Skip to content

chore(knowledge): retire best-practices doc-queue entry after slice completion - #1765

Merged
kyle-sexton merged 1 commit into
mainfrom
chore/docqueue-best-practices-complete
Jul 30, 2026
Merged

chore(knowledge): retire best-practices doc-queue entry after slice completion#1765
kyle-sexton merged 1 commit into
mainfrom
chore/docqueue-best-practices-complete

Conversation

@kyle-sexton

Copy link
Copy Markdown
Contributor

Summary

  • Removes the code.claude.com best-practices entry from the docpage-digest Anthropic profile's doc queue — its slice completed end-to-end (fetch through interview handoff) per the queue's remove-on-completion rule. It was the sole "Applies across all of the above" entry, so the emptied category heading goes with it.
  • Channel: raw-md (.md appended to the page URL; HTTP 200, 610 lines / 39,668 bytes — channel re-verified for this page, no degradation); provenance recorded in the slice checklist.
  • Slice verification: Verifier A (same-vendor, fresh context) CORRECTION-NEEDED (1+3); Verifier B (cross-vendor Codex CLI 0.146.0 via the issue Restore cross-vendor Verifier B when openai/codex#32655 and #35871 are fixed (working invocation available now) #1740 elevated recipe, no degraded fallback) CORRECTION-NEEDED (8+1). One correction round (session-default agents — cross-model harness doc, no model pin per the profile's model-matching table); re-verified REVERIFY: PASS by both verifiers, 12/12 findings resolved, zero new findings. Records under .work/code-claude-com-docs-en-best-pr-9686dc16/verification/.
  • Profile applicability-filter clarification codified from that verification: a digested page that is itself a live code.claude.com harness doc serves as its own row-local basis for intrinsic harness-guidance claims; the boundary rule still routes API-surface-naming claims to mixed, with third-party APIs (e.g. the GitHub API) counting as API surfaces.
  • Knowledge plugin 0.10.40.10.5 with matching CHANGELOG entry.

Verification

  • markdownlint-cli2 on changed markdown: 0 errors
  • check-skill.sh docpage-digest (CHECK_SKILL_SKILLS_ROOT=plugins/knowledge/skills, base origin/main): PASS (1 pre-existing soft warning, SKILL.md length)
  • check-changelog-parity.sh --check-bump origin/main: PASS
  • Independent fresh-context reviewer on the diff: APPROVE (traced the changelog claims to the slice checklist and verification records; its one info-level attribution observation was applied before commit)
  • Base freshness: fetched origin/main immediately before commit; zero commits behind

No linked issue — this PR closes no GitHub issue; the doc queue is tracked in the profile file itself.

Related

🤖 Generated with Claude Code

…ompletion

Removes the code.claude.com best-practices entry (and its now-empty
"Applies across all of the above:" heading) from the docpage-digest
Anthropic profile's doc queue - the slice completed end-to-end (raw-md
fetch through interview handoff, dual verification with one correction
round, re-verified REVERIFY: PASS by both verifiers). Adds an
applicability-filter clarification from that verification (a live
code.claude.com harness doc is its own row-local basis; third-party
APIs count as API surfaces) and bumps the knowledge plugin
0.10.4 -> 0.10.5 with a matching CHANGELOG entry.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
@claude

claude Bot commented Jul 30, 2026

Copy link
Copy Markdown

Claude finished @kyle-sexton's task in 1m 45s —— View job


PR Review

  • Gather context and understand request
  • Read changed files and diff
  • Review plugin.json version bump
  • Review CHANGELOG.md entry
  • Review anthropic-docs-profile.md changes
  • Post findings

Three-file, three-concern diff: queue entry removal, filter-rule addition, and version bookkeeping. All three hang together correctly.

plugin.json — version bump (permalink): 0.10.4 → 0.10.5 is the right patch increment — profile prose update, no schema or API surface change.

CHANGELOG.md[0.10.5] section (permalink): Format is consistent with all prior entries (version heading, ### Changed, bold item labels). The two bullet points accurately mirror the two diffs in the profile: queue entry removal and filter-rule addition. The queue-entry bullet correctly notes that the emptied category heading goes with it — that's precisely what the diff shows.

anthropic-docs-profile.md — filter-rule addition (permalink): The new "Harness docs are their own live basis" bullet integrates cleanly as a fifth item in the filter list and is internally coherent — it scopes the own-basis rule to intrinsic harness-guidance claims while explicitly preserving the API-surface → mixed boundary and extending it to third-party APIs with a concrete example. Provenance attribution "(From the best-practices slice…)" follows the same pattern as the sonnet-5 ruling that precedes it.

anthropic-docs-profile.md — queue entry removal (permalink): The "Applies across all of the above:" heading and its sole entry are removed together, leaving a clean blank-line separator before "Blog posts:". No orphaned whitespace or list-structure gap.

Model-matching table (line 60): The parenthetical example "best practices" in the cross-model/harness-doc row still stands correctly as a category example independent of the queue — no update needed there.

REVIEW.md checks: No high-risk security actions, no multi-record writes with atomicity concerns — both mandatory checks from REVIEW.md are inapplicable to this all-markdown diff. Security lane has its own workflow; nothing to flag here.

No findings. The diff is correct, self-consistent, and follows the project's conventions. Ready to merge.

@claude

claude Bot commented Jul 30, 2026

Copy link
Copy Markdown

Claude finished @kyle-sexton's task in 57s —— View job


Security Review — PR #1765

  • Gather context: read PR diff and changed files
  • Analyze for security issues (logic flaws, injection, secrets, auth gaps, trust-boundary issues)
  • Post findings

No security findings.

The three changed files are pure documentation/prose:

  1. plugin.json — patch version bump (0.10.4 → 0.10.5), no schema, dependency, or permission changes.
  2. CHANGELOG.md — changelog prose only; no executable content.
  3. anthropic-docs-profile.md — two changes:
    • Removes a completed doc-queue URL entry (https://code.claude.com/docs/en/best-practices) and its now-empty category heading. The removal is consistent — no orphaned heading, no dangling cross-references.
    • Adds an applicability-filter clarification bullet. The new rule codifies that third-party APIs (e.g. the GitHub API) count as API surfaces with "no vendor exemption." This tightens the existing boundary rule rather than relaxing it, closing a potential loophole where a third-party API claim could have been argued into the narrower cc-applicable tag.

Checked and found nothing in scope for this review lane:

  • No secrets, tokens, credentials, or PII in any changed file.
  • No new outbound URLs, webhooks, or network call surfaces introduced.
  • No injection surfaces — the profile is prompt/instruction content authored by the repo maintainer with no user-controlled interpolation paths.
  • No trust-boundary relaxations in the applicability-filter rules.
  • No plugin manifest permission widening.
  • No GitHub Actions workflow files touched.

@kyle-sexton
kyle-sexton merged commit d783ada into main Jul 30, 2026
31 checks passed
@kyle-sexton
kyle-sexton deleted the chore/docqueue-best-practices-complete branch July 30, 2026 02:36
kyle-sexton added a commit that referenced this pull request Jul 30, 2026
…slice completion (#1775)

## Summary

- Removes the reduce-hallucinations guardrail entry from the
`docpage-digest` Anthropic profile's doc queue — its slice completed
end-to-end (fetch through interview handoff) per the queue's
remove-on-completion rule. The increase-consistency guardrail entry
remains queued, so the "Guardrail guides" heading stays.
- Channel: raw-md (`.md` appended to the page URL; HTTP 200, 49 lines /
6,309 bytes — channel re-verified for this page, no degradation);
provenance recorded in the slice checklist.
- Slice verification: Verifier A (same-vendor, fresh context) PASS with
2 advisories; Verifier B (cross-vendor Codex CLI 0.146.0 via the issue
#1740 elevated recipe, no degraded fallback) CORRECTION-NEEDED (5+3, two
findings against INDEX.md). Two correction rounds (session-default
agents — guardrail guide, no model pin per the profile's model-matching
table; round 2 fixed one pre-existing finding the round-1 re-verify
newly detected plus a Verifier A advisory); final state REVERIFY2: PASS
from both verifiers, zero new correction-needed findings (one
non-blocking pre-existing narrowing note recorded in reverify2-a).
Records under
`.work/platform-claude-com-docs-en-tes-2baa7563/verification/`.
- No profile-learning bullet this run: the one generalizable-ruling
candidate (the unverified-inference marker threshold for
adjacent/mechanism-level harness support) was deliberately escalated to
the interview by both verifiers rather than settled — codifying it now
would front-run that open question.
- Knowledge plugin `0.10.5` → `0.10.6` with matching CHANGELOG entry.

## Verification

- `markdownlint-cli2` on changed markdown: 0 errors
- `check-skill.sh docpage-digest`
(`CHECK_SKILL_SKILLS_ROOT=plugins/knowledge/skills`, base
`origin/main`): PASS (1 pre-existing soft warning, SKILL.md length)
- `check-changelog-parity.sh --check-bump origin/main`: PASS (re-run
after rebasing onto the new changelog-order gate commit; 0.10.6 ordering
conforms)
- Independent fresh-context reviewer on the diff: APPROVE (traced the
changelog claims to the slice checklist and verification records;
applied its rebase-before-PR recommendation)
- Base freshness: rebased onto origin/main immediately before commit;
zero commits behind

No linked issue — this PR closes no GitHub issue; the doc queue is
tracked in the profile file itself.

## Related

- #1765 (previous doc-queue completion in this series — best-practices
slice)
- #1740 (Verifier B elevated recipe used for cross-vendor verification)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
kyle-sexton added a commit that referenced this pull request Jul 31, 2026
…ry (#1868)

## Summary

The thinking-steering-and-cost platform doc slice completed, so its
entry leaves the
`docpage-digest` Anthropic profile's doc queue per the queue's
remove-on-completion rule. The
now-empty "Thinking" category heading goes with it — that category held
two overlapping docs
digested one page per run under its own contract, and the run-9 entry's
PR (#1842) removed the
first while anticipating this removal taking the heading.

Knowledge bumps 0.10.10 → 0.10.11 so consumers receive the queue change.

## Verification

Dual verification reached PASS on both arms against **identical frozen
bytes** — a SHA-256 pin of
all nine slice files, with the tree quiesced before either arm audited,
per the frozen-tree rule
this campaign adopted after a concurrent-correction race produced a
spurious MAJOR.

- **Arm B (cross-vendor, Codex)** — `VERDICT: PASS`, `FINDINGS: none`,
six checks PASS, three
  round-1 findings RESOLVED.
- **Arm A (same-vendor, fresh context, rationale withheld)** —
`REVERIFY2: PASS`, six checks PASS,
five prior findings RESOLVED, three MINORs, all record-keeping and none
touching fidelity.
Fidelity was swept mechanically: all 108 quoted spans across the six
digests are exact substrings
of the single source line each cites, 0 misses. Tag census 41
`cc-applicable` / 28 `mixed` /
  12 `api-only` = 81 rows, exactly one vocabulary tag per row.

The three MINORs were remediated after the verdicts without altering any
claim row: two stale
self-check footer records got dated "historical as of" annotations, and
the missing round-2/3
applied record was written. The slice's `interview-handoff.md` was
independently re-validated
against the corrected digest bytes by a separate agent and its five
stale items corrected.

No degraded fallback was used at any point.

Three findings from this run carry to the batched dispositions interview
rather than this PR: the
absence of any cross-digest citation-consistency check in the
verification contract, the absence of
a required applied-record artifact per correction round, and a genuine
unharmonized cross-source
tension about where a resolved effort value physically lives.

## Related

- Follows #1842 (run 9, the paired thinking doc), which removed the
first entry of this category.
- Same campaign as #1816, #1788, #1779, #1775, #1765, #1761, #1756,
#1752.

No linked issue.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
kyle-sexton added a commit that referenced this pull request Aug 1, 2026
…ge-digest queue (#1874)

The `platform.claude.com/docs/en/release-notes/system-prompts` slice
completed. It is the **last entry in the doc queue** — after this
merges, the queue section holds only the deferred task-budgets trigger
entry, which was never queued.

## What ran

The largest slice this pipeline has processed: **18 digests over a
2,548-line source, 659 claim rows, 561 `api-only`.**

- Seven correction rounds and five dual-verification rounds, each on
SHA-256-pinned bytes with the frozen-tree rule enforced — both arms
re-hash before *and* after auditing, and no correction runs while a
verifier holds the tree.
- Final state: both arms `VERDICT: PASS`, with a confirming round after
the last corrections.
- Final gates: **1,895 recorded command/count pairs replay with 0
mismatches**, 0 `<corpus>` placeholders, 659/659 rows parse with `N.
Quote (line` count equal to `- Tag:` count in all 18 digests, every
stated tally equal to its anchored `grep -c`, `check-quotes.py` clean.

## What the run found worth carrying forward

- **Narrow-slug false absences** remained the dominant defect — a basis
testing one literal while the corpus documents the same concept in other
words. Rows now disclose near-misses by name and line, each produced by
a command recorded in that row.
- **Prose is unparsed by every gate.** Summary paragraphs, Implications
bullets and Open questions carried stale counts and false statements
across several rounds; two sweeps (one whitespace-normalized with an
offset map back to physical lines) closed the class.
- **A contested tag-ordering question is escalated, not decided** —
whether selecting a positive tag requires first establishing harness
applicability. It is written up as a candidate profile amendment with
both readings, the evidence, and a recommendation, for the dispositions
interview.

Residual MINOR findings are disclosed in the slice's
`interview-handoff.md` as Open questions, per the run's stopping rule.

## What this PR changes

- Removes the system-prompts entry and the now-empty "Supplementary
references" heading from the profile's Doc queue.
- Bumps the `knowledge` plugin `0.10.13` → `0.10.14`.
- Adds the matching CHANGELOG entry.

No linked issue

## Related

- Third and final of the serialized run-11 queue PRs, after #1872
(resources overview) and #1873 (verification-loops blog). All three
touch the same profile file, so they merged one at a time.
- Completes the queue drain begun in #1752 and continued through #1756,
#1761, #1765, #1775, #1779, #1788, #1816, #1842 and #1868.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant