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 hristo2612/jinn --skill self-healgit clone --depth 1 https://github.com/hristo2612/jinnWrote 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/hristo2612/jinn/self-heal)<a href="https://agentmods.dev/skills/hristo2612/jinn/self-heal"><img src="https://agentmods.dev/badge/skills/hristo2612/jinn/self-heal/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/hristo2612/jinn/self-heal"><img src="https://agentmods.dev/badge/skills/hristo2612/jinn/self-heal.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 Rogue Agent · line 81 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00019 | $0.01045 |
| Opus 5 | $0.00010 | $0.00522 |
| Sonnet 5 | $0.00004 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
self-heal 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Heal Skill
Trigger
This skill activates when {{portalName}} is experiencing issues, errors, or unexpected behavior. It also activates when the user asks to diagnose problems, check system health, or fix something that is not working.
Diagnostic Steps
Work through these checks in order. Stop and fix issues as you find them.
1. Check Gateway Logs
Read ~/.jinn/logs/gateway.log and look for:
- Error messages or stack traces
- Repeated failures or crash loops
- Connection refused or timeout errors
- Out of memory warnings
- Unhandled promise rejections
Summarize any problems found to the user.
2. Validate Configuration
Read ~/.jinn/config.yaml and verify:
- The file is valid YAML (no syntax errors)
- The
gateway.portfield is a valid number (default7777) - Required sections are present:
gateway(withport) andengines(with adefaultand a config block for that engine) engines.defaultis one of:claude,codex,antigravity- The default engine has a model set under
engines.<name>.model(e.g.engines.claude.model) - No duplicate keys or malformed values
3. Verify Engine Availability
Check that the configured AI engine is installed and accessible:
- For Claude: run
claude --versionand confirm it returns a version number - For Codex: run
codex --versionand confirm it returns a version number - For Antigravity (Gemini models): confirm the configured
engines.antigravity.binis on the PATH
If the engine command is not found, inform the user that the engine is not installed or not on their PATH.
4. Check Session Database
Look at the session registry for stuck sessions:
- Read the session registry at
~/.jinn/sessions/registry.db(SQLite) - Look for sessions with status
runningthat have not been updated recently (more than 30 minutes old) - These may be stuck and need to be reset
5. Check Disk and Temp Files
- Check if
~/.jinn/tmp/contains stale files that should be cleaned up - Large or numerous temp files can cause issues
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 · 117 lines · 19 tokens per session scan A a0105bcc5ad9
self-heal is a skill published in the GitHub repository hristo2612/jinn (315 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 1,045 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.