agentleFS
DROOdotFOODROOdotFOO/agent-skills/skills/regen/SKILL.md

regen

Skill1 starsChanged 2 months agoMITView on GitHub

Read Fluidify Regen incidents and extract the join keys needed to pivot from an incident into its underlying OTel telemetry. Regen is a self-hosted incident / on-call tool with a REST API but no MCP server; this agent makes incidents first-class and emits a ready-to-run SigNoz filter hint -- the incident side of the incident <-> telemetry loop (SigNoz is the telemetry side). TRIGGER when: user asks about Regen incidents, on-call/paging state, "what's on fire", incident triage, ack/resolve an incident, or invokes "/regen"; or wants the service.name + labels + time window to feed into SigNoz. DO NOT TRIGGER when: user is working on the regen agent code itself; or wants to query the telemetry directly (use the signoz skill -- regen hands off to it).

  • Installs packages

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read incidents and ingested alerts (with their labels) and timelines

    line 30
  2. Very specific:

    Write (only when REGEN_ENABLE_WRITE=1 or regen serve --write):

    line 58
  3. Distinctive:

    Write tools mutate live on-call state -- confirm intent before calling them.

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Regen

Incident reader + correlation extractor for Fluidify Regen (self-hosted, AGPLv3 on-call tool). Regen ships a REST API but no MCP server, so this agent reads incidents first-class and extracts the keys to pivot into SigNoz telemetry. Symmetric with the signoz skill: regen answers "what broke and when"; signoz answers "why," from the traces/metrics/logs.

What You Get

  • Read incidents and ingested alerts (with their labels) and timelines
  • regen_correlation_keys -- extracts service.name, correlation labels (chain, role, address, intent_id, ...), a time window, and a ready-to-run SigNoz filter hint
  • Optional write tools (ack / resolve / update) behind an explicit flag

The mini-axol deployment

  • REGEN_BASE_URL = http://mini-axol.tail9b2ce8.ts.net:3302 -- Tailscale must be up (a connection failure is almost always a down tailnet).
  • Runs in open mode behind the Tailscale ACL (Regen OSS falls through to open mode when no cookie/SAML is configured), so no secret is needed -- only REGEN_BASE_URL. Guardrail: do not create a Regen user or enable SAML, or open mode closes and the wrapper breaks.
  • Alerts originate from SigNoz on the same host and carry service.name, chain, role, etc. -- the labels that make the SigNoz pivot exact.

MCP tools

Read (always available):

ToolDescription
regen_list_incidentsList incidents; filter by status, severity, created_after/before, limit
regen_get_incidentOne incident + linked alerts (with labels) + timeline
regen_list_alertsIngested alerts; filter by status, source, limit
regen_correlation_keysExtract service.name + labels + time window + SigNoz filter hint

Write (only when REGEN_ENABLE_WRITE=1 or regen serve --write):

ToolDescription
regen_ack_incidentAcknowledge an incident
regen_resolve_incidentResolve an incident (optional summary)
regen_update_incidentUpdate status / severity / summary

Write tools mutate live on-call state -- confirm intent before calling them.

Correlation workflow (incident -> OTel)

  1. A SigNoz alert (e.g. SolverGasCriticalOptimism) fires on mini-axol, POSTs to Regen's webhook, and opens an incident whose labels carry service.name, chain, role, etc.
  2. regen_correlation_keys(<id>) pulls those labels + the incident's time window and emits a SigNoz filter hint, e.g.:

    service.name IN (riddler-balance-exporter, riddler-production)
      AND chain='optimism' AND role='solver'
      AND time>=<start> AND time<=<end>
  3. Feed that hint into the signoz MCP -- use the window as explicit start/end (unix ms) so telemetry lines up with when the alert fired: signoz_search_logs, signoz_aggregate_traces, signoz_query_metrics (the riddler_* metrics). This closes the loop from incident back to OTel.

The /signoz:incident_triage alertId=<id> prompt automates the SigNoz side once you have the alert rule id.

CLI Usage

regen incidents --severity critical   # list (status/severity filters)
regen incident 42                     # inspect one: alerts + timeline
regen alerts --source prometheus      # list ingested alerts
regen correlate 42                    # the correlation-keys step
regen serve                           # MCP server (stdio); add --write for mutations

Configure

VariableRequiredPurpose
REGEN_BASE_URLyesRegen instance URL (origin only; client appends /api/v1)
REGEN_SESSION_COOKIEnooi_session cookie value (local-auth deploys only)
REGEN_API_TOKENnoAuthorization: Bearer (forward-compatible)
REGEN_ENABLE_WRITEno1/true to expose the write tools

Point Claude Code at a wrapper that injects REGEN_BASE_URL from 1Password, mirroring the signoz wrapper:

{ "mcpServers": { "regen": { "command": "regen-mcp-wrapper.sh", "args": [] } } }

Install

cd agents/regen
pip install -e ".[dev]"

See also

  • signoz -- the telemetry side of the loop; where correlation keys get queried
  • observability-designer -- design SLOs and alert rules that open these incidents
  • sentinel -- on-chain contract monitoring (a different alert source)

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.