LearnNewsExamplesServices
Frontmatter
id11128
titlepeer-role-mode.md: codify pro-active essential + session-sunset duration (sister to #11124)
stateClosed
labels
enhancementaimodel-experience
assigneesneo-opus-4-7
createdAtMay 10, 2026, 6:14 PM
updatedAtMay 13, 2026, 7:21 AM
githubUrlhttps://github.com/neomjs/neo/issues/11128
authorneo-opus-4-7
commentsCount1
parentIssuenull
subIssues[]
subIssuesCompleted0
subIssuesTotal0
blockedBy[]
blocking[]
closedAtMay 13, 2026, 7:21 AM

peer-role-mode.md: codify pro-active essential + session-sunset duration (sister to #11124)

Closedenhancementaimodel-experience
neo-opus-4-7
neo-opus-4-7 commented on May 10, 2026, 6:14 PM

Context

Operator @tobiu surfaced 2026-05-10 (this session, post-#11124-PR-#11127):

"if we update the lead role skill, we might add a follow up ticket to adjust the peer role skill too. do not be passive, but pro-active might land. VBA."

Sister substrate-evolution to #11124 (lead-role-mode.md codification, in-flight via PR #11127). The lead-role codification added:

  • §0 The Essential — "Lead ≠ micro management" anchor + maximum-abstraction one-liner
  • §6 Exit Conditions duration — session-sunset anchor

Symmetric application to peer-role-mode.md is the substrate-correct shape.

Empirical State — peer-role-mode.md (post-#10930-merge)

Current peer-role-mode.md is substantially developed:

  • §1 Core Paradigm (Flat Peer-Team)
  • §2 Actions (Substrate Audit + Convergence Pressure)
  • §3 Targeted Memory Mining
  • §4 Cross-Skill Composition
  • §5 Convergence-Artifact Vocabulary
  • §6 Symmetric Peer Patterns (already includes "self-select lanes; resist 'wait for assignment'")
  • §7 Anti-Pattern Catalog (covers ack-and-move-on / parallel-execution / rubber-stamping / etc.)
  • §8 Halt Triggers
  • §9 Non-Execution Boundary

What's missing (per operator's framing + #11124 lead-role sister symmetry):

  1. §0 The Essential — maximum-abstraction one-liner with negation-form anchor "Peer ≠ passive"
  2. §6 Exit Conditions duration — session-sunset anchor (consistent with lead-role-mode.md §6 update via #11124)

The Problem

Without §0 essential anchor:

  • Agents reading peer-role-mode.md must traverse §1-§9 to internalize the discipline
  • The negation-form "Peer ≠ passive" + maximum-abstraction one-liner cuts through where positive-only framing tripped (per #11124 empirical anchor: lead-role had §6 anti-pattern for lead-as-lane-assigner BUT still tripped without negation anchor)
  • Operator's framing "do not be passive, but pro-active might land" IS the negation-anchor; deserves codification

Without session-sunset duration anchor:

  • Agents may interpret /peer-role as per-decision-space discipline (release after one peer-review)
  • Operator-framing on lead-role ("lead role lasts until session sunset") applies symmetrically — peer-role discipline persists across decision spaces in same session
  • Cross-skill consistency: lead-role just got the duration anchor via #11124; peer-role should match

The Fix

Patch shape (.agents/skills/peer-role/references/peer-role-mode.md):

+## 0. The Essential — "Peer ≠ passive"
+
+**Peer = surface friction proactively + V-B-A + challenge. Everything else is operational.**
+
+Sample phrasing: *"I'm reviewing X. Surfaced friction: Y. V-B-A says Z. Challenge: ..."*
+
+The 3 core values (V-B-A §3.5, friction → gold §13.2, equal peer + maintainer agency §15.6)
+do the heavy lifting; peer-role just adds "surface friction proactively." Everything below
+is operational expansion.
+
+**Waiting for assignment?** §6 anti-pattern.
+**Empty agreement / ack-and-move-on?** §7 halt trigger.
+**Forced disagreement / pedantic pushback?** §7 anti-pattern.
+**Pro-active V-B-A + substantive challenge?** This.
+
+The maximum-abstraction shape minimizes coordination overhead.
+
+**Empirical anchor (operator @tobiu, 2026-05-10):** *"if we update the lead role skill,
+we might add a follow up ticket to adjust the peer role skill too. do not be passive, but
+pro-active might land. VBA."* Distilled in same session as #11124 lead-role codification;
+sister substrate-evolution.
+
+## 1. Core Paradigm: ...

And §6 Exit Conditions parallel update:

 ## 6. Exit Conditions  (or wherever §6 actually lives in peer-role-mode.md)
+
+**Duration:** Peer-role lasts until **session sunset** (per `session-sunset` skill).
+Per-decision-space convergence is *local* exit (review-cycle complete); session-end is the
+*global* exit (skill release). Once invoked, the discipline stays active for ALL subsequent
+turns until session end — not just the invoking turn.
+
+**Empirical anchor (2026-05-10):** Same session-sunset framing as lead-role-mode.md §6
+(per #11124 / PR #11127). Cross-skill consistency.

Acceptance Criteria

  • peer-role-mode.md patched with §0 The Essential — negation-form anchor "Peer ≠ passive" + maximum-abstraction one-liner + sample phrasing
  • peer-role-mode.md exit-conditions section patched with session-sunset duration anchor (verbatim parallel to lead-role-mode.md §6 update via PR #11127)
  • Both anchors cite operator-quote with [paraphrase] source per pr-review-guide.md Source-of-Authority discipline
  • Cross-references audited: pull-request-workflow.md / pr-review-guide.md / AGENTS.md §15.6 — do any need updates to reflect the pro-active anchor / session-sunset duration?
  • Empirical validation: next /peer-role invocation in any session — verify the agent (a) reads §0 essential first; (b) treats peer-role as session-sunset-duration discipline; (c) defaults to "surface friction proactively" framing

Out of Scope

  • Modifying /lead-role skill — sister substrate already shipped via PR #11127 (#11124)
  • Modifying /session-sunset skill — referenced but not in this ticket's scope
  • AGENTS.md §15.6 modifications — already codifies Flat Peer-Team paradigm
  • Modifying /pr-review skill — different depth protocol per pr-review-guide.md; orthogonal

Avoided Traps / Gold Standards Rejected

Decision Matrix

  1. Patch peer-role-mode.md directly with both anchors (Selected): Lowest implementation cost; mirrors #11124 lead-role shape symmetrically. Substrate-correct because cross-skill consistency on the negation-form-anchor + duration discipline strengthens the discipline empirically.

  2. Add only the §0 essential anchor: Rejected. Cross-skill consistency on session-sunset duration is load-bearing per #11124's empirical anchor; addressing one without the other leaves the duration-discipline asymmetric across the lead/peer pair.

  3. Add only the session-sunset duration anchor: Rejected. Operator's "pro-active VBA" framing is the load-bearing operational discipline; addressing without anchor leaves the operational pattern unexpressed.

  4. Defer until #11124/#11127 ships + validates: Considered. Pro: real-world feedback on lead-role codification before peer-role mirror. Con: same-session symmetry is hot-context advantage; operator's directive captures both in same framing. Lean: file now (this ticket); pace implementation per #11127 land + operator/peer judgment.

  • Trap: Treating peer-role as having no symmetric gap because it already has §6 + §7 patterns. Rejection: #11124's empirical anchor (lead-role had §8 anti-pattern but still tripped without §0 essential anchor) demonstrates that anti-pattern coverage alone is insufficient operationalization. Negation-form anchor cuts through where positive operational pattern alone doesn't.
  • Trap: Asymmetric application of session-sunset duration discipline across lead/peer pair. Rejection: Cross-skill consistency is load-bearing; agents invoke both during sessions; divergent durations create cognitive friction.

Related

  • #11124 / PR #11127 — sister substrate-evolution: lead-role-mode.md §0 essential + §6 duration. This ticket mirrors symmetrically.
  • AGENTS.md §15.6 — Flat Peer-Team paradigm (foundational for both lead-role and peer-role).
  • AGENTS.md §3.5 V-B-A core value — the "VBA" in operator's framing.
  • #11102 (sister) — epic-resolution Verdict-Authority calibration; same family of skill-payload codification.
  • #11105 (sister) — pull-request author-side template-adherence check; same family.
  • #11116 (sister) — code-vs-data-migration commit-shape discipline; same family.
  • peer-role-mode.md §6 Symmetric Peer Patterns — already captures "self-select lanes; resist 'wait for assignment'" — pro-active framing already ESTABLISHED in operational shape; this ticket adds the §0 maximum-abstraction headline that makes it land.

Origin Session ID: c2912891-b459-4a03-b2af-154d5e264df1 Retrieval Hint: "peer-role-mode.md codification", "Peer != passive negation anchor", "pro-active V-B-A peer", "session-sunset duration peer-role"

tobiu referenced in commit 9213f9a - "feat(swarm,sync): codify Helpful-Assistant negative constraint in §15.6 (#11128) + chunked-content data migration (#11121) + fix JSDoc optional parsing (#11164) on May 11, 2026, 2:09 AM
tobiu closed this issue on May 13, 2026, 7:21 AM
tobiu referenced in commit 8baffd6 - "docs(skills): codify peer-role essential + session-sunset duration (#11128) (#11279) on May 13, 2026, 7:21 AM