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 agentmods add commands/edobreque/clens/session-comparegit clone --depth 1 https://github.com/edobreque/clensWhat 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 | $0.00013 | $0.00811 |
| Opus 5 | $0.00006 | $0.00405 |
| Sonnet 5 | $0.00003 | $0.00162 |
| Haiku 4.5 | $0.00001 | $0.00081 |
Grade A, and why
session-compare 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 2d 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.
This is a copy
100% identical to session-compare — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Compare Command
Compare two distilled clens sessions side-by-side to identify performance differences and determine which approach was more effective.
Setup
Load the session-analysis skill for schema knowledge and interpretation context before proceeding.
Variables
TARGET: $ARGUMENTS
Workflow
1. Resolve Both Sessions
- If TARGET contains two session IDs (space-separated), use those
- If TARGET is
--last 2or--last, find the two most recent distilled sessions in.clens/distilled/ - If TARGET contains only one session ID, use it as Session A and the most recent other session as Session B
- If fewer than 2 distilled sessions exist, inform the user:
Need at least 2 distilled sessions to compare. Run
clens distillon more sessions first.
Label the older session as Session A and the newer as Session B.
2. Gather Data for Both Sessions
Read both distilled JSON files from .clens/distilled/{sessionId}.json for the full DistilledSession objects. Each contains all extracted data: stats, backtracks, decisions, file_map, git_diff, edit_chains, reasoning, user_messages, summary, timeline, agents, team_metrics, communication_graph, plan_drift, and cost_estimate.
No CLI commands are needed — the distilled JSON files are the primary data source.
3. Compute Metrics Comparison
Build a comparison table with deltas for:
| Metric | How to Compare |
|---|---|
| Duration | Shorter is better |
| Tool calls | Fewer is generally better |
| Failures | Fewer is better |
| Failure rate | Lower is better |
| Estimated cost | Lower is better |
| Backtracks | Fewer is better |
| Files touched | Context-dependent |
| Files modified | Context-dependent |
| Thinking blocks | Context-dependent |
Use arrows or indicators to mark which session performed better on each metric.
4. Compare Backtracks
Break down backtracks by type for both sessions:
failure_retrycount in A vs Biteration_strugglecount in A vs Bdebugging_loopcount in A vs B
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.
- 2d ago First seen · 105 lines · 13 tokens per session scan A 5ce8d017c770
session-compare is a command published in the GitHub repository edobreque/clens (2 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 811 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to session-compare, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
session-report
Analyze a distilled clens session and generate a structured performance report.
backtrack-analysis
Deep-dive into backtracking patterns from distilled clens sessions.
session-compare
Compare two distilled clens sessions side-by-side to identify performance differences.
project-hierarchy-check
Use this command before changing organisation, project, or database config behavior.
security-validation
Use this command before handing off security-sensitive OpenLIT changes.
code-review
Perform a comprehensive review of code changes, checking quality, security, performance, and convention compliance.