Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wrg32786/aigent-osnpx agentmods add skills/wrg32786/aigent-os/system-checkWrote 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/wrg32786/aigent-os/system-check)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/system-check"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/system-check/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/wrg32786/aigent-os/system-check"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/system-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00702 |
| Opus 5 | $0.00015 | $0.00351 |
| Sonnet 5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
system-check 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/system-check
Run from the aigent-OS root:
bash daemons/system-check.sh
The script is read-only. It prints one line per check, a final
SUMMARY: N PASS / N FAIL / N INFO, and exits 1 when any check fails.
Path resolution
Framework code resolves from AIGENT_ROOT, defaulting to the parent directory
of daemons/system-check.sh.
Operational memory resolves in this order:
AIGENT_STATE_HOME_DIR/vault/memorywhen the state-home diversion is set.AIGENT_STATE_HOME_DIR/memoryas a compatibility fallback.AIGENT_ROOT/vault/memoryfor a normal installation.AIGENT_ROOT/memoryonly when the canonical vault path does not exist.
This is the same shape used by the nightly controller. Tests should set
AIGENT_ROOT, AIGENT_STATE_HOME_DIR, and date-sensitive environment values
explicitly so ambient state cannot change the result.
Checks
- Required top-level skills exist, including the nightly close-parity skills.
- Shell and Python daemons parse.
- Every nightly daemon exists and passes
node --check. - The memory-heat daemon parses.
- Operational state files have their required schemas, including the generic sweep log and dispatch-fitness table.
- Capsules have valid frontmatter, identity, and status.
- Canonical cognitive JSON and JSONL inputs exist and parse. Missing canonical input is a failure, not an empty-success case.
DREAM_LOG.mdfreshness comes from its newest valid dated header, never its file modification time.- The newest
NIGHTLY_LOG.mdpass is current and has complete terminal evidence. A terminalstatus: FAILremains red even when every checkpoint row is present. /nightlyresolves through the unique/nightly-close-parityroute.- The eval directory contains at least one supported file.
- The local daemon error log is surfaced as INFO when it contains entries.
Date configuration
All date-sensitive checks use one timezone and one cutoff:
export AIGENT_NIGHTLY_TIME_ZONE="America/Los_Angeles"
export AIGENT_NIGHTLY_CUTOFF_HOUR="4"
bash daemons/system-check.sh
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.
- 9d ago First seen · 86 lines · 31 tokens per session scan A d1fee35455c6
system-check is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 702 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 2026-09-03.
Other skills, from other repositories
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.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
hive.error-recovery
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
skill-repair
Diagnose and fix failing or degraded skills automatically - systemic-first triage, per-category playbooks, and a verification plan.
self-improve
Improve the agent itself, or audit its recent performance - better skills, prompts, workflows, and config, plus a quality/reliability/memory-hygiene review of what it did and what failed.
systematic-debugging
Systematic approach to diagnosing and fixing errors.