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 skills add sliamh11/Deus --skill review-logsgit clone --depth 1 https://github.com/sliamh11/DeusWrote 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/sliamh11/deus/review-logs)<a href="https://agentmods.dev/skills/sliamh11/deus/review-logs"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/review-logs/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/skills/sliamh11/deus/review-logs"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/review-logs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Rogue Agent · line 62 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 62 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00036 | $0.00723 |
| Opus 5 | $0.00018 | $0.00362 |
| Sonnet 5 | $0.00007 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
review-logs 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 6d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-logs
Runs the Deus log review and rotation system at scripts/log_review.py.
Subcommands
Run the appropriate command based on what the user asks for:
| User intent | Command |
|---|---|
| Full run / daily review / "what's wrong" | python3 scripts/log_review.py |
| See last report / summary | python3 scripts/log_review.py --summary |
| See pinned / flagged issues | python3 scripts/log_review.py --pinned |
| Clean up old logs / rotate | python3 scripts/log_review.py --rotate-only |
| Re-analyze without rotating | python3 scripts/log_review.py --review-only |
If invoked with no further context, run the full review (python3 scripts/log_review.py).
What each mode does
Full run (default):
- Deletes container logs older than
LOG_CONTAINER_RETENTION_DAYS(default: 14 days) - Archives
logs/deus.log/logs/deus.error.logtologs/archives/if they exceedLOG_MAIN_MAX_MB(default: 20 MB) and truncates them - Reads new log entries since the last review (byte-offset tracked — never re-reads old entries)
- Scans new container session logs for errors
- Sends collected warnings/errors to a local Ollama model (
LOG_REVIEW_MODEL, default:gemma4:e4b) for structured health analysis - Saves daily report to
~/.deus/reviews/YYYY-MM-DD.md - Pins DEGRADED/CRITICAL reports to
~/.deus/reviews/pinned.mdand fires a macOS notification
Health levels returned by Ollama:
OK— no actionable issuesDEGRADED— issues present, not urgentCRITICAL— needs immediate attention, gets pinned
Output interpretation
After running, explain the health report to the user:
- Summarize the Issues Found section in plain language
- For each Action Required item, explain what it means and how to fix it
- If health is OK, confirm the system is running cleanly
- If issues are pinned, tell the user they can run
deus logs pinnedanytime to review them
Environment overrides
| Variable | Default | Effect |
|---|---|---|
LOG_REVIEW_MODEL |
gemma4:e4b |
Ollama model for analysis |
OLLAMA_HOST |
http://localhost:11434 |
Ollama server URL |
LOG_CONTAINER_RETENTION_DAYS |
14 |
Days before container logs are deleted |
LOG_MAIN_MAX_MB |
20 |
Main log size threshold for archiving |
LOG_ARCHIVE_RETENTION_DAYS |
30 |
Days before archived logs are deleted |
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.
- 6d ago First seen · 63 lines · 36 tokens per session scan A fe1e214c7208
review-logs is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 723 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
ha-self-diagnosis
Self-understanding and issue reporting for Hope Agent itself. Use when the user asks how Hope Agent works internally, asks about its own source code/docs/runtime behavior, reports a bug/failure/slowness/crash, asks to diagnose logs, or asks to create/submit a GitHub issue for a bug, feature request, or improvement…
sentry-app-setup
Create and configure a Sentry internal integration so the assistant can manage issues, alerts, and releases under its own identity.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
diagnostic-first-refactoring
Analyze codebase structure before making changes — the "Surgeon's Scan" pattern.
investigate
Systematic root-cause debugging: find the cause before writing any fix.