Artifact budget enforcement
Skill matt-bat/agent-command-center/skills/artifact-budget-enforcement
Governance-first agent command center for workflow automation, validation, policy, documentation sync, and execution discipline.
npx -y skills add matt-bat/agent-command-center --skill artifact-budget-enforcementAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use for enforcing hard limits on cached artifacts, summaries, indexes, and other compact metadata files so they stay bounded and high-signal.
SKILL.md
3.6 KB, as published. Nobody here has run it
Artifact Budget Enforcement
Quick Index (Action-Routed)
Read First (All Actions)
MissionTrigger RuleBudget Policy
Action Modules (Read As Needed)
- Choosing caps:
Default Budgets
- Pruning and consolidation:
Pruning RuleMerge Rule
- Preventing drift:
Staleness Rule
Output
Output Contract
Mission
Keep cached artifacts useful by giving them explicit size limits and pruning rules.
Authority and Artifact Policy
- Activating this skill grants no authority to create, update, prune, merge, or delete an artifact.
- Apply budgets as recommendations during read-only work; mutate an artifact only when the task separately authorizes maintaining that artifact.
- Do not create a cache, tracker, summary, or index solely because this skill activated.
Trigger Rule
Use this skill when:
- conversation caches, indexes, or trackers can grow without bound
- summaries or descriptions need strict length limits
- multiple files hold overlapping cached state
- a repo needs a repeatable rule for trimming low-value history
Anti-Overuse Rules
Use when:
- an artifact has a real growth risk
- cache-like docs need explicit caps
- pruning or merging is part of the task
Do not use when:
- no bounded artifact is being created or maintained
- a normal documentation edit has no cache behavior
- the relevant artifact already stays under its cap
Stop after:
- caps are defined or confirmed
- oversized artifacts are pruned or merged
- remaining exceptions are recorded with rationale
Budget Policy
Every cache-like artifact must have:
- a hard item cap
- a per-entry size cap
- a pruning rule when the cap is exceeded
- a canonical file of record when multiple files overlap
Default Budgets
Use these defaults unless a stricter repo rule already exists:
- rolling conversation summary: 10 entries
- index summaries: 40 words max
- short descriptions: 12 words max unless the schema is stricter
- tracker notes: 25 words max
- bullet lists in cached artifacts: 10 items max unless the schema is stricter
Pruning Rule
When a cap is exceeded:
- remove the oldest low-value entry first
- merge stable duplicates before removing unique information
- preserve the newest user-relevant state
- record what was pruned if the artifact tracks history
Merge Rule
Merge entries when they are:
- duplicate
- superseded
- too similar to justify separate cache slots
Staleness Rule
If a cached entry is old but still relevant:
- keep the newest accurate version
- mark the older one superseded where the artifact supports it
- do not keep both unless the artifact explicitly needs lineage
Default Scope
Common targets include:
docs/chat-history-summary.mddocs/chat-history-index.mduser-instructions.md- tracker-style markdown tables
Output Contract
When using this skill, provide:
- artifact(s) capped
- limit(s) applied
- entries removed or merged
- residual risk if a stricter cap is still needed
Related Skills
- Conversation Retention Summary: maintains the rolling 10-conversation cache.
- History Indexing: maintains the broader detailed index.
- Token Reduction: keep summaries and notes compact.
- File Maintenance: detect stale or duplicate artifact growth.