<feed xmlns='http://www.w3.org/2005/Atom'>
<title>claude-plugins-official.git/plugins, branch morganl/code-modernization-plugin</title>
<subtitle>Official Claude Code plugin directory
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/'/>
<entry>
<title>code-modernization: harden writes a patch instead of editing legacy; make map/security guidance language-agnostic</title>
<updated>2026-05-11T23:46:03+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-05-11T23:46:03+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=5e4a45001d608ce34437181d96340faa1f5899c9'/>
<id>5e4a45001d608ce34437181d96340faa1f5899c9</id>
<content type='text'>
- modernize-harden: never edits legacy/ anymore. Writes findings plus a
  reviewed unified diff to analysis/&lt;system&gt;/security_remediation.patch.
  A second security-auditor pass reviews each hunk (RESOLVES / PARTIAL /
  INTRODUCES-RISK) before presenting. The user reviews and applies the
  patch deliberately, then re-runs to verify. This makes every command
  consistent with the recommended deny Edit(legacy/**) workspace setting,
  so the README's exception note is gone.
- modernize-map: restructure the parse-target list around three stack-
  agnostic principles (dispatcher targets are variables; code-storage
  joins live in config; entry points live in deployment descriptors), with
  COBOL/Java/web/CLI examples on equal footing rather than COBOL-dominant.
  Same protections against false dead-code findings, less stack-specific.
- security-auditor agent: rephrase coverage items in stack-neutral terms
  (record layouts/temp datasets, resource ACLs, deployment scripts/job
  definitions, batch input records) so the checklist reads naturally for
  COBOL, Java EE, .NET, and web targets alike.
- README: drop the harden exception note; describe the patch workflow.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- modernize-harden: never edits legacy/ anymore. Writes findings plus a
  reviewed unified diff to analysis/&lt;system&gt;/security_remediation.patch.
  A second security-auditor pass reviews each hunk (RESOLVES / PARTIAL /
  INTRODUCES-RISK) before presenting. The user reviews and applies the
  patch deliberately, then re-runs to verify. This makes every command
  consistent with the recommended deny Edit(legacy/**) workspace setting,
  so the README's exception note is gone.
- modernize-map: restructure the parse-target list around three stack-
  agnostic principles (dispatcher targets are variables; code-storage
  joins live in config; entry points live in deployment descriptors), with
  COBOL/Java/web/CLI examples on equal footing rather than COBOL-dominant.
  Same protections against false dead-code findings, less stack-specific.
- security-auditor agent: rephrase coverage items in stack-neutral terms
  (record layouts/temp datasets, resource ACLs, deployment scripts/job
  definitions, batch input records) so the checklist reads naturally for
  COBOL, Java EE, .NET, and web targets alike.
- README: drop the harden exception note; describe the patch workflow.
</pre>
</div>
</content>
</entry>
<entry>
<title>Harden code-modernization plugin from a real CardDemo dry run</title>
<updated>2026-05-11T23:28:27+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-05-11T23:28:27+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=22a1b2597750246f104c88e66f0c379932d05c9b'/>
<id>22a1b2597750246f104c88e66f0c379932d05c9b</id>
<content type='text'>
Fixes found by running the discovery workflow against the AWS CardDemo
mainframe sample (~50 KLOC of COBOL/CICS/JCL/BMS/VSAM):

- modernize-assess: add scc -&gt; cloc -&gt; find/wc fallback chain with the
  COCOMO-II formula so Step 1 works when scc isn't installed; same for
  portfolio-mode cloc/lizard. Drop the reference to a specific
  agent-spawning tool name (just "in parallel"). Sharpen the structural-
  map subagent prompt: 5-12 domains, subgraph clustering, ~40-edge cap,
  repo-relative paths, dangling-reference check.
- modernize-map: expand the parse-target list with the things a
  literal-minded reader would miss on a real mainframe codebase — CICS
  CSD DEFINE TRANSACTION/FILE for entry points and online file I/O,
  EXEC CICS file ops, SELECT...ASSIGN TO joined with JCL DD,
  EXEC SQL table refs (not JCL DD), SEND/RECEIVE MAP, dynamic
  data-name XCTL resolution, COBOL fixed-format column slicing. Without
  these the dead-code list is wrong (most CICS programs look unreachable).
  Also write a machine-readable topology.json alongside the summary.
- modernize-extract-rules: add a Priority (P0/P1/P2) field with a
  heuristic, and an optional Suspected-defect field. modernize-brief
  reads P0 rules to build the behavior contract, but the Rule Card had
  no priority slot — the chain was broken.
- modernize-brief: read the new P0 tags; flag low-confidence P0 rules as
  SME blockers.
- modernize-reimagine: drop "for the demo" wording.
- security-auditor agent: add mainframe/COBOL coverage items (RACF,
  JCL/PROC creds, BMS field validation, DB2 dynamic SQL, copybook PII)
  and mark web-only items as such so it adapts to the target stack.
- README: add Optional Tooling section and a symlink example for the
  expected layout.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fixes found by running the discovery workflow against the AWS CardDemo
mainframe sample (~50 KLOC of COBOL/CICS/JCL/BMS/VSAM):

- modernize-assess: add scc -&gt; cloc -&gt; find/wc fallback chain with the
  COCOMO-II formula so Step 1 works when scc isn't installed; same for
  portfolio-mode cloc/lizard. Drop the reference to a specific
  agent-spawning tool name (just "in parallel"). Sharpen the structural-
  map subagent prompt: 5-12 domains, subgraph clustering, ~40-edge cap,
  repo-relative paths, dangling-reference check.
- modernize-map: expand the parse-target list with the things a
  literal-minded reader would miss on a real mainframe codebase — CICS
  CSD DEFINE TRANSACTION/FILE for entry points and online file I/O,
  EXEC CICS file ops, SELECT...ASSIGN TO joined with JCL DD,
  EXEC SQL table refs (not JCL DD), SEND/RECEIVE MAP, dynamic
  data-name XCTL resolution, COBOL fixed-format column slicing. Without
  these the dead-code list is wrong (most CICS programs look unreachable).
  Also write a machine-readable topology.json alongside the summary.
- modernize-extract-rules: add a Priority (P0/P1/P2) field with a
  heuristic, and an optional Suspected-defect field. modernize-brief
  reads P0 rules to build the behavior contract, but the Rule Card had
  no priority slot — the chain was broken.
- modernize-brief: read the new P0 tags; flag low-confidence P0 rules as
  SME blockers.
- modernize-reimagine: drop "for the demo" wording.
- security-auditor agent: add mainframe/COBOL coverage items (RACF,
  JCL/PROC creds, BMS field validation, DB2 dynamic SQL, copybook PII)
  and mark web-only items as such so it adapts to the target stack.
- README: add Optional Tooling section and a symlink example for the
  expected layout.
</pre>
</div>
</content>
</entry>
<entry>
<title>Fix code-modernization plugin: align README with commands, fix pipeline gaps</title>
<updated>2026-05-11T23:17:59+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-05-11T23:17:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=718818146e93eeef3a94a3dac9ffa087558115cc'/>
<id>718818146e93eeef3a94a3dac9ffa087558115cc</id>
<content type='text'>
- modernize-brief: read TOPOLOGY.html (what modernize-map actually
  produces) instead of nonexistent TOPOLOGY.md, and tell the user which
  command produces each missing input.
- README: rewrite the Commands section to match actual command behavior —
  correct output filenames, ordering (brief is the synthesis/approval gate
  after discovery, not the first step), agent attributions, and required
  args. Add a workspace-layout note and an explicit callout that
  modernize-harden edits legacy/, which conflicts with the recommended
  deny rule. Reconcile the Overview and Typical Workflow sequences.
- modernize-assess: generalize the production-runtime overlay step so it
  no longer assumes a specific MCP server/tool; mark it optional. Fix
  app/jcl/ -&gt; legacy/$1/jcl/ for layout consistency.
- modernize-map: make TOPOLOGY.html self-contained (load Mermaid from a
  CDN) so it renders in any browser; drop assumptions about an external
  artifact renderer. Generalize the telemetry annotation note.
- business-rules-extractor agent: fix command cross-reference to the
  actual command name.
- plugin.json: include the brief step in the workflow description.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- modernize-brief: read TOPOLOGY.html (what modernize-map actually
  produces) instead of nonexistent TOPOLOGY.md, and tell the user which
  command produces each missing input.
- README: rewrite the Commands section to match actual command behavior —
  correct output filenames, ordering (brief is the synthesis/approval gate
  after discovery, not the first step), agent attributions, and required
  args. Add a workspace-layout note and an explicit callout that
  modernize-harden edits legacy/, which conflicts with the recommended
  deny rule. Reconcile the Overview and Typical Workflow sequences.
- modernize-assess: generalize the production-runtime overlay step so it
  no longer assumes a specific MCP server/tool; mark it optional. Fix
  app/jcl/ -&gt; legacy/$1/jcl/ for layout consistency.
- modernize-map: make TOPOLOGY.html self-contained (load Mermaid from a
  CDN) so it renders in any browser; drop assumptions about an external
  artifact renderer. Generalize the telemetry annotation note.
- business-rules-extractor agent: fix command cross-reference to the
  actual command name.
- plugin.json: include the brief step in the workflow description.
</pre>
</div>
</content>
</entry>
<entry>
<title>Add code-modernization plugin</title>
<updated>2026-04-24T19:52:02+00:00</updated>
<author>
<name>Morgan Westlee Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-04-24T19:44:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=bdca23e8e46f8832d0030c05804ae207786ae37f'/>
<id>bdca23e8e46f8832d0030c05804ae207786ae37f</id>
<content type='text'>
Structured workflow (assess → map → extract-rules → reimagine → transform →
harden) and specialist agents (legacy-analyst, business-rules-extractor,
architecture-critic, security-auditor, test-engineer) for modernizing legacy
codebases into current stacks.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Structured workflow (assess → map → extract-rules → reimagine → transform →
harden) and specialist agents (legacy-analyst, business-rules-extractor,
architecture-critic, security-auditor, test-engineer) for modernizing legacy
codebases into current stacks.
</pre>
</div>
</content>
</entry>
<entry>
<title>skill-creator: sync from anthropics/skills (drop ANTHROPIC_API_KEY requirement) (#1523)</title>
<updated>2026-04-23T19:02:26+00:00</updated>
<author>
<name>jschwar2552</name>
<email>jason@anthropic.com</email>
</author>
<published>2026-04-23T19:02:26+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=2a40fd2e7c52207aa903bd33fc4c65716126966e'/>
<id>2a40fd2e7c52207aa903bd33fc4c65716126966e</id>
<content type='text'>
Ports anthropics/skills#547 (b0cbd3d) so this repo matches the upstream
skills repo.

improve_description.py and run_loop.py now shell out to `claude -p` instead
of using the Anthropic SDK directly, so the description optimizer uses the
session's existing Claude Code auth and no longer requires a separate
ANTHROPIC_API_KEY. SKILL.md drops the stale extended-thinking reference and
adds guidance for updating an existing skill.

Several enterprise customers sync exclusively from this repo (not
anthropics/skills, whose README disclaims production use), so they have been
stuck on the old SDK-based path.</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Ports anthropics/skills#547 (b0cbd3d) so this repo matches the upstream
skills repo.

improve_description.py and run_loop.py now shell out to `claude -p` instead
of using the Anthropic SDK directly, so the description optimizer uses the
session's existing Claude Code auth and no longer requires a separate
ANTHROPIC_API_KEY. SKILL.md drops the stale extended-thinking reference and
adds guidance for updating an existing skill.

Several enterprise customers sync exclusively from this repo (not
anthropics/skills, whose README disclaims production use), so they have been
stuck on the old SDK-based path.</pre>
</div>
</content>
</entry>
<entry>
<title>Align mcp-server-dev skills with claude.com/docs connector guidance (#1418)</title>
<updated>2026-04-17T16:02:48+00:00</updated>
<author>
<name>Tobin South</name>
<email>tobin.south@gmail.com</email>
</author>
<published>2026-04-17T16:02:48+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=b00abee24ea2dd020f56fcb65e9fa3230522a3ec'/>
<id>b00abee24ea2dd020f56fcb65e9fa3230522a3ec</id>
<content type='text'>
- build-mcp-server: load llms-full.txt for Claude-specific context;
  add Phase 6 (test in Claude, review checklist, submit, ship plugin)
- references/auth.md: add Claude auth-type table, callback URL,
  not-supported list
- references/tool-design.md: add Anthropic Directory hard requirements
  (annotations, name length, read/write split, prompt-injection rule)
- build-mcp-app: add Claude host specifics (prefersBorder,
  safeAreaInsets, CSP) and submission asset specs; testing via
  custom connector
- build-mcpb: note remote servers are the recommended directory path</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- build-mcp-server: load llms-full.txt for Claude-specific context;
  add Phase 6 (test in Claude, review checklist, submit, ship plugin)
- references/auth.md: add Claude auth-type table, callback URL,
  not-supported list
- references/tool-design.md: add Anthropic Directory hard requirements
  (annotations, name length, read/write split, prompt-injection rule)
- build-mcp-app: add Claude host specifics (prefersBorder,
  safeAreaInsets, CSP) and submission asset specs; testing via
  custom connector
- build-mcpb: note remote servers are the recommended directory path</pre>
</div>
</content>
</entry>
<entry>
<title>Add Apache 2.0 LICENSE to session-report plugin (#1306)</title>
<updated>2026-04-10T19:46:37+00:00</updated>
<author>
<name>Noah Zweben</name>
<email>noahz@anthropic.com</email>
</author>
<published>2026-04-10T19:46:37+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=d19dab67e891a932a78d68ccc63b6580d4692c65'/>
<id>d19dab67e891a932a78d68ccc63b6580d4692c65</id>
<content type='text'>
Co-authored-by: Claude &lt;noreply@anthropic.com&gt;</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Co-authored-by: Claude &lt;noreply@anthropic.com&gt;</pre>
</div>
</content>
</entry>
<entry>
<title>Add per-day session timeline and collapse cache-breaks list</title>
<updated>2026-04-10T04:32:34+00:00</updated>
<author>
<name>Thariq Shihipar</name>
<email>thariq@anthropic.com</email>
</author>
<published>2026-04-10T02:07:37+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=9dc3809e747a4e7fd4a3dee56501e4f711693901'/>
<id>9dc3809e747a4e7fd4a3dee56501e4f711693901</id>
<content type='text'>
- analyze-sessions.mjs: track per-session start/end/tokens and emit
  by_day[] in JSON output (date, dow, tokens, peak concurrency,
  per-session spans). Hoist shared token-sum in commit loop.
- template.html: new "session timeline by day" section — horizontal
  day pills (% of total + session count) drive a lane-packed gantt of
  concurrent sessions, colored by project, with hover details and
  ←/→ keyboard nav. Extract drillList() helper and use it for both
  top-prompts and cache-breaks (5 visible + "show more" toggle).
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- analyze-sessions.mjs: track per-session start/end/tokens and emit
  by_day[] in JSON output (date, dow, tokens, peak concurrency,
  per-session spans). Hoist shared token-sum in commit loop.
- template.html: new "session timeline by day" section — horizontal
  day pills (% of total + session count) drive a lane-packed gantt of
  concurrent sessions, colored by project, with hover details and
  ←/→ keyboard nav. Extract drillList() helper and use it for both
  top-prompts and cache-breaks (5 visible + "show more" toggle).
</pre>
</div>
</content>
</entry>
<entry>
<title>Add session-report plugin</title>
<updated>2026-04-08T00:40:13+00:00</updated>
<author>
<name>Thariq Shihipar</name>
<email>thariq@anthropic.com</email>
</author>
<published>2026-04-08T00:40:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=147ddf8ee3d83e99faa47e391e3d9de91f93540b'/>
<id>147ddf8ee3d83e99faa47e391e3d9de91f93540b</id>
<content type='text'>
Generates an explorable HTML report of Claude Code session usage from
local ~/.claude/projects transcripts: total tokens, cache efficiency,
per-project/subagent/skill breakdowns, most expensive prompts with
transcript context, and cache breaks. Terminal-styled, single-file
output with sortable tables and expandable drill-downs.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Generates an explorable HTML report of Claude Code session usage from
local ~/.claude/projects transcripts: total tokens, cache efficiency,
per-project/subagent/skill breakdowns, most expensive prompts with
transcript context, and cache breaks. Terminal-styled, single-file
output with sortable tables and expandable drill-downs.
</pre>
</div>
</content>
</entry>
<entry>
<title>math-olympiad: housekeeping (#1172)</title>
<updated>2026-03-30T19:56:21+00:00</updated>
<author>
<name>Tobin South</name>
<email>tobin.south@gmail.com</email>
</author>
<published>2026-03-30T19:56:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=9d468adfb857b1aeedb45f6279409820a0ffa573'/>
<id>9d468adfb857b1aeedb45f6279409820a0ffa573</id>
<content type='text'>
* math-olympiad: add LICENSE, marketplace entry, and prettier formatting

- Add Apache 2.0 LICENSE file
- Register plugin in marketplace.json
- Run prettier (prose-wrap=always, 80 cols) over all plugin markdown
- Simplify model tier naming in reference docs

:house: Remote-Dev: homespace

* Update .claude-plugin/marketplace.json</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
* math-olympiad: add LICENSE, marketplace entry, and prettier formatting

- Add Apache 2.0 LICENSE file
- Register plugin in marketplace.json
- Run prettier (prose-wrap=always, 80 cols) over all plugin markdown
- Simplify model tier naming in reference docs

:house: Remote-Dev: homespace

* Update .claude-plugin/marketplace.json</pre>
</div>
</content>
</entry>
</feed>
