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 JetXu-LLM/DocMason --skill runtime-log-reviewgit clone --depth 1 https://github.com/JetXu-LLM/DocMasonWrote 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/jetxu-llm/docmason/runtime-log-review)<a href="https://agentmods.dev/skills/jetxu-llm/docmason/runtime-log-review"><img src="https://agentmods.dev/badge/skills/jetxu-llm/docmason/runtime-log-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.00916 |
| Opus 5 | $0.00014 | $0.00458 |
| Sonnet 5 | $0.00005 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
runtime-log-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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Log Review
Use this skill when the task is to review recent runtime activity, identify failures, or extract candidate cases from DocMason logs.
This is an explicit operator-facing workflow.
The user may ask for it directly, or ask may route here automatically when the real intent is runtime review rather than question answering.
Required Capabilities
- local file access
- shell or command execution
- ability to inspect structured JSON output
If the agent cannot inspect local runtime logs, stop and explain that log review is not possible.
Procedure
- For an explicit operator refresh, prefer
docmason workflow runtime-log-review --jsonso the derived summary and the request-level audit record are regenerated together. - Start with
runtime/logs/review/summary.jsonandruntime/logs/review/benchmark-candidates.jsonwhen they exist.- treat live conversation state under
runtime/state/as the owner andruntime/logs/conversations/as projection-onlyprojection-onlymeans a derived mirror, not the primary truth surface
- require canonical ask ownership before classifying a case as
interactive-ask; workflow names, conversation linkage, or reconciliation leftovers alone are not enough- here
canonical ask ownershipmeans the case is backed by a governed ask turn and linked runtime artifacts, not only host transcript residue
- here
- treat live conversation state under
- Use the summary modes that best match the request:
- recent activity
- no-result retrieval sessions
- artifact-rich queries that still degraded or returned the wrong source family
- degraded answer-first traces
- trace cases where artifact supports existed but the final answer still remained partially grounded or unresolved
- repeated failure patterns
- frequently consulted sources or units
- candidate benchmark or operator-review cases
- real interaction activity versus synthetic evaluation traffic
- active waiting shared jobs
- active confirmation-required shared jobs
- orphaned query sessions or retrieval traces that are not backed by committed truth
- When the summary shows a case worth deeper inspection, open the referenced query-session or retrieval-trace JSON directly.
- If the operator needs the underlying evidence, route to retrieval, provenance tracing, or grounded-answer rather than guessing from log metadata alone.
- Keep the workflow descriptive and review-oriented. Do not mutate prompts, skills, overlays, or benchmarks from inside this workflow.
- If you need to export a scratch review summary and the user did not specify a destination, place it under
runtime/agent-work/. - Treat
runtime/logs/review/requests/<request_id>.jsonas the canonical audit surface for the explicit review request that refreshed or read the review-side outputs. - Return the operator-facing review summary and recommended next steps to the main agent.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 68 lines · 27 tokens per session scan A f7cc41b270c1
runtime-log-review is a skill published in the GitHub repository JetXu-LLM/DocMason (135 stars, last pushed 5d ago), licensed Apache-2.0. It adds 27 tokens to every session and 916 once invoked, about $0.0001 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
openkb-deck-neon
A skill for creating a single-file HTML slide deck from content stored in OpenKB, a knowledge-base chat system. It defines a dark, high-tech visual style using neon colors, glow effects, and glass-like panels.
openkb-deck-editorial
A tool for creating a single-file HTML slide presentation from compiled knowledge-base content. Its visual style uses a warm cream background, serif typography, and brick-red accents.
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
openlore
Query and publish to an OpenLore knowledge base over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.