Borrowing it
Nothing to install: this file belongs to sageox/ox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sageox/ox/main/.claude/skills/ox-session-review/SKILL.mdgit clone --depth 1 https://github.com/sageox/oxWrote 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/sageox/ox/ox-session-review)<a href="https://agentmods.dev/skills/sageox/ox/ox-session-review"><img src="https://agentmods.dev/badge/skills/sageox/ox/ox-session-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 13 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium System Prompt Leakage · line 262 Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
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 | $0.00111 | $0.03624 |
| Opus 5 | $0.00056 | $0.01812 |
| Sonnet 5 | $0.00022 | $0.00725 |
| Haiku 4.5 | $0.00011 | $0.00362 |
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 8d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill carries the operational knowledge from the 2026-04-25 cleanup (see PRs #559–#564 and bd ox-b917, ox-9o29, ox-4ncz, ox-1i3k). Read the Failure-mode watch-list before acting — it is the difference between a routine audit and re-causing the same incident.
Failure-mode watch-list (READ FIRST)
When operating on the ledger, watch for and handle each of these explicitly. Silent skipping is not allowed — surface them in the report.
| Mode | Symptom | Right action |
|---|---|---|
| Cache-only invariant break | After hydration, the in-place <ledger>/sessions/<name>/raw.jsonl is real content (not a ~140B LFS pointer). |
Stop. Do not run any ox command that may git add the session dir. Investigate which code path wrote in-place — likely a regression of .claude/rules/cache-only-design.md. |
| Phantom LFS OID | ox session download returns HTTP 404 from the LFS Batch API for an OID referenced in meta.json. |
Unrecoverable from client. ox session remove <name> --force and report the lost session in the final summary. |
| 0-byte in-place stub | meta.json references a real OID, but in-place file is 0 bytes (and not a pointer). |
Treat as needing download. Confirm cmd/ox/session_hydrate.go has the info.Size() > 0 guard (PR #564). Without it, the resolver will silently return "" forever. |
| Daemon anti-entropy clobber | A freshly-pushed good summary gets overwritten with a failure-marker stub minutes later. | The daemon scheduled finalize before our regen landed. Look at internal/daemon/agentwork/session_finalize.go workNoLongerNeeded re-verify guard (PR #561). If running a long batch regen, prefer a quiet daemon window. |
| Validation banner on the website | Site shows "Summary failed content validation: title too short" but the ledger has good content. | Likely browser-side React Query cache (staleTime 5m, gcTime 30m). Verify origin/main HEAD has the right summary; advise hard refresh. Do not "fix" by re-pushing. |
| LLM regenerate hangs / asks for permission | Regenerate spawns Claude Code and times out without writing. | Pass --permission-mode bypassPermissions to the headless invocation (PR #560 / regenerate flow). |
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.
- 8d ago First seen · 309 lines · 111 tokens per session scan A 53ac0ccefe01
ox-session-review is a skill published in the GitHub repository sageox/ox (51 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 3,624 once invoked, about $0.0006 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
neo4j-snowflake-graph-analytics-skill
Run Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra, KNN, Node2Vec, FastRP, GraphSAGE) directly inside Snowflake without moving data. Use when running graph algorithms against Snowflake tables via the Neo4j Snowflake Native App ("GDS Snowflake", "graph algorithms in Snowflake", "Neo4j Graph…
neo4j-aura-graph-analytics-skill
Serverless Aura Graph Analytics (AGA) GDS Sessions — covers GdsSessions, AuraGraphDataScience, AuraAPICredentials, DbmsConnectionInfo, SessionMemory, getorcreate, remote graph projection with gds.v2.graph.project and gds.graph.project.remote, gds.v2 session endpoints, gds.v2.graph.construct, AuraDB Cypher API…
neo4j-driver-dotnet-skill
Neo4j .NET Driver v6 — IDriver lifecycle, DI registration (singleton), ExecutableQuery fluent API, ExecuteReadAsync/ExecuteWriteAsync managed transactions, IResultCursor (FetchAsync/ ToListAsync), record value access (.Get /As ), null safety, UNWIND batching, temporal types, await using, EagerResult, object mapping…
neo4j-getting-started-skill
Orchestrates zero-to-running-app in 8 stages — prerequisites → context → provision → model → load → explore → query → build. Each stage reads its own reference file. Supports HITL and fully autonomous operation. Use when starting a new Neo4j project from scratch, provisioning Aura, generating synthetic data, building…
neo4j-import-skill
Import structured data into Neo4j — LOAD CSV, CALL IN TRANSACTIONS, neo4j-admin database import full (offline bulk), apoc.load.csv/json, apoc.periodic.iterate, driver batch writes. Covers method selection, header file format, type coercion, null handling, ON ERROR modes, CONCURRENT TRANSACTIONS, pre-import constraint…
neo4j-aura-agent-skill
Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete, and invoke Aura agents backed by an AuraDB instance. Use when configuring Aura Agent tools (CypherTemplate, SimilaritySearch, Text2Cypher), setting system prompts, deploying agents to REST or MCP endpoints, or invoking agents with…