<feed xmlns='http://www.w3.org/2005/Atom'>
<title>rulesets/claude-rules/cross-project.md, branch main</title>
<subtitle>Claude Code skills, rules, and language bundles
</subtitle>
<id>https://git.cjennings.net/rulesets/atom?h=main</id>
<link rel='self' href='https://git.cjennings.net/rulesets/atom?h=main'/>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/rulesets/'/>
<updated>2026-06-13T00:33:12+00:00</updated>
<entry>
<title>docs(rules): clarify proactive inbox-send vs the stop-and-ask rule</title>
<updated>2026-06-13T00:33:12+00:00</updated>
<author>
<name>Craig Jennings</name>
<email>c@cjennings.net</email>
</author>
<published>2026-06-13T00:33:12+00:00</published>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/rulesets/commit/?id=4fa8fd739a09e4ddd424e434fe174e3180d2f233'/>
<id>urn:sha1:4fa8fd739a09e4ddd424e434fe174e3180d2f233</id>
<content type='text'>
A literal reading of cross-project.md could see its new propagation section (send synced-file edits to rulesets without being told) as conflicting with the file's stop-and-ask rule. One sentence reconciles them: ask-first governs work inside another project's scope, and an inbox drop is the sanctioned alternative to that, so it needs no confirmation.
</content>
</entry>
<entry>
<title>docs(rules): codify propagating synced-file edits back to rulesets</title>
<updated>2026-06-13T00:15:22+00:00</updated>
<author>
<name>Craig Jennings</name>
<email>c@cjennings.net</email>
</author>
<published>2026-06-13T00:15:22+00:00</published>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/rulesets/commit/?id=f058b4c15a67ce3b54e306e8b4778aa3cb540c7c'/>
<id>urn:sha1:f058b4c15a67ce3b54e306e8b4778aa3cb540c7c</id>
<content type='text'>
A downstream edit to a rulesets-owned synced file (workflows, scripts, rules, protocols.org) is a stopgap the next template sync reverts. cross-project.md now documents the three-step propagation (edit locally, inbox-send the file to rulesets, include an intro note with the why and any companions to reconcile) so agents propagate a synced-file edit without being told.

From the .emacs.d handoff 2026-06-12.
</content>
</entry>
<entry>
<title>docs(cross-project): prefer inbox-send for handoff drops</title>
<updated>2026-05-15T19:56:43+00:00</updated>
<author>
<name>Craig Jennings</name>
<email>c@cjennings.net</email>
</author>
<published>2026-05-15T19:56:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/rulesets/commit/?id=7dd10e23cc78fab028b9ad27f0aaca0b8ec783c9'/>
<id>urn:sha1:7dd10e23cc78fab028b9ad27f0aaca0b8ec783c9</id>
<content type='text'>
The cross-project boundary rule already prescribes dropping a handoff
file in the target project's inbox/ when option 1 ("do it from here")
is chosen. The change adds a paragraph pointing at the new inbox-send
script as the preferred tool for the drop. The script handles project
discovery, source-project provenance in the filename, slug derivation,
and timestamping in one call, replacing the hand-constructed filenames
and guessed project paths the rule used to require.

Filename convention is unchanged
(YYYY-MM-DD-HHMM-from-&lt;source&gt;-&lt;slug&gt;.&lt;ext&gt;); the script just generates
it instead of me typing it out. Fallback to Write/Edit is documented
for cases where the script isn't installed (e.g. a freshly-cloned
project before the first startup-rsync).
</content>
</entry>
<entry>
<title>feat(rules): cross-project boundary rule + cj-comments preflight</title>
<updated>2026-05-13T12:31:59+00:00</updated>
<author>
<name>Craig Jennings</name>
<email>c@cjennings.net</email>
</author>
<published>2026-05-13T12:31:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/rulesets/commit/?id=22594dc3fa6af13af8a3ef0910fb8ca1eb543b06'/>
<id>urn:sha1:22594dc3fa6af13af8a3ef0910fb8ca1eb543b06</id>
<content type='text'>
New `claude-rules/cross-project.md` codifies the per-project `.ai/` scope
boundary. Stop-and-ask when a request targets another project's files,
inline numbered options, handoff-file convention when the user opts to
do it from here.

`/respond-to-cj-comments` gains a section-0 preflight (boundary check
before reading the target file) and a section-7 handoff step (writes
the carry-forward file in the target project's `inbox/` when the
boundary crossing was approved).
</content>
</entry>
</feed>
