@ferris1225/pi-subagents 4.3.3 → 4.3.4

package/CHANGELOG.md

@@ -4,6 +4,11 @@ Published versions of `@ferris1225/pi-subagents`. Unpublished numbers
 (`4.2.3`, `4.2.6`, `4.2.9`–`4.2.11`) never shipped on npm; their changes
 landed in the next published release.
 
+## 4.3.4
+
+- Keep artisan, steward, and sentinel fully usable when Ferris skills are absent.
+  Installed matching skills add deeper guidance but are optional and never block a role.
+
 ## 4.3.3
 
 - Add `sentinel`, a concise read-only adversarial reviewer that runs after cleanup,

package/README.md

@@ -12,10 +12,9 @@ once and your main agent delegates on its own.
 
 ## What's new
 
-**4.3.3** — adds the post-cleanup `sentinel`, a transactional all-in-one setup
-overlay, effective thinking in the live widget, and primary-source external research
-for scout. Role prompts now keep only essential fallback gates while detailed Ferris
-rules remain canonical in skills.
+**4.3.4** — makes Ferris skills optional enhancements instead of runtime
+requirements. Artisan, steward, and sentinel remain fully operational from their
+standalone role prompts when users have no Ferris skills installed.
 See [CHANGELOG.md](./CHANGELOG.md).
 
 ## Contents
@@ -84,13 +83,13 @@ directly when you want exact control.
 | `scout`    | Read-only   | Broad or unfamiliar code reconnaissance and external research. Returns compact file citations or source URLs as leads, not proof. |
 | `artisan`  | Full        | One substantial primary change—implementation, fix, refactor, test, or docs—through root cause, affected verification, and local hygiene. |
 | `steward`  | Full        | One final cleanup and cross-cutting docs/comment sync pass after a broad or multi-writer change. |
-| `sentinel` | Review-only | A post-cleanup adversarial review against matching Ferris skills; reports only evidence-backed defects and concrete test gaps. |
+| `sentinel` | Review-only | A post-cleanup adversarial review using standalone evidence gates plus any matching Ferris skills; reports only evidence-backed defects and concrete test gaps. |
 
-Role prompts carry the non-negotiable minimum even if skill matching misses:
-root-cause-first diagnosis, meaningful test evidence, bounded cleanup, and
-evidence-only review. Detailed language, platform, debugging, testing, and audit
-rules stay in the Ferris skills; artisan and sentinel load the matching skills,
-while steward always loads `ferris-audit`. This avoids duplicated, drifting prompts.
+Role prompts are standalone: they embed root-cause-first diagnosis, meaningful test
+evidence, bounded cleanup, and evidence-only review. Optional Ferris skills remain
+the canonical source of deeper language, platform, debugging, testing, and audit
+guidance. Artisan and sentinel load matching skills when available; steward uses
+`ferris-audit`; a missing skill never blocks a role or changes its ownership contract.
 
 Custom roles join them with a Markdown file (see [Custom agents](#custom-agents)).
 
@@ -139,10 +138,11 @@ tests, docs, comments, targeted checks, and local hygiene. Scout owns broad code
 mapping or external research and stays read-only.
 
 With the default team, every commit ends in one order: cleanup -> `sentinel`. A
-focused diff gets the `ferris-audit` pass inline; a broad or multi-writer diff
-gets one `steward` pass that attacks touched dead code, duplication, tangled
-conditionals, needless layers, and spaghetti growth without widening into a
-repo refactor. Sentinel then reviews the cleaned diff against matching skills.
+focused diff gets a bounded cleanup pass inline; a broad or multi-writer diff gets
+one `steward` pass that attacks touched dead code, duplication, tangled conditionals,
+needless layers, and spaghetti growth without widening into a repo refactor.
+Sentinel then reviews the cleaned diff with its standalone evidence gates plus any
+available matching skills.
 A review-driven edit repeats that sequence once; unresolved findings block the
 commit. Main inspects the final diff and runs the final gate.
 
@@ -316,8 +316,9 @@ search snippets, records material dates/versions, and marks uncertainty.
 
 `sentinel` has an explicit retrieval/documentation list plus a portable shell
 slot for Git inspection and the smallest proving check. It is pinned to `shared`
-so it sees the current uncommitted diff. Its concise prompt loads matching ferris
-skills, preserves their owners, and forbids mutation; that is a review contract,
+so it sees the current uncommitted diff. Its concise prompt uses matching available
+Ferris skills, preserves their owners, and forbids mutation; missing skills do not
+block review. This is a review contract,
 not a hard shell sandbox.
 
 ## Configuration

package/agents/artisan.md

@@ -7,7 +7,7 @@ You own one primary change phase: implementation, fix, refactor, test, or substa
 
 ## Rules
 
-- Load matching ferris skills before acting: `ferris-debug` for unexplained failures, `ferris-tests` for test changes, and the relevant language or platform skill. Follow their evidence gates.
+- Use matching ferris skills when available: `ferris-debug` for unexplained failures, `ferris-tests` for test changes, and the relevant language or platform skill. Missing skills are not a blocker; the rules below are the fallback contract.
 - For a reported defect or failure, inspect current behavior, confirm the defect before editing, and establish its root cause; a disproved issue means zero edits.
 - Make the smallest coherent root-cause change. Preserve unrelated work and existing conventions; avoid speculative abstractions and unrelated cleanup.
 - Own the complete primary change plus directly affected tests, README/docs, comments, and local diff hygiene. Remove debug output, dead code, stale comments, and other debris introduced in your scope.

package/agents/sentinel.md

@@ -10,7 +10,7 @@ You own one adversarial final-review phase after cleanup. The brief is your only
 ## Rules
 
 - Inspect the complete diff, untracked files, affected callers, and claimed checks. Attack behavior, trust boundaries, failure and cancellation paths, concurrency, portability, and tests.
-- Load only matching ferris skills. Treat them and AGENTS.md as the contract, not suggestions. Preserve ownership: ferris-audit/steward owns cleanup; the implementation owner owns fixes and test mutations. Do not duplicate either phase.
+- Use only matching ferris skills when available. Missing skills are not a blocker; this prompt is the fallback contract. Preserve ownership: ferris-audit/steward owns cleanup; the implementation owner owns fixes and test mutations. Do not duplicate either.
 - Work read-only. Run only the smallest targeted check needed to prove a suspected defect. Never edit, stage, commit, push, publish, tag, or release.
 - Report only actionable findings, highest severity first: `SEVERITY path:line — failure scenario; evidence; smallest fix`.
 - No nits, praise, vague risks, or inspection narrative. If none, output `No findings.` Add only concrete missing verification that could hide a regression. Stay under 30 lines.

package/agents/steward.md

@@ -7,7 +7,7 @@ You own one final hygiene phase after primary writing has finished and before se
 
 ## Rules
 
-- Load `ferris-audit` and apply its automatic pre-commit tier. Its evidence and scope limits are authoritative; do not turn this pass into repo-wide deep cleanup.
+- Use `ferris-audit` when available and apply its automatic pre-commit tier. Missing skills are not a blocker; the rules below are the fallback contract and must not widen into repo-wide cleanup.
 - Require a named completed scope such as an uncommitted diff or Git range. Start there; never repeat implementation or reconnaissance, and stop if primary writing is still active.
 - Hunt hard inside the touched scope: dead or unreachable code, unused imports/exports, duplicated facts or branches, debug residue, stale comments, one-off flags, tangled conditionals, pass-through wrappers, cast/optional fallback sprawl, feature logic in shared paths, and growth toward 1000-line files.
 - Prefer deleting branches, state, and layers; otherwise reuse the canonical helper. Never merely move spaghetti. Prove every cut has no live consumer, and keep uncertain dynamic behavior, public APIs, persisted formats, and compatibility.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ferris1225/pi-subagents",
-  "version": "4.3.3",
+  "version": "4.3.4",
   "description": "A managed sub-agent team for pi: scout, artisan, steward, and sentinel roles, durable threads, model fallback, and Git worktree isolation.",
   "type": "module",
   "license": "MIT",

package/src/config.ts

@@ -78,7 +78,7 @@ export const AGENT_PROFILES: Record<(typeof BUILTIN_AGENT_NAMES)[number], AgentP
 	},
 	sentinel: {
 		summary: "adversarial review",
-		remark: "Challenges every cleaned pre-commit diff against matching skills; follows artisan's model with max thinking by default.",
+		remark: "Challenges every cleaned pre-commit diff with standalone evidence gates plus available matching skills; follows artisan's model with max thinking by default.",
 	},
 };
 

package/src/prompt.ts

@@ -113,7 +113,7 @@ export function buildDelegationDirective(
 		...(hasScout ? ["`scout`: read-only broad code mapping or external research; return file/source citations as leads, not proof."] : []),
 		...(hasArtisan ? ["`artisan`: one substantial primary change; own root cause, implementation, affected tests/docs, and targeted checks."] : []),
 		...(hasSteward ? ["`steward`: final cleanup/docs sync for a completed broad or multi-writer diff; keep focused hygiene inline."] : []),
-		...(hasSentinel ? ["`sentinel`: read-only post-cleanup review; use matching skills and report only evidenced defects."] : []),
+		...(hasSentinel ? ["`sentinel`: read-only post-cleanup review; use available matching skills, but never block on their absence; report only evidenced defects."] : []),
 		...(hasSentinel
 			? [`Before every commit: cleanup -> sentinel review. ${hasSteward ? "Use steward once only for broad or multi-writer diffs" : "Keep cleanup inline"}. Then dispatch sentinel on the final diff and check evidence. After review fixes, clean and review once more; findings block commit.`]
 			: []),