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 skills add tmj-90/gaffer --skill incident-responsegit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/incident-response)<a href="https://agentmods.dev/skills/tmj-90/gaffer/incident-response"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/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 5.1 | $0.00085 | $0.00892 |
| Opus 5 | $0.00043 | $0.00446 |
| Sonnet 5 | $0.00017 | $0.00178 |
| Haiku 4.5 | $0.00009 | $0.00089 |
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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage declared incidents end-to-end
Triage fast, escalate correctly, contain early, learn systematically. An incident not reviewed is an incident that will recur.
Severity framework
| Severity | Impact | Response time | Escalation |
|---|---|---|---|
| SEV1 | Customer data loss, full outage, SLA breach | Immediate — wake on-call lead | Engineering director + comms |
| SEV2 | Major feature degraded, >20% error rate | < 15 min | On-call lead + affected team |
| SEV3 | Minor degradation, workaround available | < 1h | Team Slack channel |
| SEV4 | Low impact, no SLO breach | Next business day | Ticket only |
NIST SP 800-61 lifecycle
Detect → Triage → Contain → Eradicate → Recover → Post-mortem
Steps
- Detect and classify. Is this a real incident or a false positive? Check: baseline metrics normal? Alert recently changed? If false positive → suppress alert and file a tuning ticket; stop here.
- Declare severity. Apply the severity framework above. When in doubt, escalate up and downgrade later — under-escalation costs more than over-escalation.
- Assign roles. Incident commander (owns comms + decisions), tech lead (owns diagnosis + fix), comms lead (stakeholder updates). One person can cover multiple roles for SEV3/4.
- Contain. Isolate blast radius before root-cause analysis. Feature flag off? Rollback? Kill canary? Do the fastest safe contain action first.
- Diagnose. Read logs and traces chronologically from the first anomaly. Golden signals: which of latency/traffic/errors/saturation broke first? Follow the causal chain.
- Eradicate + recover. Apply the fix; verify with health checks and SLI recovery; confirm SLO is back inside budget.
- Post-mortem (mandatory for SEV1/2). Blameless — systems and processes, not people. Template: timeline, impact, root cause, contributing factors, action items with owners + due dates. Review within 5 business days.
Post-mortem template (key sections)
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.
- 8d ago First seen · 63 lines · 85 tokens per session scan A 7a36be922e45
incident-response is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 892 once invoked, about $0.0004 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
issue-debugging
Systematic methodology for issue debugging including root cause analysis, impact mapping, tiered validation plans, and confidence assessment. Use when analyzing bugs, fixing issues, or validating fixes.
fix-bug
Run the Fix Validation pipeline to investigate, fix, and validate a bug. Ensures deterministic pipeline execution with IssueAnalyzer, FixWriter, TestWriter (conditional), TestAudit (conditional), and FixValidator stages.
pact-bug
Log a bug investigation using PACT's structured bug tracker.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
hive.error-recovery
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.