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/sageox/agentx/ox-session-reviewgit clone --depth 1 https://github.com/sageox/agentxWrote 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/commands/sageox/agentx/ox-session-review)<a href="https://agentmods.dev/commands/sageox/agentx/ox-session-review"><img src="https://agentmods.dev/badge/commands/sageox/agentx/ox-session-review.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 | $0.00000 | $0.01168 |
| Opus 5 | $0.00000 | $0.00584 |
| Sonnet 5 | $0.00000 | $0.00234 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade A, and why
ox-session-review 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
98% identical to ox-session-review — 2 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit all sessions in the project ledger for quality, then offer cleanup and regeneration actions.
Phase 1 — Scan & Score (read-only)
- Run
ox session list --allto enumerate all sessions - Resolve the ledger sessions directory:
- Read
.sageox/config.jsonto getrepo_idand endpoint - The ledger lives at
~/.local/share/sageox/<endpoint-slug>/ledgers/<repo_id>/sessions/ - List subdirectories — each is a session folder
- Read
- For each session directory:
a. Read
meta.json— getentry_count,title,summary,files,created_atb. Readsummary.jsonif it exists — gettitle,summary,key_actions,outcomec. Check hydration status: ifraw.jsonlis missing or is an LFS pointer (starts withversion https://git-lfs.github.com), runox session download <session_name>to hydrate it d. Readraw.jsonl— count substantive messages, tool calls (Write/Edit), total entries e. Score quality using the signals below
Quality Signals
Categorize each session into one of these buckets (first match wins):
Removal Candidates
entry_countis 0 OR meta has nofilesmanifest- Very few substantive messages (< 3 user+assistant turns in
raw.jsonl) - Only skill invocations, no real work (e.g., just
/ox-session-start+/ox-session-stopwith nothing between) - Session errored/failed immediately (check
outcome= "failed" in summary, or raw.jsonl shows early error) - No files modified (zero Write/Edit tool calls) AND < 5 total entries in
raw.jsonl
Missing/Poor Summary
- No
summary.jsonexists at all summary.jsonhas empty or missingtitle,summary, orkey_actions- Summary is fallback stats-only text (matches pattern like "N user messages, N assistant responses")
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 · 115 lines · 0 tokens per session scan A c74ef276cafe
ox-session-review is a command published in the GitHub repository sageox/agentx (4 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,168 tokens. A static security scan graded it A with 0 findings. It is 98% identical to ox-session-review, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
iterate
Iteration delivery — delivery check + archive + commit & tag + bump version.
init
Initialize dev-flow project — scan current state, create/align .dev-doc, update agent instruction file.
task
Start TASK phase — task decomposition.
mode
Select development mode — control flow phases.
issue
DOCROOT obtained via dow status --field docroot.
fix
User-triggered workflow to automatically fix open issues.