Add security-reviewer role and targeted skill preloads (WP5 PR-B) - #376

…asks,

metrics, gate, procedure)

Freezes the E2E preregistration half of full-save/PLAN.md step 9 (the
baseline-receipt half already merged via #369) before any organic run:
77 frozen task definitions (16 reused Claude + 15 reused Codex information
needs from #296/#343's receipts, 46 seeded/control tasks), every AA §8.3
metric/threshold/guardrail/outcome rule with its three "proposed" bounds now
stated as frozen, the AA §8.1b capability gate, the AA §8.4 procedure, the
AA §8.5 overturn conditions, the identity scheme, the Q1 blind-process
qualification, the Workflow script that will run arms B/A/A0 (syntax-checked
only, never executed), and the measurement runbook.

Corrected on independent Claude review (11 findings, 95 turns) and a GPT-6
cross-family review (2 findings, 1 high) plus one combined repair round (13/13
addressed with failing-first evidence): relocated from
blueprints/token-practice-e2e/ to evidence/artifacts/token-adoption-e2e-20260926/
per adoption-audit/PLAN.md line 402; moved the Workflow script out of
examples/claude-native/workflows/ to avoid that directory's shared
PACKET/ROUTING contract test, which this one-off frozen script correctly does
not match; corrected PR-A's status (its base branch merged as #369 -- baseline
only, tooling-fix scope still open); added the six AA §6 machine-readable
policy fields the JSON was missing; fixed a wrong Codex arm-A lifecycle
binding; blocked the one information need (an otel-tui receiver task) that no
current role may legally run, pending a named permitted role; froze the
coordinator's own main-dispatch task at xhigh instead of max; fixed a
denylist word-boundary gap that let underscore-qualified MCP names slip past;
and sealed the five normative files' SHA256 with an append-only amendment
rule. Also refreshes PR #376 and #364's status to merged (both landed while
this unit was in review), while recording that #364's field-preservation gap
(workflow.run_id/tool_use_id still missing from collector.yaml) persists after
its merge.

Co-Authored-By: Claude Sonnet 5 <[email protected]>

…asks, (#381)

metrics, gate, procedure)

Freezes the E2E preregistration half of full-save/PLAN.md step 9 (the
baseline-receipt half already merged via #369) before any organic run:
77 frozen task definitions (16 reused Claude + 15 reused Codex information
needs from #296/#343's receipts, 46 seeded/control tasks), every AA §8.3
metric/threshold/guardrail/outcome rule with its three "proposed" bounds now
stated as frozen, the AA §8.1b capability gate, the AA §8.4 procedure, the
AA §8.5 overturn conditions, the identity scheme, the Q1 blind-process
qualification, the Workflow script that will run arms B/A/A0 (syntax-checked
only, never executed), and the measurement runbook.

Corrected on independent Claude review (11 findings, 95 turns) and a GPT-6
cross-family review (2 findings, 1 high) plus one combined repair round (13/13
addressed with failing-first evidence): relocated from
blueprints/token-practice-e2e/ to evidence/artifacts/token-adoption-e2e-20260926/
per adoption-audit/PLAN.md line 402; moved the Workflow script out of
examples/claude-native/workflows/ to avoid that directory's shared
PACKET/ROUTING contract test, which this one-off frozen script correctly does
not match; corrected PR-A's status (its base branch merged as #369 -- baseline
only, tooling-fix scope still open); added the six AA §6 machine-readable
policy fields the JSON was missing; fixed a wrong Codex arm-A lifecycle
binding; blocked the one information need (an otel-tui receiver task) that no
current role may legally run, pending a named permitted role; froze the
coordinator's own main-dispatch task at xhigh instead of max; fixed a
denylist word-boundary gap that let underscore-qualified MCP names slip past;
and sealed the five normative files' SHA256 with an append-only amendment
rule. Also refreshes PR #376 and #364's status to merged (both landed while
this unit was in review), while recording that #364's field-preservation gap
(workflow.run_id/tool_use_id still missing from collector.yaml) persists after
its merge.

Co-authored-by: Scout <scout@local>
Co-authored-by: Claude Sonnet 5 <[email protected]>

…ed count

Skills-trial condition log: isolated-builder's verification-before-completion
preload and the body line that names it came from #376 (623d34f,
2026-09-27T03:38:47Z per TZ=UTC git log -S on
adoption/agents/claude/isolated-builder.md), a boundary inside C0, not a
constant across every condition. The one recorded install time is
attributed as measured-gaps.md reports it (the coordinator's local
measurement), without naming a host. Token-lanes addendum: the community
alternative keeps superpowers as the verifiable example and drops a survey
count that is not retained in the repository.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

…ed count

Skills-trial condition log: isolated-builder's verification-before-completion
preload and the body line that names it came from #376 (623d34f,
2026-09-27T03:38:47Z per TZ=UTC git log -S on
adoption/agents/claude/isolated-builder.md), a boundary inside C0, not a
constant across every condition. The one recorded install time is
attributed as measured-gaps.md reports it (the coordinator's local
measurement), without naming a host. Token-lanes addendum: the community
alternative keeps superpowers as the verifiable example and drops a survey
count that is not retained in the repository.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

…ed count

Skills-trial condition log: isolated-builder's verification-before-completion
preload and the body line that names it came from #376 (623d34f,
2026-09-27T03:38:47Z per TZ=UTC git log -S on
adoption/agents/claude/isolated-builder.md), a boundary inside C0, not a
constant across every condition. The one recorded install time is
attributed as measured-gaps.md reports it (the coordinator's local
measurement), without naming a host. Token-lanes addendum: the community
alternative keeps superpowers as the verifiable example and drops a survey
count that is not retained in the repository.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

…ed count

Skills-trial condition log: isolated-builder's verification-before-completion
preload and the body line that names it came from #376 (623d34f,
2026-09-27T03:38:47Z per TZ=UTC git log -S on
adoption/agents/claude/isolated-builder.md), a boundary inside C0, not a
constant across every condition. The one recorded install time is
attributed as measured-gaps.md reports it (the coordinator's local
measurement), without naming a host. Token-lanes addendum: the community
alternative keeps superpowers as the verifiable example and drops a survey
count that is not retained in the repository.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

…l line (AN-15, after #447) (#456)

* Token-lanes carrier: evidence line replaces the verification-skill instruction

Default block line 13 now asks for evidence (the command and what it
returned, or the file:line read) and keeps the search-first sentence:
4,094 -> 4,088 bytes against the unchanged 4,100-byte bound (AN-15).
The builder block drops its verification sentence (2,883 -> 2,747
bytes): isolated-builder.md:7-9 preloads the skill and :12 names it.

Sources: code.claude.com/docs/en/best-practices.md L52 (show evidence);
platform.claude.com prompting-claude-opus-5.md L61, L81 (remove explicit
verification instructions), prompting-claude-opus-5-5.md L9 (carried
forward), claude-prompting-best-practices.md L780 (Opus 5 exception).

Handbook mirror: carrier line, its sources paragraph naming only
search-first, and the builder table row and variant. Tests: the default
key phrase becomes "Show evidence before a success claim", the builder
drops the skill phrase, and no block may name the withdrawn skill.
SHA256SUMS refreshed for both blocks. No installer run.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

* Decision records: verification-line addendum and skills-trial carrier conditions

Token-lanes decision, addendum 2026-09-28: why the default carrier line
now asks only for evidence (Opus 5 guide L61, L81; Opus 5.5 guide L9;
prompting best practices L780; Claude Code best practices L52), why the
builder line is removed on its own merits (isolated-builder.md L5, L7-9,
L12; sub-agents reference L600), sizes, the failing-first control, the
non-Opus boundary, alternatives, #381 freeze and overturn.

Skills-trial record, addendum 2026-09-28: condition log C0-C3 (#378,
2026-10-25 review rule for verification-before-completion: a
with/without comparison on frozen builder tasks through an upstream
harness named with its pin (tokens, elapsed time, review-found defects).

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

* Decision records: date the builder preload boundary; drop an unretained count

Skills-trial condition log: isolated-builder's verification-before-completion
preload and the body line that names it came from #376 (623d34f,
2026-09-27T03:38:47Z per TZ=UTC git log -S on
adoption/agents/claude/isolated-builder.md), a boundary inside C0, not a
constant across every condition. The one recorded install time is
attributed as measured-gaps.md reports it (the coordinator's local
measurement), without naming a host. Token-lanes addendum: the community
alternative keeps superpowers as the verifiable example and drops a survey
count that is not retained in the repository.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

* Token-lanes carrier: tag the evidence sentence's upstream item; narrow the no-verification claim

Repair round for the verification-line change (review findings R-F2, R-F7).

- token-lanes-block.md line 13 moves "(code.claude.com best practices)" to
  follow "the command and what it returned", the item Claude Code best
  practices L52 names (https://code.claude.com/docs/en/best-practices.md,
  re-read 2026-09-28). The file:line alternative is local policy, not in
  L52. Zero-byte reorder: the block stays 4,088 bytes and line 13 295.
- SHA256SUMS lists the new block hash; `sha256sum -c SHA256SUMS` passes.
- Handbook: the mirrored line follows, and the sources paragraph records
  the file:line alternative as local policy. It now says the carrier gives
  no instruction to verify finished work and names no verification skill,
  since the codebase-memory line still checks caller lists (handbook L264).
- Test comment: WITHDRAWN_PHRASES is a literal skill-name check, not a
  check for every verification wording.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

* Decision records: keep the manifest prune rule, name confounds and overturn variables

Repair round for the verification-line addendum and the skills-trial
carrier-condition addendum (findings V-F1, R-F1, R-F3, R-F4, R-F5, R-F6,
R-F7, GAP-3, GAP-6, GAP-7).

Skills-trial addendum:
- The review no longer "replaces" the count-based prune rule. It adds a
  with/without comparison that varies the builder's preload for the
  skill's Claude listing; trial.prune_rule (adoption/skills/manifest.json
  L30) and tools/skill-usage/skill_usage.py L516-538 still apply, and
  Codex enablement stays under that rule. A disagreement is written into
  the manifest update the trial window end already requires.
- Other sources and role changes: the landscape-sweep templates name both
  skills from 1b0e459 (templates.json common; build_args.py L59
  TEMPLATE_SKILLS), for the Claude workers and the GPT-6 lane; the C0
  baseline counts (child-lane baseline README L128-130) match that list
  without proving cause; #398 (5483412) and #402 (d022295) change the
  sweep workers' type and model and the builder's model inside C1.
- Boundaries: the installer writes no install record (shutil.copy2 at
  install_claude_profile.py L113, L143 keeps the source mtime), and #381
  step 2 freezes hashes, not install times.

Verification-line addendum:
- The builder runs model: opus, which is Opus 5.5 on this host since
  September 22 (grand-catalog-handbook.md L242-244), so the Opus 5 advice
  reaches it through the 5.5 guide's L9; before #402 it ran sonnet.
- #381 records hashes, not an install time; a Supersedes note corrects
  the qmd addendum's L389 wording the same way.
- Overturn names what each comparison varies: default-block line 13, a
  non-Opus child set, the builder line with the preload held on, or a
  prompting-guide reversal.
- Line 13's quote, the local file:line policy, the re-read of every
  documentation quote at its cited line (2026-09-28 08:55Z), the
  installed SKILL.md hash check and the control's own returned lines.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

* Token-lanes record: the no-command-output case needs neither Bash nor ctx_execute

security-reviewer has no Bash but runs commands through Context Mode's
ctx_execute (Codex review), so the rationale is qualified to children with no
command runner.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

* Evidence manifest: re-register this change's files

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

---------

Co-authored-by: Scout <scout@local>
Co-authored-by: Claude Opus 5.5 (1M context) <[email protected]>