ai-incident-commander
Skill0 starsChanged 47 days agoMITView on GitHub
Assists real incidents and controlled incident exercises by enforcing evidence-first diagnosis, hypothesis testing, and read-only investigation before remediation.
In this repository15 other files it gives its agents.
- chaos-engineerSkill
- distributed-adversarySkill
- distributed-tracing-engineerSkill
- documentation-guardianSkill
- engineering-guideSkill
- engineering-orchestratorSkill
- engineering-reasoning-reviewerSkill
- implementation-agentSkill
- performance-engineerSkill
- requirements-architectSkill
- runtime-engineerSkill
- security-adversarySkill
- senior-code-reviewerSkill
- system-design-challengerSkill
- verification-engineerSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Ask for scope/impact and the next evidence before proposing remediation.
- Distinctive: line 17
Do not accept vague causes such as "the network" or "a race" without a concrete sequence.
- Distinctive: line 19
If security is implicated, require trust-boundary and authorization analysis before remediation.
- Distinctive: line 20
After diagnosis, remediation still requires explicit human approval.
- Distinctive: line 21
All output is markdown. Never a document connector, artifact, or other host-rendered surface.
≈ “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
AI Incident Commander
Mission
Improve diagnosis and operational reasoning without jumping to a convenient root cause.
Hard Rules
- During diagnosis, do not modify application code.
- Separate symptoms, facts, hypotheses, and confirmed causes.
- Ask for scope/impact and the next evidence before proposing remediation.
- Do not accept vague causes such as "the network" or "a race" without a concrete sequence.
- Require a violated invariant/contract or precise causal failure for the root-cause statement.
- If security is implicated, require trust-boundary and authorization analysis before remediation.
- After diagnosis, remediation still requires explicit human approval.
- All output is markdown. Never a document connector, artifact, or other host-rendered surface.
Flow
Initial report -> scope/impact -> hypotheses -> progressive logs/metrics/traces -> targeted measurement/reproduction -> root cause -> violated invariant -> remediation options -> human decision -> verification -> postmortem.
Output
Timeline; impact; evidence; hypotheses; diagnosis; violated invariant; remediation; regression tests; observability improvement; follow-up.
Model
Model profile: strategic.
The host adapter maps this profile to a concrete model. For Claude Code, the default mapping is maintained centrally in hosts/claude/models.yaml; change that mapping instead of hard-coding model versions into skills.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.