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 zircote-plugins/claude-team-orchestration --skill jsonl-log-analyzergit clone --depth 1 https://github.com/zircote-plugins/claude-team-orchestrationWrote 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/zircote-plugins/claude-team-orchestration/jsonl-log-analyzer)<a href="https://agentmods.dev/skills/zircote-plugins/claude-team-orchestration/jsonl-log-analyzer"><img src="https://agentmods.dev/badge/skills/zircote-plugins/claude-team-orchestration/jsonl-log-analyzer/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/zircote-plugins/claude-team-orchestration/jsonl-log-analyzer"><img src="https://agentmods.dev/badge/skills/zircote-plugins/claude-team-orchestration/jsonl-log-analyzer.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 | $0.00058 | $0.03261 |
| Opus 5 | $0.00029 | $0.01631 |
| Sonnet 5 | $0.00012 | $0.00652 |
| Haiku 4.5 | $0.00006 | $0.00326 |
Grade A, and why
jsonl-log-analyzer 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 9d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JSONL Log Analyzer
Automated schema-aware analysis of large JSONL log files. Discovers the field schema dynamically, generates tailored jq extraction recipes, and orchestrates the standard RLM fan-out/fan-in pipeline — making JSONL log analysis a single-prompt operation.
Related skills:
- RLM Pattern — Core chunked analysis pattern this skill builds on
- Orchestration Patterns — Pattern 7 (RLM) and team lifecycle
Architecture
flowchart TD
A[User prompt + JSONL file path] --> B[Phase 1: Schema Discovery]
B -->|inline: head + jq| C[Schema extract + field classification]
C --> D[Phase 2: Partition & Generate Prompts]
D -->|chunk file by line count| E[Chunk 1]
D --> F[Chunk 2]
D --> G[Chunk N]
E --> H["swarm:rlm-json-analyzer<br/>(Haiku)"]
F --> I["swarm:rlm-json-analyzer<br/>(Haiku)"]
G --> J["swarm:rlm-json-analyzer<br/>(Haiku)"]
H --> K[Phase 3: Synthesis]
I --> K
J --> K
K -->|"swarm:rlm-synthesizer<br/>(Sonnet)"| L[Final Report]
Three phases:
- Schema Discovery — Extract field paths, types, and presence counts using
head/tail+jq. No raw log lines enter the orchestrator's context. - Partition & Generate Prompts — Split the file by line count, generate per-chunk analyst prompts with schema summary and tailored jq recipes.
- Synthesis — Aggregate analyst findings into a coherent report with log-specific guidance (temporal patterns, error clustering, service breakdown).
When to Use
| Scenario | Use This Skill? |
|---|---|
| Large JSONL log file (>1500 lines) | Yes |
| Incident investigation in structured logs | Yes |
| Traffic/request analysis from JSONL event streams | Yes |
| JSONL files with unknown or evolving schema | Yes |
| Plain text logs (unstructured) | No — use basic RLM with swarm:rlm-chunk-analyzer |
| Small JSONL file (<1500 lines) | No — Claude handles it directly |
| JSON array (not line-delimited) | No — use Content-Aware JSON RLM |
| CSV/TSV data files | No — use Content-Aware CSV RLM |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 301 lines · 58 tokens per session scan A 2260009c95b1
jsonl-log-analyzer is a skill published in the GitHub repository zircote-plugins/claude-team-orchestration (14 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 3,261 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
flash-attention
Speed up long-sequence transformer training and inference.
nemo-curator
Curate LLM training data: dedupe, filter, PII redaction.
llava
Vision-language chat: VQA, captioning, image dialogue.
simpo
Reference-free preference alignment, simpler than DPO.
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…