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 agentmods add commands/shuxueshuxue/spexcode/specgit clone --depth 1 https://github.com/shuxueshuxue/SpexcodeWhat 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 | $0.00000 | $0.00394 |
| Opus 5 | $0.00000 | $0.00197 |
| Sonnet 5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
spec 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 2d 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.
What it actually says
commands
The invocable command plugins live here: leaf plugins whose body is a prompt preset a human can pick
from the / dropdown while launching or driving a session, each carrying surface: command. Grouping them keeps .plugins/ legible at
a glance — the command presets on this shelf, the skill plugins on [[skills]], the auxiliary system
contracts on [[prompts]], with [[core]] (the dev-flow contract subsystem) a flat child beside them.
Invocation belongs to the backend prompt boundary, not to whichever client happens to render the picker.
Every compose surface sends the raw /<preset> [[node]]… <free text> prompt; the shared resolver expands the
live surface: command body before either [[launch]] starts a worker or [[dispatch]] sends text to one. At
launch, the raw invocation remains the session's originating prompt and identity source, so links inside a
plugin body can never invent a node target. Dashboard and phone menus are therefore discovery/insertion
chrome, while dashboard, phone, CLI, API, and in-process fallback all invoke through the same backend
resolution. A preset with {{targets}} always receives the resolved target block; one without that placeholder
gets a target block only when the invocation actually names a target, so a targetless utility remains a small
prompt. An unknown leading /name stays ordinary prompt text and is never swallowed or guessed.
This node is a shelf, not a surface. Its routing and relocation invariant is owned once by [[.plugins]]'s shelf invariant; this node only describes command-specific discovery and invocation.
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.
- 2d ago First seen · 26 lines · 0 tokens per session scan A 3202789658ac
spec is a command published in the GitHub repository shuxueshuxue/Spexcode (180 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 394 tokens. 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 commands, from other repositories
claude-flow-swarm
Coordinate multi-agent swarms for complex tasks.
bootstrap
PACT session-start ritual — identify the session team (platform-provisioned), secretary spawn, paused-state surface, bootstrap marker.
ox-session-review
Command "ox-session-review" from sageox/ox, covering failure-mode watch-list (read first), from the ledger root. should print 0, phase 1 — scan & score (read-only), quality buckets (first match wins) and removal candidates.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
handoff
Package current state for the next agent.
xdo
Direct development by the Main Agent.