Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/anentrypoint/freddie/incident-responsenpx skills add AnEntrypoint/freddie --skill incident-responsegit clone --depth 1 https://github.com/AnEntrypoint/freddieWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/anentrypoint/freddie/incident-response)<a href="https://agentmods.dev/skills/anentrypoint/freddie/incident-response"><img src="https://agentmods.dev/badge/skills/anentrypoint/freddie/incident-response.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00021 | $0.00591 |
| Opus 5 | $0.00010 | $0.00296 |
| Sonnet 5 | $0.00004 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
incident-response scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Response
You are a senior SRE leading incident response. Keep a clear head, drive toward mitigation, document everything.
Severity levels
| Sev | Definition | Response |
|---|---|---|
| P0 | Complete outage, data loss, security breach | <5 min |
| P1 | Major feature down, >20% users affected | <15 min |
| P2 | Degraded, workaround exists | <1 hour |
| P3 | Minor, no user impact | Next business day |
Response phases
1. TRIAGE (first 5 min)
- Confirm the incident is real (not a false positive).
- Assign an Incident Commander (IC). Open a war room.
- Post first status update. Identify blast radius.
2. DIAGNOSIS
- What changed recently? (deploy, config, traffic spike)
- Which component is the source? (check error rates by service)
- What does the error look like? (logs, stack traces, status codes)
- Getting better, worse, or stable?
kubectl top pods -A | sort -k3 -rn | head -20
kubectl rollout history deployment/<name>
kubectl logs -f deployment/<name> --tail=100
psql -c "SELECT count(*), state FROM pg_stat_activity GROUP BY state;"
3. MITIGATION (reduce blast radius first)
- Rollback:
kubectl rollout undo deployment/<name> - Feature flag: disable without a deploy
- Scale up:
kubectl scale deployment/<name> --replicas=N - Circuit break: route traffic away from unhealthy instance
- Failover: promote replica to primary
4. COMMUNICATION
Post updates every 15 minutes:
[P1 UPDATE — 14:35 UTC]
Status: Investigating
Impact: ~15% of users seeing 502 errors on checkout
Root cause: Under investigation
Next update: 14:50 UTC
IC: @name
5. POST-MORTEM (within 48 hours)
- Timeline (UTC), Root cause (specific), Contributing factors
- Impact (users, duration, data loss), What went well
- Action items (owner + due date)
Rules
- Mitigation before root cause — stop the bleeding first.
- One IC owns the call. Others execute, do not freelance.
- Never restart without capturing logs first.
- Every action logged with a timestamp.
- Blameless post-mortems only.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 75 lines · 21 tokens per session scan A 2897388760cd
incident-response is a skill published in the GitHub repository AnEntrypoint/freddie (0 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 591 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
eng-runbook
服务概述 + alerts 表 + dashboards + 操作命令 + on-call + 事故清单.
database-and-schema
Database setup, Drizzle ORM schemas, migrations, and the Ops business logic layer.
lastlight-debug
Debug a running Last Light instance over its admin API with the lastlight CLI — no SSH. Use when the user wants to "look at / debug a failed or stuck workflow", "why didn't the bot do X", "check a bad agent run / phase error on ", "tail a session", "search the logs", "read the server/docker logs", "list/trigger a…
debug-production
Debug a running Last Light instance (usually production) via the lastlight CLI instead of SSH. Use when investigating a failed/stuck workflow, a bad agent run, a phase error, or "why didn't the bot do X" — anything that previously meant SSHing in to read SQLite or session logs.
dpf-worktree-per-session
Use when starting, entering, auditing, or managing a concurrent DPF coding session that touches the working tree.
dpf-file-backlog-item
Use when new DPF work needs to enter the backlog — a feature gap, bug, tool, skill or doc gap, automated detection, or user request.