claude-code-kit 0.67.0__tar.gz → 0.69.0__tar.gz

{claude_code_kit-0.67.0 → claude_code_kit-0.69.0}/.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
       "name": "claude-kit",
       "source": "./",
       "description": "Cookiecutter-style scaffolder for an autonomous Claude Code SDLC config (no app code, no Docker): install CLAUDE.md + .claude/ (rules, the profile's agents/skills, hooks, artifact templates) + optional .mcp.json, then run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates, working memory, and a self-improving learnings loop.",
-      "version": "0.67.0",
+      "version": "0.69.0",
       "license": "MIT",
       "keywords": ["sdlc", "agents", "orchestration", "quality-gates", "workflow", "scaffold", "cookiecutter"]
     }

{claude_code_kit-0.67.0 → claude_code_kit-0.69.0}/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-kit",
-  "version": "0.67.0",
+  "version": "0.69.0",
   "description": "Cookiecutter-style scaffolder for an autonomous Claude Code SDLC config (no app code, no Docker). `claude-kit init` asks ordered questions and installs CLAUDE.md + .claude/ (rules, the profile's agents/skills, hooks, artifact templates) + optional .mcp.json; run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates with working memory and a self-improving learnings loop.",
   "author": {
     "name": "Arjunsingh Yadav",

{claude_code_kit-0.67.0 → claude_code_kit-0.69.0}/CHANGELOG.md

@@ -4,6 +4,181 @@ All notable changes to claude-kit are documented here. The format follows
 [Keep a Changelog](https://keepachangelog.com/), and the project uses
 [semantic versioning](https://semver.org/).
 
+## [0.69.0] — 2026-07-26
+
+**Absorption pass over [pborenstein/handoff](https://github.com/pborenstein/handoff) (user-named
+source; MIT, © 2026 Philip Borenstein) — session-continuity skills built around a hot-state /
+cold-storage split.** Ideas absorbed in the kit's own words with attribution; zero prose copied.
+All 18 repo files read; 7 candidate disciplines extracted and adversarially verified against the
+live kit (one verify agent per candidate, every verdict with file:line citations); 4 adopted,
+3 deliberately not. **0 new agents/skills/rules/hooks — every adoption is a prose/script extension
+of an existing surface.**
+
+### Added
+- **Size budget & rotation for working memory** (`rules/continuity.md` §"Size budget & rotation",
+  the CONTINUITY template header, and the `load-continuity.sh` messages): the live
+  `.claude/CONTINUITY.md` now carries a **write-side budget — ~8,000 bytes / ~150 lines, the size
+  the SessionStart hook injects uncut** — and a rotation protocol: when a phase completes (or the
+  file nears the budget), compress it to 3–5 lines and move the displaced detail to
+  `.claude/state/continuity-archive.md`, an append-only cold file in the already-gitignored
+  runtime-state dir that is never auto-injected. Previously the only size control was the hook's
+  read-side middle-trim, which silently cuts exactly the sections resume depends on (Decisions
+  Made, Mistakes & Learnings); this repo's own live file had reached ~94 KB (11.7× the cap) —
+  empirical proof the soft "keep it short" rule doesn't hold without a number and a destination.
+  The trim notice and the hook's closing instruction now point at the rotation protocol.
+- **Upstream-currency check on resume** (`rules/continuity.md`, resume-snapshot section): the
+  existing `git.sha` comparison catches a checkout that *moved*; the new check catches one that is
+  **behind** — `git fetch`, then `git rev-list --left-right --count @{upstream}...HEAD`. Behind →
+  reconcile (usually `git pull --rebase`) before trusting the snapshot; diverged → stop and
+  reconcile before planning new work; no upstream / offline → advisory note, never a hard stop.
+  Rationale: snapshot and CONTINUITY timestamps are self-reported and can look fresh while commits
+  landed out-of-band (another worktree, a teammate, CI).
+- **7-day staleness warning** (`hooks/scripts/load-continuity.sh` + a Protocol note in
+  `rules/continuity.md`): the SessionStart hook now checks the live file's mtime (GNU/BSD-portable
+  `stat`, degrading to a silent no-op on any failure) and prepends a warning when the file hasn't
+  been written in 7+ days — stale working memory is historical context to verify against
+  `git log`/`git status`, not a plan to resume. Two new behavioral tests pin the warning and its
+  absence on fresh files.
+- **Retroactive ADR backfill** (`skills/documentation-and-adrs` §"Retroactive Backfill", plus a
+  Guidelines pointer in `skills/decision`): the process half of what the kit's ADR template
+  already anticipated with its "Reconstructed from `<source>`" provenance line — mine git history
+  for decision points (`git log --grep` on decide/choose/instead/switch/migrate/refactor), group
+  the history into 3–6 eras, write only the 5–10 decisions that **still constrain the code**,
+  time-box the exercise to hours, and stop: no ADR-per-commit, and no invented rationale — a
+  back-filled ADR that guesses at *why* is worse than no ADR.
+
+### Not adopted (deliberately)
+- **Uninitialized-directory guard** (handoff's report → suggest-init → STOP before wrapup/pickup
+  work) — the kit prevents this failure mode *by construction* rather than by detection:
+  `load-continuity.sh` seeds the live file from the (plugin-bundled) template and no-ops when
+  none exists, and the CLI already fails with "run `claude-kit init`" in `validate`, `upgrade`,
+  and `status`. A prose detection guard would duplicate the seeding subsystem.
+- **Per-phase chronicle files** (`docs/chronicles/phase-N.md` with slim numbered entries) — every
+  chronicle field already has a typed home in the kit (gate-evidence artifacts, the sprint
+  archive, ADRs, the CHANGELOG discipline, agent-memory decision traces), and `doc-consolidation`'s
+  posture is the inverse: harvest run-generated markdown *into* canonical stores, then delete. A
+  chronicles tree would be a fifth, competing history store; its one legitimate fragment —
+  spillover run history — is absorbed by the new CONTINUITY cold archive instead.
+- **Meta-repo pattern** (`project-repo`: a coordinating repo with explicitly-gitignored member
+  dirs and shared meta-level docs) — the kit is a per-project scaffolder and explicitly treats
+  repo layout as an organizational choice outside its prescription surface
+  (`system-design-patterns`); multi-repo *changes* and *comprehension* already have homes
+  (`planning-and-task-breakdown` §cross-service, `context-engineering`), and org scope distributes
+  packs into each repo's own install. Different axis; not adopted.
+- **Committed tracking files** (handoff commits its CONTEXT/IMPLEMENTATION/DECISIONS files) — the
+  kit deliberately keeps CONTINUITY gitignored (high diff churn) and routes durable content to
+  committed `agent-memory/` and ADRs; adopting committed hot state would reverse a documented
+  design decision (`rules/continuity.md` §CONTINUITY vs. agent-memory).
+- **The 50-line figure itself** — the kit's budget derives from its own hook's 8,000-byte
+  injection cap, not an imported constant.
+
+## [0.68.0] — 2026-07-24
+
+**Absorption pass over the [ashishps1](https://github.com/ashishps1) trilogy (user-named sources):
+[awesome-low-level-design](https://github.com/ashishps1/awesome-low-level-design) (GPL-3.0) ·
+[awesome-system-design-resources](https://github.com/ashishps1/awesome-system-design-resources)
+(GPL-3.0) · [awesome-engineering-articles](https://github.com/ashishps1/awesome-engineering-articles)
+(MIT).** Linked lessons © AlgoMaster.io; articles © their companies; the two GPL repos carry Java
+solution code — **ideas absorbed in our own words, zero code and zero prose copied**, attribution in
+every digest and `docs/influences.md`. Every one of the **596 listed items got a coverage-map row**;
+248 were triaged deep (all LLD lessons/problems, all fetchable system-design articles, and the 63
+engineering articles whose Topics tags hit the kit's gap surface — the user-approved
+triage-by-topic), 221 captures survived plain-HTTP fetching, and a **112-agent digest→verify
+pipeline classified 1,547 candidate patterns** against the live kit (390 absent / 621 partial /
+502 covered / 34 not-absorbable; 218/221 digests passed the 3-claim fidelity check, 3 honest
+thin-capture flags). The global refute ran in the main loop (no synth agent) and enforced the caps:
+**exactly 1 new skill, exactly 6 SDP/DSP changes, exactly 1 convergence-justified extension.**
+
+### Added
+- **`object-oriented-design` collection skill** — the class-level (LLD) design layer the kit
+  previously carried only in digests: OOP pillars as design decisions (encapsulation as invariant
+  enforcement, composition-first inheritance discipline, runtime-type-checks as a
+  missing-abstraction smell), class relationships (association/aggregation/composition/dependency
+  decision axes, unidirectional-by-default references), SOLID/DRY/YAGNI/KISS as decision heuristics
+  (cross-linked to `over-engineering-review`, never duplicated), the **22-pattern GoF selection
+  table** (problem shape → pattern → trade-off → digest), UML as communication (five diagram types,
+  tool-neutral and text-first), concurrency-primitive **vocabulary** (mutex/semaphore/CAS, the
+  predicate re-check loop — flagged independently by four lessons — Coffman-condition deadlock
+  prevention; practice cross-linked to `async-python-patterns` and `python-dao-and-database`), and
+  the **33-problem → pattern map**. 94 attributed `alld-` digests in `references/`.
+- **Three coverage maps** — [`docs/lld-catalog.md`](docs/lld-catalog.md) (113 rows),
+  [`docs/system-design-resources.md`](docs/system-design-resources.md) (140 rows),
+  [`docs/engineering-articles.md`](docs/engineering-articles.md) (343 rows with Topics/Year
+  metadata and per-row triage outcome): every item's fetch status, digest location, and kit
+  outcome — including honest "not fetched" rows for hosts that refuse plain-HTTP clients.
+- **Six capped changes to the two 0.67.0 skills** (each gap re-verified against the live kit
+  during the main-loop refute):
+  - `system-design-patterns` §*Edge and traffic path* — forward vs reverse proxy, the ordered
+    API-gateway pipeline, DNS as a design surface (TTL as a failover lever), client- vs
+    server-side service discovery, least-response-time routing, series-vs-parallel availability
+    math and the three-condition SPOF test.
+  - `system-design-patterns` §*Realtime transport* — the short-poll → long-poll → SSE → WebSocket
+    selection ladder on two axes (direction × frequency); middlebox compatibility; "late-or-lost"
+    as the transport question; connection-count autoscaling, drain-on-deploy, and
+    thundering-herd-bounded node sizing for persistent-connection tiers (previously the kit taught
+    only the WebSocket branch).
+  - `system-design-patterns` §*Choosing the datastore* — access-pattern-first SQL-vs-NoSQL
+    framework, ACID as working vocabulary, index selectivity, latency-vs-throughput as
+    independent axes.
+  - `distributed-systems-patterns` §*Distributed locking and fencing* — efficiency-vs-correctness
+    lock triage, why TTL leases break under pauses, **fencing tokens** (the resource is the final
+    arbiter), fence-the-old-primary at failover scale, idempotent/monotonic writes as the
+    lock-free alternative.
+  - `distributed-systems-patterns` §*Batch vs stream processing* — bounded-vs-unbounded input as
+    the primary fork, windowed aggregation, failure granularity, micro-batching, batch resource
+    windows.
+  - `distributed-systems-patterns` — a **consensus paragraph** in §Replication and quorum (leader
+    election + replicated log + majority commit; when consensus is needed vs when
+    leader-follower + quorums suffice; never hand-roll). This makes the 0.67.0 pointer in
+    `system-design-patterns` §Service decomposition — which already delegated "consensus" here —
+    actually true.
+- **`deprecation-and-migration` §Shadow Verification Before Cutover** — the one
+  convergence-justified extension beyond the two pattern skills (five independent sources:
+  shadow reads with per-item fallback, budgeted dark traffic with a mismatch-rate SLO as the
+  cutover gate, dark launches for protocol swaps, logical-before-physical staging, fast reversible
+  cutover with parity watermarks).
+- **121 further digests** filed references-only across the owning skills with zero SKILL.md
+  changes — `system-design-patterns` ×58, `distributed-systems-patterns` ×40 (net of the
+  extension-feeding digests above), plus `api-and-interface-design` ×4, `otel-tracing` ×3,
+  `debugging-and-error-recovery` ×2, `python-dao-and-database` ×2, and one each in
+  `observability-and-logging`, `over-engineering-review`, `code-simplification`, `bug-hunt`,
+  `graphql-patterns`, preserving the covered-vs-extended distinction.
+
+### Changed
+- `rules/design-patterns.md` — the existing skill pointer gains one clause routing class-level
+  object design (SOLID trade-offs, GoF selection, UML, concurrency primitives) to
+  `object-oriented-design` (the only always-loaded touch).
+- Count anchors: **108 skills (57 core + 51 stack-collection)** in `README.md`,
+  `docs/stack-skills/README.md` (+1 catalog row), and `docs/skill-audit.md`.
+- `docs/influences.md` — one combined trilogy row with per-repo license notes.
+
+### Not adopted (deliberately)
+- **GPL-3.0 solution code (33 LLD problems, Java)** — never copied, in any form: the harvest
+  fetched only the problem statements; digests describe entities, state machines, and pattern
+  choices in prose; a pre-commit grep gate confirms zero code fences across all `alld-` digests.
+- **YouTube videos (44), courses, books, newsletters** — note-only rows; the kit absorbs written
+  engineering substance it can verify, not video content.
+- **The 10 classic distributed-systems papers** (Paxos, Dynamo, GFS, Bigtable, Spanner, LSM, …) —
+  note-only rows; their kit-relevant concepts are taught by `distributed-systems-patterns`
+  (quorums, consensus, storage engines, locking) and `rules/resilience-engineering.md`, and a
+  paper-summary layer would duplicate them.
+- **280 of the 343 engineering articles** — topics outside the kit's gap surface (125 are
+  ai/ml-tagged: recommender systems, model serving, GenAI product work — out of scope for a
+  stack-agnostic SDLC configuration kit). All noted with Topics/Year in the coverage map.
+- **A §End-to-end integrity (checksums) section** — killed by the refute to hold the ≤6 cap: the
+  gap is real but narrower than the six shipped (threat-model-driven checksum selection and
+  windowed integrity validation live on as digests in `distributed-systems-patterns/references/`).
+- **An outbox/CDC extension** to `kafka-config-driven` — three independent ABSENT votes make it a
+  genuine gap, but it exceeded this release's extension budget; digests filed
+  (`asdr-022`, `asdr-042`), explicitly a candidate for the next pass.
+- **123 of the 130 machine-proposed extension candidates** — killed in the main-loop refute:
+  covered on re-grep, digest-sufficient, composite repeats, or they would duplicate the
+  always-loaded `resilience-engineering` rule (constant-work fallbacks, RTO/RPO sizing,
+  retry-feedback loops).
+- **Raw captures** — never committed: the gitignored harvest scratch is deleted before commit;
+  27 items that refused plain-HTTP fetching (Medium/Cloudflare bot walls, dead Substack
+  redirects, one unreachable host) are honest "not fetched" map rows — no mirrors, no bypasses.
+
 ## [0.67.0] — 2026-07-24
 
 **System-design absorption pass from

{claude_code_kit-0.67.0 → claude_code_kit-0.69.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-code-kit
-Version: 0.67.0
+Version: 0.69.0
 Summary: Cookiecutter-style scaffolder for an autonomous Claude Code SDLC configuration (no app code, no Docker). Asks ordered questions and installs CLAUDE.md + .claude/ (rules, the chosen profile's agents/skills, hooks, artifact templates) + optional .mcp.json; run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates, working memory, and a self-improving learnings loop.
 Project-URL: Homepage, https://github.com/ajyadav013/claude-kit
 Project-URL: Repository, https://github.com/ajyadav013/claude-kit
@@ -146,7 +146,7 @@ claude-kit init --defaults      # non-interactive: React + Python/FastAPI + Post
 |------|--------------|
 | 🔁 **Pipeline & quality gates** | Gate-enforced progression — a phase advances only with zero open Critical/High/Medium findings — plus a fast-track for small changes and an anti-sycophancy `devils-advocate` pass |
 | 🤖 **Agent roster** | **28** tiered agents led by an Orchestrator that never writes code, plus per-database overlay agents and 6 org personas ([full roster](docs/agents.md)) |
-| 📐 **Rules & skills** | **25** stack-agnostic core rules + **107** context-activated skills (57 core + 50 stack-collection), pulled into context on demand |
+| 📐 **Rules & skills** | **25** stack-agnostic core rules + **108** context-activated skills (57 core + 51 stack-collection), pulled into context on demand |
 | 🧱 **Stacks & overlays** | A stack-agnostic core + **13** overlay rule files (React · FastAPI · Go · Postgres · Mongo) wired to your exact commands and path-scoped to load only when you touch matching files |
 | 🛠️ **Hooks & guards** | **18** event hooks — deterministic safety guards and advisory warnings — that no-op gracefully without `jq` |
 | 📦 **Distribution & lifecycle** | Plugin **and** pip from one source, **24** ready MCP fragments (version-pinned), edit-preserving `upgrade`, and a root `AGENTS.md` at init so non-Claude agents share the same standards |
@@ -225,7 +225,7 @@ PostgreSQL project, individual scope:
 |---------|-------:|-------:|------:|
 | `lean` | 8 | 15 | 36 |
 | `standard` (default) | 26 | 43 | 36 |
-| `enterprise` | 31 | 107 | 36 |
+| `enterprise` | 31 | 108 | 36 |
 
 - **Rules are profile-independent** — every profile installs the same 25 core rules + the selected
   stack's overlays (11 for this stack = 36); rigor changes the *agents and gates*, not the rule set.
@@ -251,7 +251,7 @@ that matters most: **native gives you the agents; claude-kit gives you the gover
 | **[wshobson/agents](https://github.com/wshobson/agents)** & similar collections | Large libraries of individual subagent prompts you pick from | A smaller, opinionated set wired into a sequenced pipeline — agents are stages that hand off and block on each other, not a menu |
 | **[GitHub spec-kit](https://github.com/github/spec-kit)** | Spec-driven development as a platform: constitution → spec → tasks → analyze, plus label-driven CI stages | The same coverage-gate idea absorbed into a broader in-session lifecycle — review, security, build, test, release, and observability gates with enforced severity blocking. Complementary: their CI stages, this kit's gate depth ([details](docs/autonomous-operation.md)) |
 | **claude-flow / multi-agent runtimes** | Runtime orchestrators that *execute* swarms of agents | Portable configuration, not a running process — no daemon, no lock-in, no app code |
-| **dotfiles / `CLAUDE.md` starters** | A single rules file or settings snippet | A catalog-driven generator: resolves your stack/profile/scope into the right subset of 25 rules, 28 agents, 107 skills, gates, and hooks — kept upgradeable with your edits preserved |
+| **dotfiles / `CLAUDE.md` starters** | A single rules file or settings snippet | A catalog-driven generator: resolves your stack/profile/scope into the right subset of 25 rules, 28 agents, 108 skills, gates, and hooks — kept upgradeable with your edits preserved |
 
 **Choose claude-kit when** you want a consistent, gate-enforced autonomous-SDLC setup that's the
 same across every repo and stack, installs in seconds, and ships nothing you have to run. It is

{claude_code_kit-0.67.0 → claude_code_kit-0.69.0}/README.md

@@ -113,7 +113,7 @@ claude-kit init --defaults      # non-interactive: React + Python/FastAPI + Post
 |------|--------------|
 | 🔁 **Pipeline & quality gates** | Gate-enforced progression — a phase advances only with zero open Critical/High/Medium findings — plus a fast-track for small changes and an anti-sycophancy `devils-advocate` pass |
 | 🤖 **Agent roster** | **28** tiered agents led by an Orchestrator that never writes code, plus per-database overlay agents and 6 org personas ([full roster](docs/agents.md)) |
-| 📐 **Rules & skills** | **25** stack-agnostic core rules + **107** context-activated skills (57 core + 50 stack-collection), pulled into context on demand |
+| 📐 **Rules & skills** | **25** stack-agnostic core rules + **108** context-activated skills (57 core + 51 stack-collection), pulled into context on demand |
 | 🧱 **Stacks & overlays** | A stack-agnostic core + **13** overlay rule files (React · FastAPI · Go · Postgres · Mongo) wired to your exact commands and path-scoped to load only when you touch matching files |
 | 🛠️ **Hooks & guards** | **18** event hooks — deterministic safety guards and advisory warnings — that no-op gracefully without `jq` |
 | 📦 **Distribution & lifecycle** | Plugin **and** pip from one source, **24** ready MCP fragments (version-pinned), edit-preserving `upgrade`, and a root `AGENTS.md` at init so non-Claude agents share the same standards |
@@ -192,7 +192,7 @@ PostgreSQL project, individual scope:
 |---------|-------:|-------:|------:|
 | `lean` | 8 | 15 | 36 |
 | `standard` (default) | 26 | 43 | 36 |
-| `enterprise` | 31 | 107 | 36 |
+| `enterprise` | 31 | 108 | 36 |
 
 - **Rules are profile-independent** — every profile installs the same 25 core rules + the selected
   stack's overlays (11 for this stack = 36); rigor changes the *agents and gates*, not the rule set.
@@ -218,7 +218,7 @@ that matters most: **native gives you the agents; claude-kit gives you the gover
 | **[wshobson/agents](https://github.com/wshobson/agents)** & similar collections | Large libraries of individual subagent prompts you pick from | A smaller, opinionated set wired into a sequenced pipeline — agents are stages that hand off and block on each other, not a menu |
 | **[GitHub spec-kit](https://github.com/github/spec-kit)** | Spec-driven development as a platform: constitution → spec → tasks → analyze, plus label-driven CI stages | The same coverage-gate idea absorbed into a broader in-session lifecycle — review, security, build, test, release, and observability gates with enforced severity blocking. Complementary: their CI stages, this kit's gate depth ([details](docs/autonomous-operation.md)) |
 | **claude-flow / multi-agent runtimes** | Runtime orchestrators that *execute* swarms of agents | Portable configuration, not a running process — no daemon, no lock-in, no app code |
-| **dotfiles / `CLAUDE.md` starters** | A single rules file or settings snippet | A catalog-driven generator: resolves your stack/profile/scope into the right subset of 25 rules, 28 agents, 107 skills, gates, and hooks — kept upgradeable with your edits preserved |
+| **dotfiles / `CLAUDE.md` starters** | A single rules file or settings snippet | A catalog-driven generator: resolves your stack/profile/scope into the right subset of 25 rules, 28 agents, 108 skills, gates, and hooks — kept upgradeable with your edits preserved |
 
 **Choose claude-kit when** you want a consistent, gate-enforced autonomous-SDLC setup that's the
 same across every repo and stack, installs in seconds, and ships nothing you have to run. It is