or unresolved bare reference [CC-9]. The bundle is never committed to `main` — `claude-code/` is gitignored build staging — and CI publishes the built output to the orphan `claude-code-plugin` branch on every push to `main` [CC-11]. Users install it through the marketplace catalog checked into `main` at `.claude-plugin/marketplace.json`, which points the `systematic` plugin entry at the `claude-code-plugin` branch ref [CC-12]: `claude plugin marketplace add marcusrbrown/systematic` then `claude plugin install systematic@systematic`. The plugin has no version field; it is versioned by the source commit SHA baked into each publish commit.
+
+Delegation is name-based: a prompt invokes a subagent by name (for example, "Use the systematic-implementer subagent to …") and Claude Code resolves it against the plugin's `agents/` directory; skills may additionally run scoped subagent forks via `context: fork` [CC-1]. `AskUserQuestion` is the blocking-interaction tool [CC-2]. `TodoWrite` is deprecated and disabled by default; `TaskCreate`/`TaskGet`/`TaskList`/`TaskUpdate` are the current task-tracking tools [CC-3][CC-4]. Skills are discovered natively from `SKILL.md` under `~/.claude/skills/`, `.claude/skills/`, and the plugin's own `skills/` directory through the built-in Skill tool; Systematic registers no `systematic_skill` tool on Claude Code, unlike its OpenCode and Pi adapters [CC-5][CC-6][CC-9].
+
+Behavioral enforcement rides a plugin output style (`force-for-plugin: true`), which is the documented plugin-native channel that modifies the system prompt directly and auto-applies when the plugin is enabled. The `SessionStart` hook carries declarative session state only (a static skill/agent count and catalog) — imperative hook content is refused as prompt injection, so the hook does not attempt to inject behavioral instructions. Workflow content ships as native skills; agents ship as native subagents. Integration coverage lives in `tests/integration/claude-code.test.ts` [CC-10].
 
 ## Codex CLI — Tier 2 documented portability target
 
@@ -50,9 +54,9 @@ Copilot documents built-in agents and custom-agent invocation [GH-1][GH-2]. Its
 
 ## Similarities and differences
 
-`SKILL.md` is the clearest cross-harness convergence: it is documented for Claude Code and Copilot, consumed by OpenCode's Systematic skill path, and shipped through Systematic-on-Pi [OC-4][PI-4][CC-5][GH-6]. `AGENTS.md` is also converging as an instruction-file convention: this repository uses it (`AGENTS.md:1-7`), and Copilot documents it [GH-7][GH-8].
+`SKILL.md` is the clearest cross-harness convergence: it is documented for Claude Code and Copilot, consumed by OpenCode's Systematic skill path, and shipped through Systematic's adapters for both Pi and Claude Code [OC-4][PI-4][CC-5][CC-9][GH-6]. `AGENTS.md` is also converging as an instruction-file convention: this repository uses it (`AGENTS.md:1-7`), and Copilot documents it [GH-7][GH-8].
 
-Delegation semantics diverge materially: OpenCode supports parallel/background dispatch [OC-1], Pi's adapter is sequential-only [PI-1], Claude's `context: fork` is skill-scoped [CC-1], and the remaining Tier 2 delegation claims are **UNVERIFIED**. Blocking input likewise ranges from native tools (`question`, `request_user_input`, `ask_user`, `AskUserQuestion`) to Pi's numbered-chat fallback and Copilot's plan-mode clarification [OC-2][PI-2][CC-2][CX-1][GE-1][GH-3].
+Delegation semantics diverge materially: OpenCode supports parallel/background dispatch [OC-1], Pi's adapter is sequential-only [PI-1], Claude Code dispatches subagents by name and additionally supports skill-scoped `context: fork` [CC-1], and the remaining Tier 2 delegation claims are **UNVERIFIED**. Blocking input likewise ranges from native tools (`question`, `request_user_input`, `ask_user`, `AskUserQuestion`) to Pi's numbered-chat fallback and Copilot's plan-mode clarification [OC-2][PI-2][CC-2][CX-1][GE-1][GH-3].
 
 ## Maintenance
 
@@ -77,12 +81,17 @@ Migrated-skill discipline is enforced by the [content-integrity gate](scripts/co
 - **PI-4** — `package.json:17-23`; `tests/unit/package-exports.test.ts:42-66,241-267`.
 - **PI-5** — `tests/integration/pi.test.ts:349-388`; installed Pi source `node_modules/@earendil-works/pi-coding-agent/dist/config.js:396-398`.
 - **PI-6** — `docs/src/content/docs/guides/pi-harness.mdx:39-47`.
-- **CC-1** — [Claude Code skills](https://code.claude.com/docs/en/skills) (`context: fork`); public-docs `subagent_type` verification is **UNVERIFIED**.
+- **CC-P** — [Claude Code profile](skills/using-systematic/references/claude-code-profile.md#L5-L10).
+- **CC-1** — [Claude Code skills](https://code.claude.com/docs/en/skills) (`context: fork`); name-based subagent dispatch verified via `claude-code/agents/` and the plugin's invocation convention [CC-9].
 - **CC-2** — [Claude Code tools reference](https://code.claude.com/docs/en/tools-reference).
 - **CC-3** — [Claude Code tools reference](https://code.claude.com/docs/en/tools-reference).
 - **CC-4** — [Claude Code todo tracking](https://code.claude.com/docs/en/agent-sdk/todo-tracking.md).
 - **CC-5** — [Claude Code skills](https://code.claude.com/docs/en/skills).
 - **CC-6** — [Claude Code Agent SDK skills](https://code.claude.com/docs/en/agent-sdk/skills.md).
+- **CC-9** — `scripts/build-claude-code-plugin.ts:5-27,253-291,345-379` (builder, identifier translation, integrity gate); `.gitignore` (`claude-code/` gitignored build staging).
+- **CC-10** — `tests/integration/claude-code.test.ts`.
+- **CC-11** — `.github/workflows/main.yaml:263-338` (`publish-claude-code-plugin` job: builds, guards required artifacts, publishes to the orphan `claude-code-plugin` branch on push to `main`).
+- **CC-12** — `.claude-plugin/marketplace.json:1-18` (marketplace catalog; `systematic` plugin entry sourced from the `claude-code-plugin` branch ref).
 - **CX-1** — [Codex request_user_input definition](https://github.com/openai/codex/blob/35aaa5d9/codex-rs/tools/src/request_user_input_tool.rs).
 - **CX-2** — [Codex request_user_input handler](https://github.com/openai/codex/blob/d47b755a/codex-rs/core/src/tools/handlers/request_user_input.rs).
 - **GE-1** — [Gemini ask-user documentation](https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/ask-user.md).

package/README.md

@@ -36,7 +36,7 @@ Systematic is an [OpenCode](https://opencode.ai/) plugin — and, from v3, a [Pi
 **OpenCode plugin** — full integration (slash commands, `systematic_skill` tool, agent registration):
 
 ```json
-{ "plugins": ["@fro.bot/systematic@latest"] }
+{ "plugin": ["@fro.bot/systematic@latest"] }
 ```
 
 Add that to `~/.config/opencode/opencode.json` and restart OpenCode.

package/dist/index.js

@@ -240,7 +240,7 @@ ${profileBlock}`;
   return `<SYSTEMATIC_WORKFLOWS>
 You have access to structured engineering workflows via the Systematic plugin.
 
-**IMPORTANT: The using-systematic skill content is included below. It is ALREADY LOADED - you are currently following it. Do NOT use the systematic_skill tool to load "using-systematic" again - that would be redundant.**
+**IMPORTANT: The using-systematic skill content is included below. It is ALREADY LOADED - you are currently following it. Do not load "using-systematic" again - that would be redundant.**
 
 ${content}
 

package/dist/pi.js

@@ -3158,7 +3158,7 @@ ${profileBlock}`;
   return `<SYSTEMATIC_WORKFLOWS>
 You have access to structured engineering workflows via the Systematic plugin.
 
-**IMPORTANT: The using-systematic skill content is included below. It is ALREADY LOADED - you are currently following it. Do NOT use the systematic_skill tool to load "using-systematic" again - that would be redundant.**
+**IMPORTANT: The using-systematic skill content is included below. It is ALREADY LOADED - you are currently following it. Do not load "using-systematic" again - that would be redundant.**
 
 ${content}
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@fro.bot/systematic",
-  "version": "3.1.0",
+  "version": "3.2.1",
   "description": "Structured engineering workflows for OpenCode",
   "type": "module",
   "homepage": "https://fro.bot/systematic",
@@ -52,6 +52,7 @@
     "registry:build": "bun scripts/build-registry.ts",
     "registry:drift": "bun scripts/generate-registry.ts --check",
     "registry:validate": "bun scripts/build-registry.ts --validate-only",
+    "claude-code:build": "bun scripts/build-claude-code-plugin.ts",
     "prepublishOnly": "bun run build && bun run schema:generate"
   },
   "keywords": [
@@ -87,10 +88,10 @@
     }
   },
   "devDependencies": {
-    "@biomejs/biome": "2.5.3",
-    "@earendil-works/pi-coding-agent": "0.80.6",
-    "@opencode-ai/plugin": "1.18.0",
-    "@opencode-ai/sdk": "1.18.0",
+    "@biomejs/biome": "2.5.4",
+    "@earendil-works/pi-coding-agent": "0.80.7",
+    "@opencode-ai/plugin": "1.18.2",
+    "@opencode-ai/sdk": "1.18.2",
     "@semantic-release/exec": "7.1.0",
     "@types/bun": "latest",
     "@types/js-yaml": "4.0.9",
@@ -110,6 +111,9 @@
     "jsonc-parser": "^3.3.0",
     "zod": "4.4.3"
   },
+  "overrides": {
+    "@earendil-works/pi-ai": "0.80.7"
+  },
   "publishConfig": {
     "access": "public",
     "provenance": true

package/skills/ce-brainstorm/references/synthesis-summary.md

@@ -245,7 +245,7 @@ Fall back to a numbered list in chat only when no blocking tool exists or the ca
 If the user response indicates they're in the wrong skill or want a different workflow (e.g., "this is too small, just ce:work it" or "this needs more thought, let me brainstorm differently"):
 
 - Stop ce-brainstorm
-- Suggest the alternative skill the user appears to want (e.g., `ce:work`, `ce:debug`)
+- Suggest the alternative skill the user appears to want (e.g., `ce:work`)
 - Offer to load it in-session
 - Do not push back or argue — the user's redirect signal is the deliberate choice
 

package/skills/ce-plan/SKILL.md

@@ -140,7 +140,7 @@ If the bootstrap uncovers major unresolved product questions:
 
 If the bootstrap reveals that a different workflow would serve the user better:
 
-- **Symptom without a root cause** (user describes broken behavior but hasn't identified why) — announce that investigation is needed before planning and load the `ce:debug` skill. A plan requires a known problem to solve; debugging identifies what that problem is. Announce the routing clearly: "This needs investigation before planning — switching to ce:debug to find the root cause."
+- **Symptom without a root cause** (user describes broken behavior but hasn't identified why) — announce that investigation is needed before planning: a plan requires a known problem to solve, so the root cause must be identified first. Announce the routing clearly: "This needs investigation before planning — identify the root cause first, then return to planning."
 - **Clear task ready to execute** (known root cause, obvious fix, no architectural decisions) — suggest `ce:work` as a faster alternative alongside continuing with planning. The user decides.
 
 #### 0.5 Classify Outstanding Questions Before Planning
@@ -171,7 +171,7 @@ If depth is unclear, ask one targeted question and then continue.
 
 Surface call-outs to the user — the specific forks in scope or approach where user input materially changes the plan — so scope can be corrected **before Phase 1 research is spent**. Sub-agent dispatch (systematic:research:repo-research-analyst, systematic:research:learnings-researcher, etc.) is the expensive next step this phase guards against wasted effort on.
 
-Fires **only in solo invocation** — when Phase 0.2 found no upstream brainstorm doc AND Phase 0.4 stayed in ce:plan (did not route to ce:debug, ce:work, or universal-planning) AND Phase 0.5 cleared (no unresolved blockers) AND not on Phase 0.1 fast paths (resume normal, deepen-intent). Each guard is an explicit conditional. Skip Phase 0.7 entirely when any guard fails — brainstorm-sourced invocations defer to Phase 5.1.5 instead.
+Fires **only in solo invocation** — when Phase 0.2 found no upstream brainstorm doc AND Phase 0.4 stayed in ce:plan (did not route to ce:work or universal-planning) AND Phase 0.5 cleared (no unresolved blockers) AND not on Phase 0.1 fast paths (resume normal, deepen-intent). Each guard is an explicit conditional. Skip Phase 0.7 entirely when any guard fails — brainstorm-sourced invocations defer to Phase 5.1.5 instead.
 
 **Read `references/synthesis-summary.md` before composing the scoping synthesis.** It carries the affirmability test, keep-test criteria, detail test, summary shape budgets, granularity rules, anti-patterns, revision-vs-confirmation discipline, doc-shape routing, soft-cut behavior, self-redirect support, the worked PII compression example, and full headless-mode routing — all required for a well-shaped synthesis.
 
@@ -226,8 +226,8 @@ Prepare a concise planning context summary (a paragraph or two) to pass as input
 
 Run these agents in parallel:
 
-- task systematic:research:repo-research-analyst(Scope: technology, architecture, patterns. {planning context summary})
-- task systematic:research:learnings-researcher(planning context summary)
+- Dispatch `systematic:research:repo-research-analyst` — scope: technology, architecture, patterns; pass the planning context summary.
+- Dispatch `systematic:research:learnings-researcher` — pass the planning context summary.
 Collect:
 - Technology stack and versions (used in section 1.2 to make sharper external research decisions)
 - Architectural patterns and conventions to follow
@@ -295,8 +295,8 @@ Announce the decision briefly before continuing. Examples:
 
 If Step 1.2 indicates external research is useful, run these agents in parallel:
 
-- task systematic:research:best-practices-researcher(planning context summary)
-- task systematic:research:framework-docs-researcher(planning context summary)
+- Dispatch `systematic:research:best-practices-researcher` — pass the planning context summary.
+- Dispatch `systematic:research:framework-docs-researcher` — pass the planning context summary.
 
 #### 1.4 Consolidate Research
 
@@ -324,7 +324,7 @@ This ensures flow analysis (Phase 1.5) runs and the confidence check (Phase 5.3)
 
 For **Standard** or **Deep** plans, or when user flow completeness is still unclear, run:
 
-- task systematic:workflow:spec-flow-analyzer(planning context summary, research findings)
+- Dispatch `systematic:workflow:spec-flow-analyzer` — pass the planning context summary and research findings.
 
 Use the output to:
 - Identify missing edge cases, state transitions, or handoff gaps

package/skills/ce-plan/references/synthesis-summary.md

@@ -218,7 +218,7 @@ What survived: three real forks where another reasonable agent might choose diff
 
 Fires only when:
 - Phase 0.2 found no upstream brainstorm doc
-- AND Phase 0.4 stayed in ce:plan (did not route to ce:debug, ce:work, or universal-planning)
+- AND Phase 0.4 stayed in ce:plan (did not route to ce:work or universal-planning)
 - AND Phase 0.5 cleared (no unresolved blockers)
 - AND not on Phase 0.1 fast paths (resume normal, deepen-intent)
 
@@ -361,7 +361,7 @@ This restores the audit visibility the original design intended (un-validated be
 
 If the user response indicates they're in the wrong skill or want a different workflow:
 
-- **Solo variant**: common redirects include "this is bigger than I thought — let me brainstorm first" (suggest `ce:brainstorm`), "this is just a fix, no plan needed" (suggest `ce:work`), or "I need to investigate first" (suggest `ce:debug`).
+- **Solo variant**: common redirects include "this is bigger than I thought — let me brainstorm first" (suggest `ce:brainstorm`), "this is just a fix, no plan needed" (suggest `ce:work`), or "I need to investigate first" (route to root-cause investigation before planning).
 - **Brainstorm-sourced variant**: less common, but possible — "actually this scope is wrong, take it back to brainstorm" (suggest `ce:brainstorm` to revise the upstream doc).
 
 In either case: stop ce:plan, suggest the alternative skill, offer to load it in-session. Don't push back or argue — the user's redirect signal is the deliberate choice.

package/skills/ce-review/SKILL.md

@@ -697,7 +697,7 @@ After presenting findings and verdict (Stage 6), route the next steps by mode. R
   - residual actionable work
   - advisory-only outputs
   Per-agent full-detail JSON files (`{reviewer_name}.json`) are already present in this directory from Stage 4 dispatch.
-- Also write `metadata.json` alongside the findings so downstream skills (e.g., `ce:polish-beta`) can verify the artifact matches the current branch and HEAD. Minimum fields:
+- Also write `metadata.json` alongside the findings so downstream skills can verify the artifact matches the current branch and HEAD. Minimum fields:
   ```json
   {
     "run_id": "<run-id>",

package/skills/using-systematic/SKILL.md

@@ -42,7 +42,7 @@ digraph skill_flow {
     "Already brainstormed?" [shape=diamond];
     "Invoke brainstorming skill" [shape=box];
     "Might any skill apply?" [shape=diamond];
-    "Invoke `systematic_skill` tool" [shape=box];
+    "Invoke the relevant skill via the active harness's skill-loading mechanism" [shape=box];
     "Announce: 'Using [skill] to [purpose]'" [shape=box];
     "Has checklist?" [shape=diamond];
     "Create todo per item" [shape=box];
@@ -55,9 +55,9 @@ digraph skill_flow {
     "Invoke brainstorming skill" -> "Might any skill apply?";
 
     "User message received" -> "Might any skill apply?";
-    "Might any skill apply?" -> "Invoke `systematic_skill` tool" [label="yes, even 1%"];
+    "Might any skill apply?" -> "Invoke the relevant skill via the active harness's skill-loading mechanism" [label="yes, even 1%"];
     "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
-    "Invoke `systematic_skill` tool" -> "Announce: 'Using [skill] to [purpose]'";
+    "Invoke the relevant skill via the active harness's skill-loading mechanism" -> "Announce: 'Using [skill] to [purpose]'";
     "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
     "Has checklist?" -> "Create todo per item" [label="yes"];
     "Has checklist?" -> "Follow skill exactly" [label="no"];
@@ -110,6 +110,6 @@ Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.
 
 The four capabilities are subagent delegation, blocking user interaction, task tracking, and skill loading.
 
-The bootstrap inlines the active harness profile naming the exact mechanisms—consult it. See `references/opencode-profile.md` and `references/pi-profile.md`.
+The bootstrap inlines the active harness profile naming the exact mechanisms for this session—consult it.
 
 When a mechanism is unavailable, present numbered options in chat and wait for questions, maintain a visible list for task tracking, and dispatch delegation sequentially or do the work inline.

package/skills/using-systematic/references/claude-code-profile.md

@@ -0,0 +1,37 @@
+# Claude Code Capability Profile
+
+| Capability | Mechanism | Status | Fallback |
+|---|---|---|---|
+| Subagent delegation | Name-based subagent dispatch; plugin agents ship in `agents/`; `context: fork` for skill-scoped forks | supported | Dispatch in the foreground, serially or in small batches |
+| Blocking user interaction | `AskUserQuestion` tool | supported | Present numbered options in chat and wait |
+| Task tracking | `TaskCreate` / `TaskGet` / `TaskList` / `TaskUpdate` (`TodoWrite` is deprecated and disabled by default) | supported | Maintain a visible task list in responses |
+| Skill loading | Native Skill tool with `SKILL.md` discovery (`~/.claude/skills/`, `.claude/skills/`, plugin `skills/`); Systematic ships no `systematic_skill` tool on Claude Code | supported | Read the skill instructions listed by the active harness |
+
+Behavioral enforcement on Claude Code rides a plugin output style (force-for-plugin); a declarative `SessionStart` hook carries state only, since imperative hook content is refused as prompt injection.
+
+## Invocation examples
+
+### Subagent delegation
+
+```text
+Use the systematic-implementer subagent to implement the auth module and return the changed files.
+```
+
+### Blocking user interaction
+
+```typescript
+AskUserQuestion({
+  questions: [{ question: "Which deployment target should I use?", header: "Deployment target",
+    options: [{ label: "Staging", description: "Deploy to staging" }] }],
+})
+```
+
+### Task tracking
+
+```typescript
+TaskCreate({ content: "Run validation", status: "pending", priority: "high" })
+```
+
+### Skill loading
+
+Skills are discovered natively from `SKILL.md` files under `~/.claude/skills/`, `.claude/skills/`, and plugin `skills/` directories; invoke them with the built-in Skill tool using the skill name.