shellbrain 0.1.43__tar.gz → 0.1.44__tar.gz

{shellbrain-0.1.43 → shellbrain-0.1.44}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: shellbrain
-Version: 0.1.43
+Version: 0.1.44
 Summary: Repo-scoped Shellbrain CLI with explicit evidence-backed writes.
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown

shellbrain-0.1.44/onboarding_assets/claude/CLAUDE.md

@@ -0,0 +1,40 @@
+## Shellbrain
+
+Use Shellbrain for targeted recall during agent work.
+
+Keep this tuple in mind:
+
+`goal | surface | obstacle | hypothesis`
+
+Emit one `SB:` line when the tuple changes or you hit a boundary state:
+
+- goal, surface, obstacle, or hypothesis changed
+- same approach failed twice
+- an error repeats
+- you are about to make an evidence-bearing decision
+- you switch files, subsystems, or strategy
+- you are closing out
+
+If prior context may help:
+
+`SB: recall | <goal> | <surface> | <obstacle> | <hypothesis-or-trigger>`
+
+Then run:
+
+```bash
+shellbrain recall --json '{"query":"<targeted question>","current_problem":{"goal":"<goal>","surface":"<surface>","obstacle":"<obstacle>","hypothesis":"<hypothesis or none yet>"}}'
+```
+
+If recall would not help:
+
+`SB: skip | same signature | <one-line reason>`
+
+Then continue. Do not call recall reflexively.
+
+Use `shellbrain recall` for normal task context. Use `shellbrain teach` only when the user explicitly asks you to store or teach Shellbrain something.
+
+If you changed any files since your last user-facing response, run `shellbrain snapshot` exactly once after validation and immediately before your next user-facing response. Do this on every response cycle where files changed; skip only when no files changed.
+
+Do not call `shellbrain read`, `shellbrain events`, `shellbrain memory`, `shellbrain concept`, or `shellbrain scenario`.
+
+Use the installed `shellbrain` skill for the detailed recall workflow.

shellbrain-0.1.44/onboarding_assets/codex/AGENTS.md

@@ -0,0 +1,40 @@
+## Shellbrain
+
+Use Shellbrain for targeted recall during agent work.
+
+Keep this tuple in mind:
+
+`goal | surface | obstacle | hypothesis`
+
+Emit one `SB:` line when the tuple changes or you hit a boundary state:
+
+- goal, surface, obstacle, or hypothesis changed
+- same approach failed twice
+- an error repeats
+- you are about to make an evidence-bearing decision
+- you switch files, subsystems, or strategy
+- you are closing out
+
+If prior context may help:
+
+`SB: recall | <goal> | <surface> | <obstacle> | <hypothesis-or-trigger>`
+
+Then run:
+
+```bash
+shellbrain recall --json '{"query":"<targeted question>","current_problem":{"goal":"<goal>","surface":"<surface>","obstacle":"<obstacle>","hypothesis":"<hypothesis or none yet>"}}'
+```
+
+If recall would not help:
+
+`SB: skip | same signature | <one-line reason>`
+
+Then continue. Do not call recall reflexively.
+
+Use `shellbrain recall` for normal task context. Use `shellbrain teach` only when the user explicitly asks you to store or teach Shellbrain something.
+
+If you changed any files since your last user-facing response, run `shellbrain snapshot` exactly once after validation and immediately before your next user-facing response. Do this on every response cycle where files changed; skip only when no files changed.
+
+Do not call `shellbrain read`, `shellbrain events`, `shellbrain memory`, `shellbrain concept`, or `shellbrain scenario`.
+
+Use the installed `shellbrain` skill for the detailed recall workflow.

{shellbrain-0.1.43 → shellbrain-0.1.44}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "shellbrain"
-version = "0.1.43"
+version = "0.1.44"
 description = "Repo-scoped Shellbrain CLI with explicit evidence-backed writes."
 readme = "README.md"
 requires-python = ">=3.11"

{shellbrain-0.1.43 → shellbrain-0.1.44}/shellbrain.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: shellbrain
-Version: 0.1.43
+Version: 0.1.44
 Summary: Repo-scoped Shellbrain CLI with explicit evidence-backed writes.
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown

shellbrain-0.1.43/onboarding_assets/claude/CLAUDE.md

@@ -1,52 +0,0 @@
-## Shellbrain
-
-You have a persistent memory system called Shellbrain. This section exists to make you remember to use it at the right moments.
-
-### The Core Habit
-
-As you work, maintain a mental summary of your current subproblem as:
-
-`goal | surface | obstacle | hypothesis`
-
-When that tuple changes materially, or you hit a boundary state, pause and say one `SB:` line out loud by actually generating it as output. This keeps Shellbrain in your local attention so you can decide whether recall would help.
-
-Boundary states:
-
-- The goal, surface, obstacle, or hypothesis changed.
-- The same approach failed twice.
-- An error is repeating.
-- You are about to make an evidence-bearing decision.
-- You are switching files, subsystems, or implementation strategy.
-- You are closing out a task.
-
-### What To Say
-
-If prior context might help:
-
-`SB: recall | <goal> | <surface> | <obstacle> | <hypothesis-or-trigger>`
-
-Then call Shellbrain recall:
-
-```bash
-shellbrain recall --json '{"query":"<targeted question>","current_problem":{"goal":"<goal>","surface":"<surface>","obstacle":"<obstacle>","hypothesis":"<hypothesis or none yet>"}}'
-```
-
-If the tuple has not changed and there is no new evidence, failure, or uncertainty:
-
-`SB: skip | same signature | <one-line reason>`
-
-Then continue. Do not call recall reflexively.
-
-### Worker Boundary
-
-As the working agent, use `shellbrain recall` for normal task context. Use `shellbrain teach` only when the user explicitly asks you to store or teach Shellbrain something.
-
-If you changed any files since your last user-facing response, run `shellbrain snapshot` exactly once after validation and immediately before your next user-facing response. Do this on every response cycle where files changed; skip only when no files changed.
-
-Do not call `shellbrain read`, `shellbrain events`, `shellbrain memory`, `shellbrain concept`, or `shellbrain scenario`.
-
-Shellbrain's internal agents handle raw retrieval, synthesis, memory writing, concept updates, scenario recording, and teach consolidation.
-
-### Reference
-
-Use the installed `shellbrain` skill for the detailed recall workflow.

shellbrain-0.1.43/onboarding_assets/codex/AGENTS.md

@@ -1,52 +0,0 @@
-## Shellbrain
-
-You have a persistent memory system called Shellbrain. This section exists to make you remember to use it at the right moments.
-
-### The Core Habit
-
-As you work, maintain a mental summary of your current subproblem as:
-
-`goal | surface | obstacle | hypothesis`
-
-When that tuple changes materially, or you hit a boundary state, pause and say one `SB:` line out loud by actually generating it as output. This keeps Shellbrain in your local attention so you can decide whether recall would help.
-
-Boundary states:
-
-- The goal, surface, obstacle, or hypothesis changed.
-- The same approach failed twice.
-- An error is repeating.
-- You are about to make an evidence-bearing decision.
-- You are switching files, subsystems, or implementation strategy.
-- You are closing out a task.
-
-### What To Say
-
-If prior context might help:
-
-`SB: recall | <goal> | <surface> | <obstacle> | <hypothesis-or-trigger>`
-
-Then call Shellbrain recall:
-
-```bash
-shellbrain recall --json '{"query":"<targeted question>","current_problem":{"goal":"<goal>","surface":"<surface>","obstacle":"<obstacle>","hypothesis":"<hypothesis or none yet>"}}'
-```
-
-If the tuple has not changed and there is no new evidence, failure, or uncertainty:
-
-`SB: skip | same signature | <one-line reason>`
-
-Then continue. Do not call recall reflexively.
-
-### Worker Boundary
-
-As the working agent, use `shellbrain recall` for normal task context. Use `shellbrain teach` only when the user explicitly asks you to store or teach Shellbrain something.
-
-If you changed any files since your last user-facing response, run `shellbrain snapshot` exactly once after validation and immediately before your next user-facing response. Do this on every response cycle where files changed; skip only when no files changed.
-
-Do not call `shellbrain read`, `shellbrain events`, `shellbrain memory`, `shellbrain concept`, or `shellbrain scenario`.
-
-Shellbrain's internal agents handle raw retrieval, synthesis, memory writing, concept updates, scenario recording, and teach consolidation.
-
-### Reference
-
-Use the installed `shellbrain` skill for the detailed recall workflow.