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 aksika/abtars --skill abtars-runtime-operationsgit clone --depth 1 https://github.com/aksika/abtarsWrote 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/aksika/abtars/abtars-runtime-operations)<a href="https://agentmods.dev/skills/aksika/abtars/abtars-runtime-operations"><img src="https://agentmods.dev/badge/skills/aksika/abtars/abtars-runtime-operations/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/aksika/abtars/abtars-runtime-operations"><img src="https://agentmods.dev/badge/skills/aksika/abtars/abtars-runtime-operations.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 | $0.00027 | $0.01503 |
| Opus 5 | $0.00014 | $0.00751 |
| Sonnet 5 | $0.00005 | $0.00301 |
| Haiku 4.5 | $0.00003 | $0.00150 |
Grade A, and why
abtars-runtime-operations 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 yesterday.
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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
abTARS Runtime Operations
Use this skill for questions or changes involving the running abTARS instance: health, configuration, models, providers, skills, scheduled tasks, logs, backups, updates, restarts, or deployment state.
Safety rules
- Inspect first. Do not mutate runtime state because a problem is merely suspected.
- Runtime configuration changes, restarts, updates, restores, and deletions require an explicit operator request.
- Never print, copy, or paste secrets, tokens, cookies, private keys, or peer tokens.
- Use redacted commands and status/doctor output whenever possible.
- Never edit files under
~/.abtars-releases/,~/.abtars/app, or deployed bundles. skills/core/andprompts/are deployment-managed and may be overwritten.- Never use raw
pkill,kill -9, orlaunchctl bootout; use the abTARS CLI. - Do not modify watchdog thresholds, heartbeat behavior, or watchdog files.
Runtime roots
Use the configured roots when present:
ABTARS_HOME— writable runtime state; normally~/.abtars/~/.abtars-releases/current— active read-only release~/.abtars-releases/src/— deployment source checkout; do not edit on the host~/.local/bin/— CLI wrappers
If the root is uncertain, begin with:
abtars status
abtars doctor
abtars config
abtars config redacts values that look like credentials. Do not replace it with
cat ~/.abtars/config/.env.
Runtime layout
| Path | Ownership and purpose |
|---|---|
config/.env |
Main environment configuration |
config/.env.skills |
Non-secret integration and skill settings |
config/transport.json |
Active route, providers, agent assignments, and fallbacks |
config/transport.old.json |
Previous transport configuration |
config/transport.default.json |
Factory/default transport configuration |
config/models.json |
Model metadata catalog, not active routing |
config/users.json |
User registry and platform identities |
config/peers.json |
Peer/API identities and access control |
config/abmind.json |
Optional abmind endpoint configuration |
config/budget.json |
Budget and usage limits |
config/pi-executor.json |
Pi executor settings |
config/sha-policy*.json |
Self-healer policy |
config/irc.json |
Optional IRC configuration |
secret/ |
Encrypted or protected credentials; never expose contents |
skills/core/ |
Shipped skills; overwritten during deployment |
skills/self/ |
Agent-created skills |
skills/custom/ |
Operator-provided skills |
skills/downloaded/ |
Marketplace/downloaded skills |
skills/skills_catalog.md |
Generated skill index |
prompts/ |
Deployment-managed prompt files |
tasks/tasks.json |
Scheduled task registry |
logs/ |
Bridge, watchdog, and agent logs |
state/, kanban/, workspace/ |
Runtime state and work data |
bridge.lock |
Process and heartbeat state |
deploy.state |
Deployment/restart state |
manifest.json |
Active deployment metadata |
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.
- yesterday First seen · 195 lines · 27 tokens per session scan A f517cb87a12b
abtars-runtime-operations is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 1,503 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 2026-09-08.
Other skills, from other repositories
chaos-experiment
Design and document chaos engineering experiments. Guide steady state baseline, hypothesis formation, failure injection plans, and results analysis. Use when you say "design a chaos experiment", "plan a game day", "failure injection", "test resilience", or "chaos engineering". Do NOT use for security threat analysis…
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
cloud-solution-architect
Design well-architected Azure cloud systems — 10 design principles, 6 architecture styles, 44 design patterns, technology choices, WAF pillars.
bicep-avm-mastery
Azure Verified Modules (AVM), Bicep best practices, and MCP-powered infrastructure as code for Azure.
foundry-agent-platform
Microsoft Foundry agent deployment, orchestration, and cloud-native AI service patterns.
sse-streaming
POST-based Server-Sent Events streaming for Azure Functions — HTTP streaming, chunked response parsing, reconnection.