@openrig/cli 0.6.14 → 0.7.1

package/daemon/context-packs/skills/pm/backlog-capture/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "backlog-capture"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Quickly capture product ideas, feature requests, or insights from meetings and conversations. Rapid documentation with smart categorization and deduplication."
 files:

package/daemon/context-packs/skills/pm/context-builder/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "context-builder"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Gather and distill context from meetings, competitors, regulatory sources, and internal discussions. Produces background.md for a feature and updates shared context docs when new knowledge is discovered."
 files:

package/daemon/context-packs/skills/pm/exec-summary/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "exec-summary"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Generate a 1-2 page executive summary for a feature — orients sales, leadership, and engineering from a single document."
 files:

package/daemon/context-packs/skills/pm/office-hours/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "office-hours"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "YC-style product validation using six forcing questions. Pressure-tests a feature idea before it becomes a requirement — ensuring real demand, a clear wedge, and evidence behind assumptions."
 files:

package/daemon/context-packs/skills/pm/plan-review/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "plan-review"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Multi-perspective review of a feature plan or requirements doc before development begins. Evaluates from strategy, design/UX, and engineering angles to catch gaps early."
 files:

package/daemon/context-packs/skills/pm/requirements-writer/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "requirements-writer"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies."
 files:

package/daemon/context-packs/skills/pm/ui-mockup/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "ui-mockup"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Create UI mockups at three fidelity levels — ASCII wireframes for quick iteration, standalone HTML mockups for delivery with requirements, and live prototypes for interaction testing."
 files:

package/daemon/context-packs/skills/pods/development-team/SKILL.md

@@ -26,6 +26,8 @@ Clarify consequential uncertainty, inspect the existing seam, then complete one
 coherent outcome. Reproduce a defect before repairing it; use tests that distinguish
 the failure and verify through the public surface. Keep chunks as large as the
 outcome and file territory permit. TDD is a feedback loop, not a two-seat protocol.
+When the work consolidates or refactors existing behavior, read
+[references/refactoring.md](references/refactoring.md).
 
 The builder reports the exact candidate, changed behavior, commands and observed
 results, with remaining uncertainty. No universal pre-edit proposal, QA approval

package/daemon/context-packs/skills/pods/development-team/manifest.yaml

@@ -1,10 +1,12 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "development-team"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Use when a development pod begins or hands off implementation, QA, or design work."
 files:
   - path: "SKILL.md"
     role: "instruction"
     summary: "Use when a development pod begins or hands off implementation, QA, or design work."
+  - path: "references/refactoring.md"
+    role: "reference"

package/daemon/context-packs/skills/pods/development-team/references/refactoring.md

@@ -0,0 +1,11 @@
+# Refactoring and consolidation
+
+Read this when a change consolidates duplicated logic or refactors existing behavior.
+
+- Trace the callers before you consolidate.
+- Tell shared policy apart from capture, parsing and harness adapters. Code that looks the same can serve different harnesses with different semantics.
+- Name the observable behavior you preserve, and name any change you're making on purpose, separately.
+- Reuse suitable checks, or add the smallest comparison that would detect a consequential difference.
+- Keep compatibility where callers or persisted state need it. Remove an obsolete path once that's established.
+
+Adapted from the blast-radius tracing method in Cursor's pstack plugin (https://github.com/cursor/plugins/tree/190d28736eff128ec94f502a22c7fe0c4b56cd37/pstack).

package/daemon/context-packs/skills/pods/orchestration-team/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "orchestration-team"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Use when coordinating assignments, selected review boundaries, or blocked work across a rig."
 files:

package/daemon/context-packs/skills/pods/oversight-team/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "oversight-team"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention ladder (orchestrator-ping -> refocus -> human escalation), and the cheap+deep model economics. NOT for orchestrating your OWN rig (orchestration-team) and NOT the intervention primi"
 files:

package/daemon/context-packs/skills/pods/review-team/SKILL.md

@@ -25,7 +25,7 @@ named slice's explicit exception. Authors do not perform their own selected
 independent review.
 
 Match the selected review to the consequence. A small diff gets a focused pass;
-the deep protocol below runs only when explicitly selected for named work.
+the deep review method below runs only when explicitly selected for named work.
 Importance, size or a prior finding alone cannot self-select it. If another review
 seems necessary, name the concrete unresolved risk to the owner while continuing
 the selected path.
@@ -36,32 +36,26 @@ Derive the selection before forming a review position. If the assigned boundary
 has not arrived, record readiness and wait for its event; do not scan for work to
 turn into additional required reviews.
 
-## Context priming — always do this first
+## Context
 
-Before reviewing ANY code, you must understand the codebase context. Never review cold.
+Read the context this change needs before forming a position. Don't review cold.
 
-1. Read the project's `CLAUDE.md` or equivalent conventions doc
-2. Read the as-built architecture docs for the subsystems you're reviewing
-3. Read the relevant planning/spec docs if they exist
-4. Understand the domain vocabulary and key invariants
+1. The project's `CLAUDE.md` or equivalent conventions doc
+2. The as-built architecture docs for the subsystems the change touches
+3. The relevant planning or spec docs, if they exist
+4. The domain vocabulary and the invariants the change could break
 
-If you have blanks — areas you don't understand — say so explicitly and fill them before forming opinions. A review built on misunderstood context is worse than no review.
-
-For deep reviews, write a **context proof** before proceeding:
-- Subsystem purpose summary
-- Key invariants (must-not-break rules)
-- Architecture boundaries and constraints
-- PR/range intent and expected behavior
-- Unknowns / missing context
-- Confidence scores (0-100) per section
+Preparing context is part of the review, not a gate before it. Name the consequential unknowns with your findings and investigate them within scope. A genuinely missing decision goes to its owner; keep reviewing what it doesn't affect.
 
 ## Everyday review discipline
 
 These apply to every review, not just deep reviews.
 
+Does the change solve the user's problem with a maintainable design? Check affected contracts, invalid input, state transitions, recovery, consumers and unnecessary duplication.
+
 ### Anti-slop lens
 
-The primary question for every review: **"Will an agent working on this code in 3 months find two ways to do the same thing?"**
+Then, for every review: **"Will an agent working on this code in 3 months find two ways to do the same thing?"**
 
 Check for:
 - Code duplication across files or subsystems
@@ -70,27 +64,33 @@ Check for:
 - Parallel implementations where one should extend the other
 - Abstractions that don't earn their complexity
 
-### Empirical verification
+### Grounding findings
 
-Every claim you make must be verified against actual code. Not plausible inference. Not file-tree reasoning.
+Ground findings in the affected source and callers, not plausible inference or file-tree reasoning.
 
-- Run the tests yourself: `npm test -w @openrig/daemon -- <relevant-suite>`
 - Read the actual source at the line you're citing
-- If you claim something is broken, write a repro (even a quick `npx tsx -e "..."`)
+- Reproduce a consequential behavior claim through the permitted validation path where needed; reuse relevant run evidence with its limits
 - If you claim a test is missing, explain what input would break the code
 - If you claim duplication exists, cite both locations
+- Label source-only reasoning and untested concerns, and say what would confirm or falsify them
+
+Don't run code where the assignment forbids it, and don't hide an uncertainty because you can't run it here.
 
-A finding you haven't verified is a finding you shouldn't report.
+### What a finding says
 
-### Severity rating
+For a material finding, explain the user consequence, the affected path and how you know. Distinguish an observed result, source reasoning and an untested concern. Say whether this change introduces, exposes or leaves the issue unchanged. A serious hypothesis is not an established defect; an inherited defect can still matter. Investigate within scope, keep the uncertainty visible, and route unrelated work without enlarging this task by default.
 
-Rate every finding clearly:
-- **MUST-FIX** — blocks merge. Broken behavior, security issue, or test suite failure.
-- **HIGH** — contract violation or honesty failure. Should fix before calling the range clean.
-- **MEDIUM** — real concern that affects maintenance or agent UX. Should fix soon.
-- **LOW** — polish, robustness, or minor inconsistency. Fix when convenient.
+### Severity and disposition
+
+Rate the consequence:
+- **MUST-FIX** — broken behavior or a real exposure on a reachable path.
+- **HIGH** — contract violation or honesty failure.
+- **MEDIUM** — real concern that affects maintenance or agent UX.
+- **LOW** — polish, robustness, or minor inconsistency.
 - **INFO** — observation worth noting. Not a defect.
 
+Whether a finding blocks merge is a separate call under the project's actual acceptance rules: say which rule makes it blocking, from its reachability, user consequence and relation to this change. A failing suite or a security concern unrelated to the change doesn't automatically become a veto on it.
+
 ### Reporting findings
 
 Write review artifacts to disk so they survive compaction:
@@ -101,8 +101,8 @@ docs/review/<review-name>/01-review-<your-id>.md
 Also report to the orchestrator or chatroom:
 ```bash
 rig send <orchestrator-session> "REVIEW: <title>
-HIGH :: <file:line> :: <issue>
-MEDIUM :: <file:line> :: <issue>
+HIGH :: <file:line> :: <user consequence> :: <how you know> :: introduces|exposes|leaves
+MEDIUM :: <file:line> :: <user consequence> :: <how you know> :: introduces|exposes|leaves
 ..." --verify
 ```
 
@@ -126,89 +126,39 @@ When reviewing work that was implemented without a pre-existing spec (ad hoc, do
 - Ask: "Does this code deliver what it appears to intend? Are the contracts honest?"
 - This is called a **hindsight review** — you review forward from the code, not backward from a spec
 
-## Deep review protocol
+## Deep review method
 
-Only when the owner or composition explicitly selects this protocol for named work, the orchestrator coordinates these phases. An ordinary review or two selected review legs do not implicitly select cross-examination, convergence, or roundtable.
+Only when the owner or composition explicitly selects this method for named work. An ordinary review, or two selected review legs, is not a deep review. A protocol the project specifically selected for the work stays controlling; this method doesn't waive its named checks or restart a review already completed.
 
-### Phase 1: Context priming gate
+### 1. Independent first views
 
-Each reviewer independently reads context docs and writes a context proof (see above). The orchestrator reads both proofs and decides GO or NO-GO. No code review starts until the gate passes.
-
-### Phase 2: Independent reviews
-
-Each reviewer reads the full diff/range independently and writes findings to disk:
+Each reviewer inspects the relevant context, source and exact target before reading anyone else's findings, and writes findings to disk in the format above, with consequential unknowns:
 ```
 docs/review/<review-name>/01-review-<your-id>.md
 ```
 
-Do NOT read the other reviewer's work during this phase. Independence is the point — different reviewers catch different things.
-
-Your independent review should cover:
-- Test posture (does the suite pass? are there regressions?)
-- Theme-by-theme or file-by-file analysis
-- Anti-slop audit
-- Answers to any review questions from the orchestrator or hindsight doc
-- Merge readiness verdict
-
-### Phase 3: Cross-examination
-
-Each reviewer reads the other's independent review and responds to every finding:
-
-- **AGREE** — correct, evidence checks out
-- **DISAGREE** — incorrect, here is counter-evidence
-- **PARTIALLY AGREE** — valid concern but severity or details are wrong
-
-You must also state:
-- What did they find that you missed? (Be honest about your blind spots)
-- What did you find that they missed?
-- Do their findings change any of your severity assessments?
-- Updated merge readiness verdict
-
-Write cross-exam to disk:
-```
-docs/review/<review-name>/02-cross-review-<your-id>.md
-```
-
-### Phase 4: Convergence and roundtable
-
-The orchestration pod reads all reviews and cross-exams and writes a convergence synthesis classifying each finding as:
-- **CONFIRMED** — all reviewers agree
-- **DISPUTED** — disagreement exists with evidence on both sides
-- **WITHDRAWN** — originator retracted
+Independence is the point: different reviewers catch different things. Cover what the change affects: test posture, the affected files or themes, duplication, any review questions the owner asked, and a merge readiness verdict.
 
-Then a roundtable in the chatroom where all participants (reviewers + orchestrators) post positions, respond to each other, and converge on final findings and action items.
+### 2. Compare, then challenge what could change the disposition
 
-Culture for the roundtable:
-- Truth-seeking. Not contrarian for theater. Not agreeable to be nice.
-- Every participant posts an initial position
-- Every participant responds to at least one other's position
-- Every participant posts a final concur or amend
-- The host does not synthesize early — real back-and-forth first
+The decision owner compares the independent findings. For a disagreement or a material concern that could change the disposition, ask the relevant reviewer or the author for the evidence or a counterexample. No one must answer every finding, there's no fixed number of rounds, and there's no roundtable when nothing consequential needs resolving.
 
-### Phase 5: Final output
+### 3. One disposition
 
-The host writes the final roundtable document with:
-- Confirmed findings with severity
-- Final priority stack (P0 / P1 / P2)
-- Action items with owner
-- What the implementation team should NOT reopen
+The decision owner records one disposition:
+- findings with severity, and the blocking rationale under the project's acceptance rules, kept separate
+- evidence limits and any material dissent, still visible
+- action items with owner, and what the implementation team should not reopen
 
-## Reviewer behavioral awareness
+Agreement alone doesn't prove a finding. Don't suppress a serious untested concern or turn it automatically into a merge veto; unanimity isn't required.
 
-### If you are Claude (R1)
-- You tend to be strongest on architecture and weakest on edge-case honesty
-- You verify the happy path thoroughly but may miss failure-mode gaps
-- You should deliberately check: "What happens when this fails? What happens with bad input? What about the release-then-remove sequence?"
+## Choosing reviewers
 
-### If you are Codex (R2)
-- You catch edge cases that Claude misses
-- You are thorough at empirical verification
-- You may over-weight severity on issues that are real but minor
-- You should deliberately check: "Is this actually a shipped defect or just a robustness wish?"
+Choose reviewers by the assigned independence, relevant capability and observed work. A model name does not establish which failures it will catch.
 
 ### When reviewers disagree
 
-Disagreement is useful. Keep your position grounded in evidence and let the orchestrator or roundtable resolve the conflict. Do not collapse your view just to create false consensus. If you're right, defend it. If you're wrong, retract it honestly.
+Disagreement is useful. Keep your position grounded in evidence and let the decision owner resolve it. Do not collapse your view just to create false consensus. If you're right, defend it. If you're wrong, retract it honestly.
 
 ## When there is no assigned review
 

package/daemon/context-packs/skills/pods/review-team/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "review-team"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Use when assigned a review or when an authored review boundary is reached."
 files:

package/daemon/context-packs/skills/process/agent-browser/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "agent-browser"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction."
 files:

package/daemon/context-packs/skills/process/context-engineering/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "context-engineering"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Use when designing, reviewing, or debugging how an agent's context window gets filled, pruned, or shared — choosing what loads at boot versus on demand, sizing an install or an always-loaded file, fixing an agent that drifts, repeats itself, or forgets constraints mid-task, planning compaction or summarization, deciding single-agent versus subagents, engineering handoffs between agents, or picking a tool loadout. NOT for rewording a prompt's tone, choosing which model to pin, or debugging busine"
 files:

package/daemon/context-packs/skills/process/dogfood/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "dogfood"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app/site/platform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams."
 files:

package/daemon/context-packs/skills/process/frontend-design/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "frontend-design"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics."
 files:

package/daemon/context-packs/skills/process/systematic-debugging/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "systematic-debugging"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes"
 files:

package/daemon/context-packs/skills/process/test-driven-development/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "test-driven-development"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
 purpose: "Use when implementing any feature or bugfix, before writing implementation code"
 files:

package/daemon/context-packs/skills/process/verification-before-completion/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: verification-before-completion
-description: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
+description: Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs
 metadata:
   openrig:
     vendored_from: "Obra Superpowers (https://github.com/obra/superpowers)"
@@ -14,75 +14,45 @@ metadata:
 
 Claiming work is complete without verification is dishonesty, not efficiency.
 
-**Core principle:** Evidence before claims, always.
+**Core principle:** Evidence before claims.
 
-**This rule serves shipping — it is not a ritual that outranks it.** It governs one thing: *claims that a verifiable result holds* ("tests pass", "build succeeds", "bug fixed") — run the check before you assert it, and scale the check to the stakes (a one-line copy tweak is not a test-suite ceremony). Don't dodge it with synonyms; equally, don't inflate it into a tax on the word "done" or a reason to keep re-proving instead of shipping the working thing.
+**This rule serves shipping — it is not a ritual that outranks it.** It governs one thing: *claims that a verifiable result holds* ("tests pass", "build succeeds", "bug fixed") — have evidence for the result before you assert it, and scale the check to the stakes (a one-line copy tweak is not a test-suite ceremony). Don't dodge it with synonyms; equally, don't inflate it into a tax on the word "done" or a reason to keep re-proving instead of shipping the working thing.
 
-## The Iron Law
+## The Rule
 
-```
-NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
-```
-
-If you haven't run the verification command in this message, you cannot claim it passes.
+Before claiming a verifiable result, inspect evidence that supports that result for the candidate and environment you name. Use an existing result while its relevant inputs and assumptions still hold; rerun the affected check when they change or are uncertain. State whether you ran the check or inspected another owner's evidence. A source read, syntax check or partial test supports only its stated scope. Ordinary progress reports, delegation and moving to another task do not require a new test run. Required project checks still apply.
 
-## The Gate Function
-
-```
-BEFORE claiming any status or expressing satisfaction:
+A completed run is not automatically current, and unchanged source does not establish unchanged live state.
 
-1. IDENTIFY: What command proves this claim?
-2. RUN: Execute the FULL command (fresh, complete)
-3. READ: Full output, check exit code, count failures
-4. VERIFY: Does output confirm the claim?
-   - If NO: State actual status with evidence
-   - If YES: State claim WITH evidence
-5. ONLY THEN: Make the claim
-
-Skip any step = lying, not verifying
-```
+For a claim about performance, also read [references/performance-claims.md](references/performance-claims.md).
 
 ## Common Failures
 
 | Claim | Requires | Not Sufficient |
 |-------|----------|----------------|
-| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
+| Tests pass | Test output with 0 failures, for the candidate you name | A run on an older candidate, "should pass" |
 | Linter clean | Linter output: 0 errors | Partial check, extrapolation |
 | Build succeeds | Build command: exit 0 | Linter passing, logs look good |
 | Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
 | Regression test works | Red-green cycle verified | Test passes once |
-| Agent completed | VCS diff shows changes | Agent reports "success" |
-| Requirements met | Line-by-line checklist | Tests passing |
+| Delivered outcome | Relevant artifact and observed result | An agent's success message or a diff alone |
+| Requirements met | Promised outcomes checked against applicable evidence, gaps named | Tests passing |
 
 ## Red Flags - STOP
 
 - Using "should", "probably", "seems to"
-- Claiming a specific result is *proven* ("tests pass", "it's fixed", "build's green") before running the check in this message — enthusiasm itself is fine; an unverified **result claim** is the flag
+- Claiming a specific result is *proven* ("tests pass", "it's fixed", "build's green") without evidence that applies to it — enthusiasm itself is fine; an unverified **result claim** is the flag
 - About to commit/push/PR without verification
 - Trusting agent success reports
-- Relying on partial verification
+- Claiming more than a partial check covers
 - Thinking "just this once"
 - Tired and wanting work over
-- **ANY wording implying success without having run verification**
-
-## Rationalization Prevention
-
-| Excuse | Reality |
-|--------|---------|
-| "Should work now" | RUN the verification |
-| "I'm confident" | Confidence ≠ evidence |
-| "Just this once" | No exceptions |
-| "Linter passed" | Linter ≠ compiler |
-| "Agent said success" | Verify independently |
-| "I'm tired" | Exhaustion ≠ excuse |
-| "Partial check is enough" | Partial proves nothing |
-| "Different words so rule doesn't apply" | Spirit over letter |
 
 ## Key Patterns
 
 **Tests:**
 ```
-✅ [Run test command] [See: 34/34 pass] "All tests pass"
+✅ [Run test command, or read the named candidate's CI output] [See: 34/34 pass] "All tests pass"
 ❌ "Should pass now" / "Looks correct"
 ```
 
@@ -100,19 +70,19 @@ Skip any step = lying, not verifying
 
 **Requirements:**
 ```
-✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
+✅ Check each promised outcome against applicable evidence → Report gaps or completion
 ❌ "Tests pass, phase complete"
 ```
 
 **Agent delegation:**
 ```
-✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
-❌ Trust agent report
+✅ Agent reports success → Inspect the artifact and the evidence it names → Report what was checked and what wasn't
+❌ Pass on the report alone
 ```
 
 ## When the check itself lies — content over shape
 
-Running a verification is necessary but not sufficient: a check can exit clean and still prove nothing. These are the named ways a green check lies — the failure siblings behind "evidence before claims." (Deeper treatment of *what* you verify against: `reference-first-verification`.)
+A passing check is necessary but not sufficient: a check can exit clean and still prove nothing. These are the named ways a green check lies — the failure siblings behind "evidence before claims." (Deeper treatment of *what* you verify against: `reference-first-verification`.)
 
 - **Assert on CONTENT, never shape or count.** Output that *looks* like success — a non-zero count, a clean exit, no error text — can carry failure as its content. Before trusting a check, ask what its output looks like *when it fails*: if failure and success are indistinguishable at a glance, the check proves nothing. (`[1 lines]` and `No matches found` both read as "a match" to a line-count.)
 - **Compare the returned value to the value you PASSED — never to a description of it.** A confident label (`evidenceRef NOW SET:` printed above the untouched original) is indistinguishable from a verification in a transcript. Diff the actual result against your actual input, not against a claim about it.
@@ -120,36 +90,3 @@ Running a verification is necessary but not sufficient: a check can exit clean a
 - **A syntax check proves parseability and nothing else.** A clean `node --check` / lint / parse pass is the *covered* axis; boot and runtime are the untested one. Parseable ≠ sound.
 - **A failure whose shape is a HANG reports nothing.** A bare `await` against a stated deadline that never re-checks cannot fail loudly. Race it against a timer so failure has a shape you can see.
 - **A completeness inventory read through a truncating display is worthless.** When deciding *which occurrences to change*, count with `grep -c` / `grep -o` / full-line output — never `cut`, `head`, or a pager, which can hide a match *past* the cut. Distinguish *"I found N"* (a count) from *"I saw N"* (a display). Audit multiline prose **by paragraph, not by line** — a line filter both misses long-line matches and false-flags paragraphs whose companion text is on the next line. Then re-audit with a **different method** than the one that built the inventory — same-method re-checking reproduces the blind spot. (Empty/short output is a claim about your COMMAND until re-proven a second way.)
-
-## Why This Matters
-
-From 24 failure memories:
-- your human partner said "I don't believe you" - trust broken
-- Undefined functions shipped - would crash
-- Missing requirements shipped - incomplete features
-- Time wasted on false completion → redirect → rework
-- Violates: "Honesty is a core value. If you lie, you'll be replaced."
-
-## When To Apply
-
-**ALWAYS before:**
-- ANY variation of success/completion claims
-- ANY expression of satisfaction
-- ANY positive statement about work state
-- Committing, PR creation, task completion
-- Moving to next task
-- Delegating to agents
-
-**Rule applies to:**
-- Exact phrases
-- Paraphrases and synonyms
-- Implications of success
-- ANY communication suggesting completion/correctness
-
-## The Bottom Line
-
-**No shortcuts for verification.**
-
-Run the command. Read the output. THEN claim the result.
-
-This is non-negotiable.

package/daemon/context-packs/skills/process/verification-before-completion/manifest.yaml

@@ -1,10 +1,12 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "verification-before-completion"
-version: "0.6.14"
+version: "0.7.1"
 taxonomy: "skills"
-purpose: "Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always"
+purpose: "Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs"
 files:
   - path: "SKILL.md"
     role: "instruction"
-    summary: "Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always"
+    summary: "Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs"
+  - path: "references/performance-claims.md"
+    role: "reference"

package/daemon/context-packs/skills/process/verification-before-completion/references/performance-claims.md

@@ -0,0 +1,12 @@
+# Performance claims
+
+Read this before claiming that a change makes something faster, lighter or more responsive. It's for a performance claim, not for every change.
+
+- Bind the claim to the versions, fixture and workload you measured.
+- Count the correct work completed and the failures, as well as the time. A speedup that comes from doing less work isn't one.
+- Keep the relevant setup comparable between the runs you compare, and separate what your instrumentation costs from what you measure.
+- Report the repetitions and the variability, and state the limits. Choose enough repetitions to support the precision you claim; there's no fixed minimum.
+- Freeze a suitable harness while you compare candidates.
+- Stop when the selected outcome is met, or when the remaining experiments no longer justify their cost. An honest negative result is a result; keep it.
+
+Adapted from the benchmark-checklist method in Cursor's pstack plugin (https://github.com/cursor/plugins/tree/190d28736eff128ec94f502a22c7fe0c4b56cd37/pstack).