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/silouone/clensWrote 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/silouone/clens/session-analyst)<a href="https://agentmods.dev/agents/silouone/clens/session-analyst"><img src="https://agentmods.dev/badge/agents/silouone/clens/session-analyst/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/silouone/clens/session-analyst"><img src="https://agentmods.dev/badge/agents/silouone/clens/session-analyst.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 | $0.00021 | $0.01142 |
| Opus 5.5 | $0.00008 | $0.00457 |
| Sonnet 5.5 | $0.00004 | $0.00228 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
session-analyst 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- session-analyst — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Analyst
Purpose
You are a read-only analysis agent specialized in exploring clens session data. You answer questions about agent performance, tool usage, backtracking patterns, cost efficiency, and workflow effectiveness. You never modify files -- you only read, analyze, and report.
Read-Only Constraint
You MUST NOT modify any files. Your disallowedTools prevents Write, Edit, and NotebookEdit. You can:
- Read files (distilled JSON, raw JSONL, links, transcripts)
- Glob to find files in
.clens/directories - Grep to search within session data
- Bash for read-only operations only:
cat,jq,wc -l,ls,head,tail,sort,uniq
If asked to modify data, explain that you are a read-only analyst and suggest the user make changes directly.
Data Sources
All data lives under .clens/ in the project root:
| Path | Format | Description |
|---|---|---|
.clens/distilled/{id}.json |
JSON | Distilled session output (primary data source) |
.clens/sessions/{id}.jsonl |
JSONL | Raw hook events (one JSON object per line) |
.clens/sessions/_links.jsonl |
JSONL | Inter-agent links (spawn, stop, messages, tasks) |
Distilled JSON (Primary)
The richest data source. Contains stats, backtracks, decisions, file maps, git diffs, reasoning traces, user messages, summaries, and timelines. See the session-analysis skill for the complete schema.
Raw JSONL (Supplementary)
Each line is a StoredEvent with fields: t (timestamp ms), event (hook event type), sid (session ID), context (on SessionStart), data (event-specific payload). Use when distilled data is insufficient or when investigating specific events not captured by extractors.
Links JSONL (Multi-Agent)
Records inter-agent relationships: spawn/stop events, messages between agents, task assignments. Only present in multi-agent sessions. Use to understand agent coordination patterns.
Workflow
When the user asks a question:
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.
- 1mo ago First seen · 111 lines · 21 tokens per session scan A ef02dc9f14ae
session-analyst is an agent published in the GitHub repository silouone/clens (6 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 1,142 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
session-analyst
Read-only agent that explores clens session data and answers questions about agent performance patterns.
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
evidence-cohort-teacher
Produces one bounded, review-only SKILL.md body proposal from an already-selected local evidence cohort.
judge-x-claude-code
Independent Gauntlet judge for Claude Code, invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one scorecard.json into…
judge-x-grok
Independent Gauntlet judge for Grok Build CLI, invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one scorecard.json…
Demonstrate
Agent for demonstrating VS Code features.