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 chf3198/copilot-governance --skill mem-watchdog-opsgit clone --depth 1 https://github.com/chf3198/copilot-governanceWrote 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/chf3198/copilot-governance/mem-watchdog-ops)<a href="https://agentmods.dev/skills/chf3198/copilot-governance/mem-watchdog-ops"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/mem-watchdog-ops/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/chf3198/copilot-governance/mem-watchdog-ops"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/mem-watchdog-ops.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00035 | $0.01028 |
| Opus 5 | $0.00017 | $0.00514 |
| Sonnet 5 | $0.00007 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade B, and why
mem-watchdog-ops scanned grade B with 1 finding 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 10d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Prefer `systemctl --user` only — never `sudo systemctl`. How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mem Watchdog Ops Skill
Use this skill when working in constrained Crostini environments where VS Code, Chrome/Playwright, and extension host memory spikes can trigger OOM.
Ground Rules
- Never read or reason from
SwapFreevalues on Crostini. - Prefer
systemctl --useronly — neversudo systemctl. - Treat the mem-watchdog daemon as independent runtime authority.
- For tuning, use extension settings (
memWatchdog.*) so the extension writes config and restarts service safely.
Fast Workflows
-
Status snapshot
- Use chat participant command:
/memwatchdog status - Or run helper:
~/.copilot/skills/mem-watchdog-ops/watchdog-snapshot.sh
- Use chat participant command:
-
Recent actions / diagnosis
/memwatchdog logs- Look for action markers in journal:
ACTION(SIGTERM):ACTION(SIGKILL):RECOVERY(SIGTERM):
-
Apply tuning profile
/memwatchdog tune balanced— general dev use (warn 3.4 GB, emerg 3.8 GB)/memwatchdog tune conservative— earlier intervention (warn 3.0 GB, emerg 3.4 GB)/memwatchdog tune playwright— more headroom for automation (warn 3.8 GB, emerg 4.2 GB)
-
Manual protective action
/memwatchdog act kill chrome/memwatchdog act restart service
Tuning Guidance
- balanced: general dev use — recommended for Copilot Chat multi-agent workloads that peak at 3.0–3.5 GB
- conservative: earlier intervention, safer on tight RAM — may cause more Chrome kills
- playwright: more headroom for headed browser automation sessions
When recommending profile changes, explain expected trade-off between stability and interruption frequency.
Kill Hierarchy (daemon v20260329.1+)
| Condition | Action |
|---|---|
MemAvailable ≤ 15% |
SIGKILL Chrome/Playwright |
MemAvailable ≤ 25% |
SIGTERM Chrome/Playwright (deferred if Playwright active) |
| PSI full avg10 > 25% | SIGTERM Chrome (deferred if Playwright active) |
| VS Code RSS ≥ 3.8 GB | SIGKILL Chrome (always — even during Playwright sessions); if none → kill_vscode_main() |
| VS Code RSS ≥ 3.4 GB | SIGTERM Chrome (deferred if Playwright active); if none → kill helper (Shared Process, File Watcher, Network Service); if none → cgroup throttle/reclaim |
| RSS velocity spike | Kill lowest-value helper — never a language server or Extension Host at normal severity |
| Chrome PIDs > 3 | SIGKILL oldest excess (skipped when Playwright is active) |
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.
- 10d ago First seen · 87 lines · 35 tokens per session scan B cac06e88997a
mem-watchdog-ops is a skill published in the GitHub repository chf3198/copilot-governance (1 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,028 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.