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 zephexMCP/agent-skills --skill zephexgit clone --depth 1 https://github.com/zephexMCP/agent-skillsWrote 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/zephexmcp/agent-skills/zephex)<a href="https://agentmods.dev/skills/zephexmcp/agent-skills/zephex"><img src="https://agentmods.dev/badge/skills/zephexmcp/agent-skills/zephex/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/zephexmcp/agent-skills/zephex"><img src="https://agentmods.dev/badge/skills/zephexmcp/agent-skills/zephex.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 | $0.00221 | $0.03174 |
| Opus 5 | $0.00111 | $0.01587 |
| Sonnet 5 | $0.00044 | $0.00635 |
| Haiku 4.5 | $0.00022 | $0.00317 |
Grade B, and why
zephex scanned grade B with 2 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
CLI (optional): curl -fsSL https://zephex.dev/cli/install.sh | bash Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
CLI (optional): curl -fsSL https://zephex.dev/cli/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zephex — MCP + CLI for the user's project
Zephex analyzes the user's own repo — not training data. Same ten tools, same credits:
| Surface | How |
|---|---|
| Editor MCP | Call the tool by name with path |
| Terminal CLI | cd their project → zephex <command> |
| Web terminal | Same command words, in the browser |
zephex:find_code = find_code = zephex find. If they asked you to use Zephex, you MUST call at least one Zephex tool (or one zephex command) before answering about their code. Max 3 identical calls per turn without new evidence.
Removed — never call: scope_task, inspect_url, audit_package, bare thinking.
path: absolute dir, or github:owner/repo / GitHub URL. Monorepo: the app package (or --cwd).
inline_files: { "src/a.ts": "<full file body>" } only when there is no disk.
Workflow
Pick one row. MCP when connected; CLI when they are in a shell.
| They need | MCP | CLI |
|---|---|---|
| What is this app? | get_project_context topic identity then run |
zephex overview |
| Full orientation / where to start a task | context + find + architecture | zephex deep --json or deep "the task" |
| Folder map only | — | zephex structure (0 credits) |
| How auth/API wires | explain_architecture |
zephex architecture --focus auth |
| Find code | find_code |
zephex find "…" |
| Read a known file/symbol | read_code |
zephex read <path> |
| Before install | check_package (task check then upgrade/security/migrate) |
zephex safe <pkg> |
| After edits | check_test task run, then failures on session_id |
zephex test then check test failures |
| Live URL they pasted | audit_headers |
zephex check url https://… |
| Remember / recall | project_memory |
zephex remember / recall |
| Stuck after 2+ fails | keep_thinking |
zephex think "…" |
| Generic playbook (not their repo) | Zephex_dev_info |
zephex docs "…" |
MUST check_package / safe before recommending install. MUST check_test / test after substantive edits when they care about tests.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 291 lines · 221 tokens per session scan B b7e785d5a5a3
zephex is a skill published in the GitHub repository zephexMCP/agent-skills (5 stars, last pushed 27d ago), licensed MIT. It adds 221 tokens to every session and 3,174 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
axiom-sre
Expert SRE investigator for incidents and debugging. Uses hypothesis-driven methodology and systematic triage. Can query Axiom observability when available. Use for incident response, root cause analysis, production debugging, or log investigation.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
convex-insights
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.
convex-self-heal
Production error → triaged, root-caused, repaired, and certified (tsc + rehearsal + reproduce-then-gone) fix PR for a human to merge — then confirm the error stops recurring. Never auto-merges.
convex-sentinel
Set up Sentinel production error capture in your own Convex deployment.