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 bolivian-peru/os-moda --skill self-healinggit clone --depth 1 https://github.com/bolivian-peru/os-modaWrote 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/bolivian-peru/os-moda/self-healing)<a href="https://agentmods.dev/skills/bolivian-peru/os-moda/self-healing"><img src="https://agentmods.dev/badge/skills/bolivian-peru/os-moda/self-healing/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/bolivian-peru/os-moda/self-healing"><img src="https://agentmods.dev/badge/skills/bolivian-peru/os-moda/self-healing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 139 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00043 | $0.00964 |
| Opus 5 | $0.00022 | $0.00482 |
| Sonnet 5 | $0.00009 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
self-healing 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 11d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Healing Skill
You can detect, diagnose, and fix system problems automatically.
Detection
When you detect a service failure or anomaly during a heartbeat check:
-
Check teachd for historical patterns first — teachd observes the system 24/7 between conversations
teach_context({ context: "nginx failure service down" }) teach_patterns({ min_confidence: 0.5 })This surfaces slow-burn issues (memory leaks, recurring failures, correlated events) that you wouldn't catch in a single conversation.
-
Confirm the failure — don't act on a single check
service_status({ service: "nginx" })If the service is down, check again after 10 seconds. If still down, proceed.
-
Check journal logs for why it failed
journal_logs({ unit: "nginx", lines: 30, priority: "err" }) -
Recall past incidents — have we seen this before?
memory_recall({ query: "nginx failure", timeframe: "30d" })
Diagnosis
Determine the root cause before acting:
- Service crashed → check logs for segfault, OOM, config error
- Config file missing/corrupted → check if NixOS generation has it
- Dependency failure → another service it depends on is down
- Resource exhaustion → disk full, OOM killer, too many connections
- Bad deploy → most recent nixos-rebuild introduced the issue
Remediation (ordered by safety)
Level 1: Restart the service
shell_exec({ command: "systemctl restart nginx" })
Safe, fast, fixes 80% of issues.
Level 2: NixOS rollback
If restart doesn't fix it, or if config is corrupted:
shell_exec({ command: "nixos-rebuild switch --rollback" })
This atomically reverts to the last known-good NixOS generation.
Level 3: Targeted config fix
If you can identify the exact config issue:
file_read({ path: "/etc/nixos/configuration.nix" })
Fix the config, then rebuild:
shell_exec({ command: "nixos-rebuild switch" })
Level 4: Resource relief
If disk/memory is the problem:
shell_exec({ command: "nix-collect-garbage -d" })
shell_exec({ command: "journalctl --vacuum-size=500M" })
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.
- 11d ago First seen · 143 lines · 43 tokens per session scan A 7e874c985759
self-healing is a skill published in the GitHub repository bolivian-peru/os-moda (117 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 964 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 2026-08-30.
Other skills, from other repositories
gateway-doctor
Use when diagnose and fix MCP gateway routing issues, health checks, and server connectivity problems. Use when working with gateway doctor.
devops-incident-responder
Use when actively responding to production incidents, diagnosing critical service failures, or conducting incident postmortems to implement permanent fixes and preventative measures.
analyzing-linux-elf-malware
Analyzes malicious Linux ELF (Executable and Linkable Format) binaries including botnets, cryptominers, ransomware, and rootkits targeting Linux servers, containers, and cloud infrastructure. Covers static analysis, dynamic tracing, and reverse engineering of x8664 and ARM ELF samples. Activates for requests involving…
analyzing-linux-kernel-rootkits
Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (checksyscall, lsmod, hiddenmodules), rkhunter system scanning, and /proc vs /sys discrepancy analysis to identify hooked syscalls, hidden kernel modules, and tampered system structures.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.