Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/bibutikoley-incident
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/incident
What's inside
- Skill name
incident- Description
- Stage 6 (Maintain) of the AI-native SDLC. Diagnose an anomaly, alert, ticket, or channel message with read-only tools, write the finding as an incident intent.md that re-enters the loop, and update lessons.md. Use on /sdlc:incident, when a control band is breached, when asked to investigate an alert/incident, or non-interactively from CI.
- License
- MIT
- Instructions
- 42 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /sdlc:incident — first responder that writes the next intent.md
Read `sdlc-loop` and `sdlc/lessons.md` (repeat incidents are the norm; check first).
## Diagnose (read-only)
- Tools: Read, Grep, `git log`, CI run logs (`gh run view`, GitLab MCP), Sentry MCP (issues, events, stack
traces), Grafana/Prometheus MCP (query the metric around the breach), tracker MCP (the ticket), RingCentral
MCP (the incident thread). No edits, no deploys, no production access.
- Establish: what breached (metric, band, rule, window), when, what changed in that window (deploys, merges,
config, dependency bumps), the most likely cause with confidence, what was ruled out.
- If `--evidence <file>` is given (the detection script's JSON), start from it.
## Act only through gated routes
| Tier | You may |
|---|---|
| 2σ (diagnose) | write the incident intent and comment on the ticket/thread. Nothing else. |
| 3σ (propose) | additionally open a PR into the review gate (revert, quarantine a flaky test, config fix) **or** trigger a pre-approved runbook (`rollback`) via CI. Never both silently; say which. |
Any PR you open carries `Change: sdlc/incidents/<id>` and gets the normal AI review + code owner approval.
## Write the artifact
1. `${CLAUDE_PLUGIN_ROOT}/scripts/new-change.sh "<slug>" --incident --owner "<service owner>"`.
2. Fill `sdlc/incidents/<id>/intent.md` in the Stage 1 format: anomaly and evidence, diagnosis, proposed
outcome, affected systems, constraints, open questions. Leave "Triage decision" blank.
3. Commit on `sdlc/incident/<id>`, open a PR titled `Incident: <title>` assigned to the service owner, label
`sdlc:incident` and `needs-human` if 3σ. If running headlessly, run the `sdlc:adversarial-reviewer` agent on
the intent first; on ESCALATE, stop after opening the PR.
4. Post a short summary to the incident thread/channel if `chat.type` is configured.
## Close the loop (after triage)
- Fix now → the intent goes through `/sdlc:spec` (or straight to `/sdlc:plan` for a small, bounded fix; note
the skipped stage in the plan frontmatter).
- Dismiss → propose the band tuning in `monitoring/bands.yaml` as a PR; dismissals reduce noise.
- When the fix ships → `/sdlc:eval-add <incident id>` and append the post-mortem to `sdlc/lessons.md`.
Report: diagnosis, tier, what you did through which gate, the intent path, and who triages.From bibutikoley/ai-sdlc-claude, MIT.
More from bibutikoley/ai-sdlc-claude
- 0.564score
tracker-sync
bibutikoley
Keep the legacy tracker (Jira, YouTrack, GitLab issues, GitHub issues) and the Markdown artifacts linked according to sdlc.config.json sourceOfTruth (repo |…
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
security-policy
bibutikoley
The organisation's security policy as constraints on specs, plans, code and reviews.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
ux-standards
bibutikoley
Interaction, accessibility and content-structure standards for anything users touch.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
release
bibutikoley
Stage 5 (Deploy) release of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
review
bibutikoley
Stage 5 (Deploy) AI review of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
setup
bibutikoley
Install the AI-native SDLC loop into a product repository.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
spec
bibutikoley
Stage 2 (Design) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
eval-add
bibutikoley
Stage 4 (Test) continuous evals.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
intent
bibutikoley
Stage 1 (Plan) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
metrics
bibutikoley
Compute and explain the AI-native SDLC's leading and lagging indicators from Git history, PR metadata and CI (intent time-to-commit, intent→spec, spec→plan…
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
plan
bibutikoley
Stage 3 (Build) entry of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
brand-guidelines
bibutikoley
The organisation's brand and content standards applied to specs and UI work.
SkillBFreshness: B★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 5, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bibutikoley/ai-sdlc-claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bibutikoley
- 0.564score
brand-guidelines
bibutikoley
The organisation's brand and content standards applied to specs and UI work.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
eval-add
bibutikoley
Stage 4 (Test) continuous evals.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
intent
bibutikoley
Stage 1 (Plan) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
metrics
bibutikoley
Compute and explain the AI-native SDLC's leading and lagging indicators from Git history, PR metadata and CI (intent time-to-commit, intent→spec, spec→plan…
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
plan
bibutikoley
Stage 3 (Build) entry of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
compliance-policy
bibutikoley
Regulatory and change-management obligations as constraints on specs, plans, releases and reviews.
SkillBFreshness: B★ 3Claude Code +9
Cite this page
incident skill. Agent Mart. https://agentmart.dev/skills/bibutikoley-incident (last updated 2026-10-24)