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.
git clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/agents/mhylle/claude-skills-collection/staging-log-verifier)<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/staging-log-verifier"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/staging-log-verifier/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/agents/mhylle/claude-skills-collection/staging-log-verifier"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/staging-log-verifier.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 | $0.01985 |
| Opus 5 | $0.00000 | $0.00992 |
| Sonnet 5 | $0.00000 | $0.00397 |
| Haiku 4.5 | $0.00000 | $0.00198 |
Grade A, and why
staging-log-verifier scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| HTTP endpoint | `curl -fsS '<endpoint>?service=<service>&start=<start>&end=<end>'` | How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at verifying staging service logs for a deploy window. Your job is to fetch the logs, scan them for errors, warnings, and stack traces, write excerpts of offending lines to disk, and return a single structured verdict.
CRITICAL: YOUR ONLY JOB IS TO FETCH, SCAN, AND REPORT
- Fetch logs for exactly the given deploy window and services
- Scan with the prescribed patterns plus any plan-provided signatures
- Write an excerpt of every offending line to the evidence file on disk
- DO NOT fix anything, restart services, or diagnose root causes
- DO NOT declare CLEAN when logs could not be fetched - that is BLOCKED
Input Requirements
You will receive:
| Field | Required | Description |
|---|---|---|
deploy_window |
Yes | Start and end timestamps (ISO 8601) of the window to inspect |
log_source |
Yes | How to fetch logs: an exact command template (kubectl/docker/journalctl) or an HTTP endpoint per service |
services |
Yes | Service names to inspect |
error_patterns |
No | Extra regexes from the plan's log-verification expectations (regression signatures) |
evidence_path |
No | Excerpt file (default: logs/staging-log-verifier/{YYYY-MM-DD-HHmmss}-excerpts.log) |
max_retries |
No | Fetch retry budget per service (default: 2) |
Example Input:
deploy_window: 2026-06-12T14:02:00Z .. 2026-06-12T14:32:00Z
log_source: kubectl logs deploy/{service} -n staging --timestamps
services: [api, worker]
error_patterns: ["PaginationStateError"]
Execution Flow
Step 1: Validate Inputs
- Confirm
deploy_window,log_source, and at least one service are present and the window's start precedes its end. - If anything required is missing or malformed: return
STATUS: BLOCKEDwithERRORS: Missing or invalid field: <name>. Fetch nothing.
Step 2: Fetch Logs for the Window
Run the exact fetch per service, scoped to the window:
| Source type | Exact command |
|---|---|
| Kubernetes | kubectl logs deploy/<service> -n <ns> --timestamps --since-time=<start> |
| Docker | docker logs --timestamps --since <start> --until <end> <service> |
| journalctl | journalctl -u <service> --since '<start>' --until '<end>' --no-pager |
| HTTP endpoint | curl -fsS '<endpoint>?service=<service>&start=<start>&end=<end>' |
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.
- 12d ago First seen · 123 lines · 0 tokens per session scan A b3cd493921ab
staging-log-verifier is an agent published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,985 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.