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 Tommy-yw/RunbookHermes --skill payment-503-spikegit clone --depth 1 https://github.com/Tommy-yw/RunbookHermesWrote 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/tommy-yw/runbookhermes/payment-503-spike)<a href="https://agentmods.dev/skills/tommy-yw/runbookhermes/payment-503-spike"><img src="https://agentmods.dev/badge/skills/tommy-yw/runbookhermes/payment-503-spike/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tommy-yw/runbookhermes/payment-503-spike"><img src="https://agentmods.dev/badge/skills/tommy-yw/runbookhermes/payment-503-spike.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00501 |
| Opus 5 | $0.00000 | $0.00251 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
payment-503-spike 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Payment Service HTTP 503 Spike After Release
Use this skill when payment-service starts returning HTTP 503 shortly after a release, especially after version v2.3.1.
Goal
Find whether the new release caused a database connection pool regression, then propose a safe rollback path.
Evidence to collect
prom_top_anomalies(service="payment-service")- Look for
http_503_rate, p95 latency, and request volume changes.
- Look for
loki_query(service="payment-service", query="connection pool exhausted")- Look for database pool exhaustion or timeout messages.
trace_search(service="payment-service", error_only=true)- Look for slow or failed spans to
mysql-payment.
- Look for slow or failed spans to
recent_deploys(service="payment-service")- Check whether
v2.3.1was deployed shortly before the HTTP 503 increase.
- Check whether
incident_rca_guard(...)- Confirm the evidence is consistent before producing the final RCA.
action_policy_guard(...)- Generate policy-checked actions.
Decision logic
A release regression is likely when all of these are true:
payment-servicehas a recent deployment such asv2.3.1.- HTTP 503 rate increases after the deployment.
- Logs include
connection pool exhaustedor similar DB pool messages. - Trace evidence points to
mysql-paymentlatency or failed spans.
Recommended action
If the above evidence is present, propose:
rollback_canary(service="payment-service", target_revision="v2.3.0", dry_run=true)first.- If the operator approves, call
rollback_canary(..., dry_run=false, approval_id="..."). - Then call
verify_recovery(service="payment-service").
Safety rules
- Never execute rollback without approval.
- Always create a checkpoint before destructive execution.
- Keep raw logs and full traces out of stable memory.
- Final answer must cite evidence IDs.
Final answer template
- Root cause: ...
- Evidence:
ev_metric_http_503_rate,ev_log_pool_exhausted,ev_trace_mysql_latency,ev_deploy_v231 - Recommended action: rollback from
v2.3.1tov2.3.0after approval. - Verification: check HTTP 503 rate and p95 latency for 10 minutes.
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 · 50 lines · 0 tokens per session scan A 42790cc89c81
payment-503-spike is a skill published in the GitHub repository Tommy-yw/RunbookHermes (544 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 501 tokens. 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 2026-09-03.
Other skills, from other repositories
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
convex-insights
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.
ssl-proxy-troubleshoot
Systematic workflow for troubleshooting SSL/proxy connectivity issues with government websites.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
axiom-networking
Use when implementing or debugging ANY network connection, API call, or socket. Covers URLSession, Network.framework, NetworkConnection, connection diagnostics.