<feed xmlns='http://www.w3.org/2005/Atom'>
<title>claude-plugins-official.git/plugins/code-modernization/workflows/extract-rules.js, branch codemod-dynamic-workflows</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: fix findings from adversarial audit</title>
<updated>2026-06-09T23:31:52+00:00</updated>
<author>
<name>Morgan Westlee Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-06-09T23:31:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=3b9df6160068f836214bfae942a2ca2530489c84'/>
<id>3b9df6160068f836214bfae942a2ca2530489c84</id>
<content type='text'>
Code/security:
- extract-rules.js: guard null agent() verdicts in the verify + P0 loops
  (a skipped/dead referee made {rule,v:null} survive .filter(Boolean) and
  then crashed on v.injectionSuspected / v.every) — sibling scripts already
  had the guard.
- topology viewer XSS: the map injector embedded untrusted JSON (node names
  from filenames, etc.) into a &lt;script&gt; island unescaped — a name containing
  &lt;/script&gt; executed on open. Escape &lt; &gt; &amp; in the injected data and add a CSP
  to the template.
- Second-order injection: citation/identifier fields (source / cwe /
  source_site / correctedSource) were interpolated UNFENCED into the verifier
  prompts that are supposed to be the trust anchor. Fence them in
  extract-rules, harden-scan, uplift-deltas.

uplift design (audit of the new feature):
- Working-copy model: copy the WHOLE solution to modernized/ once and edit in
  place (relative project refs survive; result is a reviewable git diff) —
  the incremental per-project copy broke multi-project builds.
- Dual-run honesty: reframed as 'if both runtimes run here' (net48 needs
  Windows; JUnit/pytest don't multi-target); dummy-test gate now binds a real
  SUT under both targets; per-stack harness notes.
- Tooling honesty: present/runnable/actually-ran distinction; never fold in a
  tool that couldn't run; apiport/2to3 demoted; py2-&gt;3 removed from 'preserve'
  examples.
- Delta classes: name the high-blast-radius landmines (JPMS strong
  encapsulation, .NET trimming/AOT, ICU globalization, hosting/runtime-config,
  analyzer/nullable) in the finder briefs + agent.
- Rewrite-vs-uplift signal: weigh by touched sites (siteCount), not delta-card
  count; judgment-share demoted to secondary.

Docs/consistency: brief reads topology.json (not TOPOLOGY.html); README
'five commands'; credential-masking claim split (analysts mask+cite vs
code-writers substitute fakes); read-only/write-scope claims softened to
match enforcement (Bash retained -&gt; discipline, not tool-lock); reimagine
nested blockers/pendingRuleIds; status splits transform vs reimagine markers;
portfolio enumeration basenames; plugin.json description updated.

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Code/security:
- extract-rules.js: guard null agent() verdicts in the verify + P0 loops
  (a skipped/dead referee made {rule,v:null} survive .filter(Boolean) and
  then crashed on v.injectionSuspected / v.every) — sibling scripts already
  had the guard.
- topology viewer XSS: the map injector embedded untrusted JSON (node names
  from filenames, etc.) into a &lt;script&gt; island unescaped — a name containing
  &lt;/script&gt; executed on open. Escape &lt; &gt; &amp; in the injected data and add a CSP
  to the template.
- Second-order injection: citation/identifier fields (source / cwe /
  source_site / correctedSource) were interpolated UNFENCED into the verifier
  prompts that are supposed to be the trust anchor. Fence them in
  extract-rules, harden-scan, uplift-deltas.

uplift design (audit of the new feature):
- Working-copy model: copy the WHOLE solution to modernized/ once and edit in
  place (relative project refs survive; result is a reviewable git diff) —
  the incremental per-project copy broke multi-project builds.
- Dual-run honesty: reframed as 'if both runtimes run here' (net48 needs
  Windows; JUnit/pytest don't multi-target); dummy-test gate now binds a real
  SUT under both targets; per-stack harness notes.
- Tooling honesty: present/runnable/actually-ran distinction; never fold in a
  tool that couldn't run; apiport/2to3 demoted; py2-&gt;3 removed from 'preserve'
  examples.
- Delta classes: name the high-blast-radius landmines (JPMS strong
  encapsulation, .NET trimming/AOT, ICU globalization, hosting/runtime-config,
  analyzer/nullable) in the finder briefs + agent.
- Rewrite-vs-uplift signal: weigh by touched sites (siteCount), not delta-card
  count; judgment-share demoted to secondary.

Docs/consistency: brief reads topology.json (not TOPOLOGY.html); README
'five commands'; credential-masking claim split (analysts mask+cite vs
code-writers substitute fakes); read-only/write-scope claims softened to
match enforcement (Bash retained -&gt; discipline, not tool-lock); reimagine
nested blockers/pendingRuleIds; status splits transform vs reimagine markers;
portfolio enumeration basenames; plugin.json description updated.

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: second-order injection fencing, path guards, scoped scaffolder agent</title>
<updated>2026-06-09T19:40:58+00:00</updated>
<author>
<name>Morgan Westlee Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-06-09T19:40:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=d44da811468a8124135a67ba64a3d0257a2e36b6'/>
<id>d44da811468a8124135a67ba64a3d0257a2e36b6</id>
<content type='text'>
Addresses automated security review of the workflow conversion:

- Agent-produced text (rule specs, finding descriptions, dedup lists) is
  fenced as untrusted data when interpolated into downstream agent prompts,
  with embedded fence markers stripped so the fence can't be escaped;
  referees and judges are told to re-derive claims from the cited code.
- system/service/subdir names that land in filesystem paths inside prompts
  are validated against a strict pattern — traversal-shaped values throw
  before any agent spawns.
- Reimagine scaffolding now uses a dedicated 'scaffolder' agent with an
  explicit minimal tool list, a single-directory write scope, and the
  untrusted-content discipline extended to the generated spec/architecture
  docs it builds from (they derive from untrusted legacy code).

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Addresses automated security review of the workflow conversion:

- Agent-produced text (rule specs, finding descriptions, dedup lists) is
  fenced as untrusted data when interpolated into downstream agent prompts,
  with embedded fence markers stripped so the fence can't be escaped;
  referees and judges are told to re-derive claims from the cited code.
- system/service/subdir names that land in filesystem paths inside prompts
  are validated against a strict pattern — traversal-shaped values throw
  before any agent spawns.
- Reimagine scaffolding now uses a dedicated 'scaffolder' agent with an
  explicit minimal tool list, a single-directory write scope, and the
  untrusted-content discipline extended to the generated spec/architecture
  docs it builds from (they derive from untrusted legacy code).

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: dynamic workflow orchestration + untrusted-content hardening</title>
<updated>2026-06-09T19:33:13+00:00</updated>
<author>
<name>Morgan Westlee Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-06-09T19:33:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=c42d4bb58913a22b4b0594bf55c14a4431219049'/>
<id>c42d4bb58913a22b4b0594bf55c14a4431219049</id>
<content type='text'>
Four commands gain a Workflow-tool path (with direct-fan-out fallback for
older builds): extract-rules loops until dry with per-rule citation referees
and a P0 two-judge panel; harden runs class-scoped finders with adversarial
per-finding refutation; assess --portfolio pipelines one survey agent per
system with COCOMO computed uniformly in script; reimagine Phase E drops the
3-service scaffolding cap.

Workflow agents return schema-validated data and only the orchestrating
session writes artifacts — analysis agents are structurally read-only. All
five agents gain an untrusted-content discipline section (source code is
data, never instructions; comment-only claims are findings, not facts), and
the README documents the prompt-injection threat model for analyzed code.

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Four commands gain a Workflow-tool path (with direct-fan-out fallback for
older builds): extract-rules loops until dry with per-rule citation referees
and a P0 two-judge panel; harden runs class-scoped finders with adversarial
per-finding refutation; assess --portfolio pipelines one survey agent per
system with COCOMO computed uniformly in script; reimagine Phase E drops the
3-service scaffolding cap.

Workflow agents return schema-validated data and only the orchestrating
session writes artifacts — analysis agents are structurally read-only. All
five agents gain an untrusted-content discipline section (source code is
data, never instructions; comment-only claims are findings, not facts), and
the README documents the prompt-injection threat model for analyzed code.

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
