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 corezoid/corezoid-ai-plugin --skill corezoid-accessgit clone --depth 1 https://github.com/corezoid/corezoid-ai-pluginWrote 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/corezoid/corezoid-ai-plugin/corezoid-access)<a href="https://agentmods.dev/skills/corezoid/corezoid-ai-plugin/corezoid-access"><img src="https://agentmods.dev/badge/skills/corezoid/corezoid-ai-plugin/corezoid-access.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 104 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.
- medium Privilege Escalation · line 156 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00141 | $0.02416 |
| Opus 5 | $0.00071 | $0.01208 |
| Sonnet 5 | $0.00028 | $0.00483 |
| Haiku 4.5 | $0.00014 | $0.00242 |
Grade A, and why
corezoid-access scanned grade A with 1 finding 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 7d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# (chmod 600 JSON: title, description, obj_id, login, secret, created_at) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Corezoid Access Control
You are the specialist for sharing Corezoid objects and managing principals
(users, groups, API keys) inside a workspace. You drive the share-object,
create-group, create-api-key, find-principal, invite-user and
related MCP tools.
Mental model
Everything you share — a single process, a folder, a whole stage, or an
entire project — uses the same API operation: a link op against the
Corezoid /api/2/json endpoint with a privs payload. The MCP tools below
are thin wrappers around that one operation.
Workspace (company)
├── Projects ─────────► share-object obj=project
│ └── Stages ───────► share-object obj=stage
│ └── Folders ──► share-object obj=folder
│ └── Processes (conv) ► share-object obj=conv
│
├── Users ── obj_to=user (real human accounts)
├── API keys ── obj_to=user (API keys are users with logins.type=api)
└── Groups ── obj_to=group (bundles of users + api keys)
Key consequence: when you share to an API key, pass obj_to=user
with the key's obj_id — not obj_to=api_key. The link API does not
accept api_key as a recipient kind; the data model treats API keys as
user records.
Privilege model
Four privileges, applied independently:
| Priv | What it lets the principal do | UI label |
|---|---|---|
view |
Read process/folder content and run-time data | View |
create |
Create new tasks in a process or new objects in a folder | Task management |
modify |
Edit the process / folder / stage definition | Modify |
delete |
Delete objects | Delete |
In tools the privs argument accepts a comma-separated list ("view,modify"),
a JSON array ('["view","create"]'), or one of the keywords "all" /
"none". Default when omitted is "all". Pass "none" (or the equivalent
literal "[]") to revoke — under the hood Corezoid uses the same link
op for grant and revoke, distinguished only by whether the privs array is
populated, so there is no separate "unshare" tool.
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.
- 7d ago First seen · 246 lines · 141 tokens per session scan A 313532df988b
corezoid-access is a skill published in the GitHub repository corezoid/corezoid-ai-plugin (73 stars, last pushed 3d ago), licensed MIT. It adds 141 tokens to every session and 2,416 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
stop-that-shit
Keep coding agents focused on requested and necessary work. Use when a request sets a read-only, answer-only, file, action, or stopping boundary; when evidence shows scope creep, speculative hardening, unnecessary hashing or dependencies, repeated audit loops, or valueless delegation; or when the user invokes Stop…
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.
superloopy-clone
Use when the user asks for Superloopy clone or asks to clone, rebuild, reverse-engineer, replicate, or copy a website or page into a Superloopy-governed implementation. Triggers on "loopy clone", target URLs plus requests such as "clone this site", "rebuild this page", "make a copy of this website", "pixel-perfect…
superloopy-loop
Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-backed completion.
superloopy-doctor
Use when diagnosing Superloopy doctor, install, wrapper, plugin cache, hook bootstrap, bundled agents, marketplace, Codex, Claude Code, stale-version, evidence-floor, or host-wiring health problems.
inspect-codex-trajectory
Inspect or show a local Codex task trajectory, including turns, approximate model steps, assistant messages, reasoning summaries, tool calls, failures, compaction, token usage, and timing. Use when the user asks for a trajectory, execution trace, task timeline, slow-tool analysis, visual event ledger, or live…