task-context-storage
Skill2 starsChanged 45 days agoMITView on GitHub
Route facts among global memory, task MEMORY.md, and task CHANGELOG.md.
In this repository15 other files it gives its agents.
- compact-directory-memorySkill
- task-archaeologySkill
- task-artifact-integritySkill
- task-aware-project-workSkill
- task-cross-machine-syncSkill
- task-external-repos-patternSkill
- task-frameworkSkill
- task-lifecycle-disciplineSkill
- task-lifecycle-edge-casesSkill
- task-lifecycle-portabilitySkill
- task-nested-subtask-lifecycleSkill
- task-requirement-intakeSkill
- task-root-git-operationsSkill
- task-timestamp-conventionSkill
- task-trackerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 51
Do not store task progress, commits, issue numbers, transient failures, or session outcomes here.
- Distinctive: line 59
Do not store momentary runtime status or chronological history here.
- Very specific: line 71
When a task spans multiple subsystems, load compact-directory-memory and use its hierarchical layout.
- Distinctive: line 80
When one observation contains both a reusable preference and a task decision, split it:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Task Context Storage
Defines which persistence layer owns each kind of context. File formats, nested directory structure, and maintenance tooling are delegated to compact-directory-memory.
Persistence layers
| Layer | Scope | Content | Read/write timing |
Global memory() | All sessions and tasks | User preferences and stable environment facts | Automatically injected; update sparingly |
Task MEMORY.md | One task or subsystem | Stable expected-state facts and constraints | Read fully before work; update only when facts change |
Task CHANGELOG.md | One task or subsystem | Decisions, operations, observed verification, blockers, next step | Read recent entries before work; append after work |
| Raw logs | One execution | Command output, traces, generated diagnostics | Read as needed; safe to clean according to task rules |
Route to global memory()
- User identity, durable preferences, and recurring corrections.
- Stable environment facts used across unrelated tasks.
- Cross-task workflow constraints.
Do not store task progress, commits, issue numbers, transient failures, or session outcomes here.
Route to task MEMORY.md
- Expected configuration and stable conventions.
- Durable paths, interfaces, ports, ownership boundaries, and invariants.
- Facts that another session must know before changing the same task or subsystem.
Do not store momentary runtime status or chronological history here.
Route to task CHANGELOG.md
- Why one option was chosen over another.
- What was changed and where.
- Real test, build, migration, or health-check results.
- Failures, fixes, unresolved blockers, and exact next step.
- Session and phase outcomes.
Hierarchical tasks
When a task spans multiple subsystems, load compact-directory-memory and use its hierarchical layout. Root files index and synthesize cross-subsystem facts; memories/<sub-system>/ owns detailed subsystem context.
The routing rule remains unchanged at every level:
- stable expected state →
MEMORY.md - chronological observed work →
CHANGELOG.md
Boundary cases
When one observation contains both a reusable preference and a task decision, split it:
- global
memory()receives the durable preference; - task
CHANGELOG.mdreceives the local decision and its consequences; - task
MEMORY.mdreceives only a resulting stable fact, if one exists.
Relationship to task-framework
task-framework should reference this skill for context-routing decisions and compact-directory-memory for concrete directory management. It should not duplicate either skill's detailed rules.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

