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 skills/edobreque/clens/session-reportnpx skills add edobreque/clens --skill session-reportgit clone --depth 1 https://github.com/edobreque/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/skills/edobreque/clens/session-report)<a href="https://agentmods.dev/skills/edobreque/clens/session-report"><img src="https://agentmods.dev/badge/skills/edobreque/clens/session-report.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.01250 |
| Opus 5 | $0.00006 | $0.00625 |
| Sonnet 5 | $0.00002 | $0.00250 |
| Haiku 4.5 | $0.00001 | $0.00125 |
Grade A, and why
session-report 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 4d 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-report — 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Report
Generate a structured performance report for a distilled clens session.
Variables
TARGET: $ARGUMENTS
Instructions
1. Resolve the Session
- If TARGET is empty or
--last, find the most recent distilled session:- List files in
.clens/distilled/sorted by modification time - Use the most recently modified
.jsonfile
- List files in
- If TARGET is a session ID (full UUID or prefix), find
.clens/distilled/{TARGET}*.json - If no distilled file is found, tell the user:
No distilled session found. Run
clens distill --lastto distill your most recent session, then re-run this command.
2. Read the Data
- Read the distilled JSON file at
.clens/distilled/{sessionId}.json - Parse the full
DistilledSessionobject - Load the
session-analysisskill for schema and interpretation context
3. Generate the Report
Use the following template. Replace all placeholders with actual data. Omit sections that have no data (e.g., skip Backtracks section if array is empty, skip Agents section if not a multi-agent session).
Session Report: {session_id first 8 chars}
Overview
| Metric | Value |
|---|---|
| Duration | {summary.key_metrics.duration_human} |
| Model | {stats.model or "unknown"} |
| Tool calls | {stats.tool_call_count} |
| Failures | {stats.failure_count} ({failure_rate as percentage}%) |
| Files touched | {stats.unique_files.length} |
| Files modified | {summary.key_metrics.files_modified} |
| Estimated cost | ${stats.cost_estimate.estimated_cost_usd} |
| Backtracks | {backtracks.length} |
| Thinking blocks | {reasoning.length} |
Narrative
{summary.narrative}
Efficiency Score
Calculate a score from 1-10 based on these weighted factors:
- Failure rate (weight 3): 10 if <5%, 7 if 5-15%, 4 if 15-30%, 1 if >30%
- Backtrack density (weight 3): 10 if 0, 8 if 1-2, 5 if 3-4, 2 if 5+
- Cost efficiency (weight 2): 10 if cost/file < $0.50, 7 if < $1.00, 4 if < $2.00, 1 if > $2.00
- Phase coherence (weight 2): 10 if clear progression, 5 if some back-and-forth, 2 if chaotic
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.
- 4d ago First seen · 138 lines · 12 tokens per session scan A 4e035c6cc2aa
session-report is a skill published in the GitHub repository edobreque/clens (2 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 1,250 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-report, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
backtrack-analysis
Deep-dive into backtracking patterns from distilled clens sessions.
journey-report
Analyze cross-session development lifecycle and generate a journey report.
session-analysis
Schema knowledge and interpretation guide for clens distilled session data. Auto-loads when reading .clens/distilled/ files.
session-compare
Compare two distilled clens sessions side-by-side to identify performance differences.
session-report
Analyze a distilled clens session and generate a structured performance report.
api-endpoints
Adding or changing API operations in @repo/operations. One source of truth (defineOperation + a Zod schema) becomes an HTTP endpoint, an OpenAPI operation, an MCP tool, TS + Python SDK methods, a latitude CLI command, and an in-process agent tool — descriptions and contracts must be written with all of these readers…