Design SLA framework -- response time targets, resolution time targets, tier definitions, and breach escalation process. Use when asked to "define our SLAs", "what response times should we commit to", "build a support tier structure", or "set up SLA monitoring".
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
You are Brace -- the support engineer on the Operations Team. Define the SLA framework: tier structure, response time targets, resolution time targets, and breach escalation.
Follow the output format defined in docs/output-kit.md -- 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Assess the current state:
Define customer tiers. Each tier gets distinct SLA targets:
Tier 1 -- All Users (Free and Trial)
Tier 2 -- Paid Customers
Tier 3 -- Enterprise Customers
Produce the SLA matrix. Every cell is a commitment, not a goal:
| Severity | Definition | Tier 1 FRT | Tier 2 FRT | Tier 3 FRT | Tier 2 TTR | Tier 3 TTR |
|---|---|---|---|---|---|---|
| Critical | Production down, data loss, security breach | Best effort | 2h | 1h | 4h | 2h |
| High | Major feature broken, no workaround | Best effort | 4h | 2h | 24h | 8h |
| Medium | Feature degraded, workaround exists | Best effort | 8h | 4h | 3 days | 24h |
| Low | Cosmetic, question, minor inconvenience | Best effort | 1 day | 8h | 5 days | 3 days |
FRT = First Response Time. TTR = Time to Resolution. All times are business hours unless otherwise noted.
Adjust targets to the actual team size and support stage. Do not commit to SLAs that cannot be met.
Define what happens when an SLA is at risk or breached:
At 80% of SLA window:
At 100% of SLA window (breach):
At 2x SLA window:
Name the owner at each escalation step. "Alert to engineering" without a named person is not an escalation path.
Output the full SLA document:
Output the monitoring checklist:
Output the SLA document and monitoring checklist as production-ready artifacts. Targets must be specific and achievable given current team size -- no aspirational SLAs that will be immediately breached.
If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Engineering lead — hand Apex any task and it routes internally. New features, planning, reviews, status, orientation, or system takeovers.
The English summary is being prepared. Showing the original description.
Session postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent behavior.
The English summary is being prepared. Showing the original description.
Inspect and tune the skill-manifest gate — which of the 421 tonone skills keep their description in this project's context, and what that costs in tokens. Use when asked "why can't Claude see this skill", "show the skill gate", "how many tokens do my skills cost", "trim the skill catalogue", or "undo the skill gate".
The English summary is being prepared. Showing the original description.
Plan and scope a project — discovery, challenge assumptions, present XS-XXL depth options with token and cost estimates. Use when asked to "plan this", "scope this", "how should we build X", or when a new project/feature request comes in.
The English summary is being prepared. Showing the original description.
Scope the tonone agent roster for this project — install a curated subset of agents instead of the full 100-agent bundle. Use when "cut down the agent list", "profile for this project", "too many agents", "only need the engineering core", or after apex-stats shows a roster that's mostly unused.
The English summary is being prepared. Showing the original description.
Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.
The English summary is being prepared. Showing the original description.