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 nexus-substrate/nexus-agents --skill system-reviewgit clone --depth 1 https://github.com/nexus-substrate/nexus-agentsWrote 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/nexus-substrate/nexus-agents/system-review)<a href="https://agentmods.dev/skills/nexus-substrate/nexus-agents/system-review"><img src="https://agentmods.dev/badge/skills/nexus-substrate/nexus-agents/system-review/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/nexus-substrate/nexus-agents/system-review"><img src="https://agentmods.dev/badge/skills/nexus-substrate/nexus-agents/system-review.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 Prompt Injection · line 63 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00048 | $0.00710 |
| Opus 5 | $0.00024 | $0.00355 |
| Sonnet 5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
system-review 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Review Skill
Trigger Conditions
Run when ANY occur:
- Open GitHub issues drop below 5
- An EPIC issue is closed (label:
epic) - 7 days since last review
- Manual request
Review Checklist
Phase 1: Registry Reconciliation
# Count techniques by status
grep -c "status: implemented" docs/research/registry/techniques.yaml
grep -c "status: planned" docs/research/registry/techniques.yaml
# Verify RESEARCH_INDEX.md matches actual counts
# Check integration_files exist for implemented techniques
Phase 2: Documentation Sync
- ARCHITECTURE.md reflects current phase status
- README.md lists current capabilities accurately
- CHANGELOG.md has entries for shipped features
- ALIGNMENT_ROADMAP.md phase status is current
Phase 3: Issue Health
gh issue list --state open --limit 50
- No orphaned issues (referenced but not in GitHub)
- No stale issues (no activity > 30 days without
wontfixlabel) - Labels are accurate and consistent
Phase 4: Generate Report
Create GitHub issue titled "System Review: YYYY-MM-DD" with findings and action items.
TZ='America/New_York' date '+%Y-%m-%d'
gh issue create --title "System Review: $(TZ='America/New_York' date '+%Y-%m-%d')" \
--label "maintenance" --body "## Findings\n\n[report here]"
Anti-rationalization — System review
| Excuse | Counter |
|---|---|
| "Skip the review, I just looked at this last week" | A week is enough for new alerts, dep advisories, and CI flakes. Run all phases. |
| "No new issues, the review is wasted time" | The review's value isn't in finding new issues — it's in confirming the system isn't drifting silently. Empty reviews are good signal. |
| "I'll skip Phase X, it's never useful" | If a phase is never useful, file an issue to remove it. Don't silently skip — the next reviewer will skip a different phase. |
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 · 83 lines · 48 tokens per session scan A d3953a59d426
system-review is a skill published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 710 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.