akshay-na/context-cache-discipline
ai/opencode/tech-team/skills/context-cache-discipline/SKILL.md
Token and prompt-cache discipline — lean always-on rules, stable prefixes, skill indirection, minimal Task payloads, bounded reads.
$ install --global
skillsauthnpx skillsauth add akshay-na/dotfiles context-cache-disciplineInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 28, 2026, 3:49 AM12.9s1 file scanned
SKILL.md
- name:
- context-cache-discipline
- description:
- Token and prompt-cache discipline — lean always-on rules, stable prefixes, skill indirection, minimal Task payloads, bounded reads.
- version:
- 1
Context and cache discipline
Use this skill when orchestrating or editing the pack so context stays small and early prompt prefixes stay stable (better cache hit odds on providers; always fewer input tokens).
Principles
| Goal | Practice |
|------|----------|
| Stable prefix | Prefer one canonical copy of long text in skills; rules point — avoid churn in alwaysApply: true bodies. |
| Lean always-on | Rarely needed norms → alwaysApply: false + globs, or load skill on demand. |
| Indirection | Agents/rules cite skill path; do not paste full playbooks into rules or agent bodies. |
| Task payloads | Parent Task prompts: goal, constraints, approved_plan_path, phase/shard id, touches[], correlation ids — not full rules or transcripts. |
| Reads | Batch parallel Read where independent; one read per file per turn unless content changed; lookup-first for brain-memory-kb. |
| Subagent traffic | Children: caveman-ultra + single YAML envelope per templates/subagent-response.yml.tmpl; parents: do not paste raw child YAML to user. |
Non-claim: Exact cache eligibility is vendor-defined; token reduction is always a win.
Memory / KB policy indirection
Load ~/ai-brain/org/global/config/memory-demotion.yml (via brain-memory-kb) for query ladder L0–L3 caps and demotion thresholds — do not duplicate full policy text here.
When to load what
- Routing, swarm, routing table, Task payload caps:
task-orchestration - Memory/KB + git-backed brain sync:
brain-memory-kb - Docs / HTTP / web / Context7: rule
vp-research.md(single broker); never duplicate broker bullets elsewhere - Envelope + parent parse:
subagent-response-protocol+templates/subagent-response.yml.tmpl - Metrics + optional
token_stats:agent-observability
Forbidden
- Pasting full
alwaysApplyrule bodies into chat to “teach” a subagent - Re-fetching the same skill/rule in one turn without reason
- Oversized inline blobs in
Task(anti-dup hook is fail-closed)
Related Skills
akshay-na/team-discovery
development
VerifiedTrustedCommunity
Discovery + naming convention reference for typed dev/SME/QA/devops team members in any workspace folder. Primary consumer: `tech-lead` (org-tier).
4SKILL.mdUpdated May 28, 2026
akshay-na/task-orchestration
devops
VerifiedTrustedCommunity
Automated task classification, agent selection, and state tracking. Use when routing tasks to agents, selecting pipelines, or managing task state.
4SKILL.mdUpdated May 28, 2026
akshay-na/systems-design-depth
testing
VerifiedTrustedCommunity
Use when designing scalable systems, evaluating consistency models, planning state management, making architectural decisions, or when trade-offs around coupling, failure isolation, and reversibility need explicit reasoning before implementation.
4SKILL.mdUpdated May 28, 2026
akshay-na/swarm-task-decomposition
tools
VerifiedTrustedCommunity
CTO/tech-lead helper — split work into disjoint shard briefs with caps (instance_cap, partition_basis, determinism keys).
4SKILL.mdUpdated May 28, 2026