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 yorrick/agent-skills --skill agent-session-monitorgit clone --depth 1 https://github.com/yorrick/agent-skillsWrote 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/yorrick/agent-skills/agent-session-monitor)<a href="https://agentmods.dev/skills/yorrick/agent-skills/agent-session-monitor"><img src="https://agentmods.dev/badge/skills/yorrick/agent-skills/agent-session-monitor/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/yorrick/agent-skills/agent-session-monitor"><img src="https://agentmods.dev/badge/skills/yorrick/agent-skills/agent-session-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Memory Poisoning · line 39 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00086 | $0.01656 |
| Opus 5 | $0.00043 | $0.00828 |
| Sonnet 5 | $0.00017 | $0.00331 |
| Haiku 4.5 | $0.00009 | $0.00166 |
Grade A, and why
agent-session-monitor 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 12d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Session Monitor
Use this skill to act as a meta agent for terminal agents running inside tmux. It is intentionally platform-neutral: the skill body uses the open Agent Skills format, and product-specific behavior lives in small references.
Compatibility Model
Keep one versioned source of truth:
agent-session-monitor/
.claude-plugin/plugin.json
skills/agent-session-monitor/
SKILL.md
scripts/
references/
Expose skills/agent-session-monitor to host-specific discovery paths with
symlinks or plugin installation. Do not copy the skill body into separate Claude
and Codex versions.
Read references/platforms.md when you need install-path or command details.
Read references/gsd.md only when monitoring GSD workflow panes.
Operating Rules
- Treat tmux panes as the source of truth. Capture the pane before every decision and again after sending input.
- Never interrupt a pane that is still working, compacting, streaming tokens, or showing an interrupt hint.
- Follow the watched agent's own next-step recommendation before applying a generic workflow. If the agent says to clear context, ask the user, or run a specific command, treat that as higher-signal than a rigid state machine.
- Send only commands that the user explicitly approved or that the watched agent explicitly requested and are low-risk in the current workflow.
- If a command is rejected, do not try an alternate command automatically. Show the rejection, explain the proposed correction, and get explicit approval unless the correction was already approved for this workflow.
- If a design appears to need fallback behavior, stop and ask first. This includes retry loops, alternate slash commands, heartbeats, replacement monitors, and rollover behavior after a monitor process exits.
- Do not clear or compact context when the agent is asking a real question, reporting ambiguity, requesting a decision, or waiting on credentials, approvals, destructive operations, or external state.
What ships with it
5 files 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.
- 12d ago First seen · 210 lines · 86 tokens per session scan A 32397597066a
agent-session-monitor is a skill published in the GitHub repository yorrick/agent-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 86 tokens to every session and 1,656 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…