Skip to content

chore(knowledge): retire context-engineering blog doc-queue entry after slice completion - #1756

Merged
kyle-sexton merged 1 commit into
mainfrom
chore/docqueue-context-engineering-blog-complete
Jul 29, 2026
Merged

chore(knowledge): retire context-engineering blog doc-queue entry after slice completion#1756
kyle-sexton merged 1 commit into
mainfrom
chore/docqueue-context-engineering-blog-complete

Conversation

@kyle-sexton

@kyle-sexton kyle-sexton commented Jul 29, 2026

Copy link
Copy Markdown
Contributor

Summary

  • Removes the new-rules-of-context-engineering blog 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.
  • Channel: rendered (raw-md confirmed absent for this page — .md probe 404, Accept: text/markdown ignored — matching the profile's blog-post channel note); source.html unaltered original + firecrawl 1.19.27 markdown extraction, artifacts 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 (10+1). All findings applied; cross-vendor re-verify round 1 resolved all 15 and surfaced 2 correction-introduced issues; round 2 REVERIFY2: PASS. Records under .work/claude-com-blog-the-new-rules-o-8e418fc0/verification/.
  • Knowledge plugin 0.10.20.10.3 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 non-blocking wording observation was applied before commit)
  • Base freshness: fetched origin/main immediately before commit; zero commits behind

Related

🤖 Generated with Claude Code

…er slice completion

The new-rules-of-context-engineering blog digest slice completed end-to-end
(rendered-channel fetch through interview handoff; Verifier A and cross-vendor
Verifier B both returned corrections, all applied and cross-vendor re-verified
to PASS), so its entry leaves the Anthropic profile's doc queue per the queue's
remove-on-completion rule.

Knowledge plugin 0.10.2 -> 0.10.3 with CHANGELOG entry (changelog-parity green).

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

claude Bot commented Jul 29, 2026

Copy link
Copy Markdown

Claude finished @kyle-sexton's task in 44s —— View job


Security Review

  • Gather PR diff and changed files
  • Review changed files for security issues
  • Report findings

No security issues found.

This PR makes three changes, none of which introduce a security-relevant surface:

  1. plugin.json — semver version bump 0.10.20.10.3. No code execution, no credential handling, no dependency changes, no trust-boundary effects.

  2. CHANGELOG.md — prose documentation of the completed slice. No executable content, no secrets, no injection vectors.

  3. anthropic-docs-profile.md — removes one URL entry from the doc queue list. The removed line is a plain markdown autolink to a public claude.com/blog page. No template expansion, no command interpolation, and no access-control or authorization implications follow from removing a queue entry.

The remaining URLs in the profile file are all to public Anthropic documentation properties (platform.claude.com, code.claude.com, claude.com/blog). No supply-chain or egress concerns.

@claude

claude Bot commented Jul 29, 2026

Copy link
Copy Markdown

Claude finished @kyle-sexton's task in 44s —— View job


PR Review

  • Gather context
  • Review changed files
  • Post findings

Verdict: LGTM — no issues found.

The three-file diff is internally consistent and follows the established patterns for this plugin.

plugin.json — version bump
0.10.20.10.3: correct semver tier for a content-only change (no behavior, no interface, no schema delta). Matches the CHANGELOG entry exactly.

CHANGELOG.md — new [0.10.3] section
Lines 7–16: entry follows the same structure and level of detail as the prior two versions (0.10.1, 0.10.2). Channel selection rationale (rendered, raw-md probe 404), verification outcome summary (both verifiers returned corrections, all applied, cross-vendor re-verify PASS), and the triggering rule (remove-on-completion) are all documented. No gaps.

anthropic-docs-profile.md — queue removal
Two lines removed: only the completed entry is excised; the surrounding queue entries and file structure are undisturbed. The remaining queue entries (claude-models-explained, building-verification-loops) are still present and correctly formatted.

Cross-checks

  • PR description's claimed verification results (markdownlint 0 errors, check-skill.sh PASS, check-changelog-parity.sh PASS) are consistent with the size and nature of the diff.
  • No hardcoded paths, PII, or secrets introduced.
  • Change is repo-agnostic (profile context file, not plugin engine).

@kyle-sexton
kyle-sexton merged commit 3468867 into main Jul 29, 2026
31 of 33 checks passed
@kyle-sexton
kyle-sexton deleted the chore/docqueue-context-engineering-blog-complete branch July 29, 2026 21:45
kyle-sexton added a commit that referenced this pull request Jul 30, 2026
…ompletion (#1761)

## Summary

- Removes the prompting-claude-sonnet-5 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 last remaining per-model guide, so the emptied category heading
goes with it.
- Channel: raw-md (`.md` appended to the page URL; HTTP 200, 15,864
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 (3+5); Verifier B (cross-vendor Codex CLI 0.146.0 via
the issue #1740 elevated recipe, no degraded fallback) CORRECTION-NEEDED
(21+1). Three correction rounds (round 3 orchestrator-approved per the
>2-round rule; digest corrections applied by subject-model-pinned
agents), re-verified each round; final state REVERIFY3: PASS from both
verifiers. Records under
`.work/platform-claude-com-docs-en-bui-1b530928/verification/`.
- Profile applicability-filter clarifications codified from that
verification's binding rulings: evidence is row-local ("same basis as
claim N" never satisfies the contract), and `unverified-inference` is an
additional uncertainty marker, never a substitute for the
`cc-applicable`/`api-only`/`mixed` tag; the sibling positive-claims
bullet now says "additionally recorded" to close the substitute-tag
misreading at its origin.
- Knowledge plugin `0.10.3` → `0.10.4` 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 non-blocking wording 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

- #1756 (previous doc-queue completion in this series —
context-engineering blog 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