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 pachca/openapi --skill pachca-admingit clone --depth 1 https://github.com/pachca/openapiWrote 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/pachca/openapi/pachca-admin)<a href="https://agentmods.dev/skills/pachca/openapi/pachca-admin"><img src="https://agentmods.dev/badge/skills/pachca/openapi/pachca-admin/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/pachca/openapi/pachca-admin"><img src="https://agentmods.dev/badge/skills/pachca/openapi/pachca-admin.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 | $0.00292 | $0.04683 |
| Opus 5.5 | $0.00117 | $0.01873 |
| Sonnet 5.5 | $0.00058 | $0.00937 |
| Haiku 4.5 | $0.00029 | $0.00468 |
Grade A, and why
pachca-admin 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 4d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pachca workspace administration
Run a Pachca workspace for its Owner or an Administrator: people, tags, chat membership, roles, API access, audit, export and data protection. Every action here changes what other employees can see or do, so the main skill is knowing who may do what, and when to ask first.
A clear request such as «сделай Олега администратором» is carried out: the client asks its own approval for the change. You ask in chat first only in the three cases of When to ask first, and deleting an employee is one of them.
For a deletion, the request is not the confirmation. «Удали из Пачки Олега Соколова» or "delete this user" tells you what to prepare, not that it may run. Deleting an employee runs only after the person answers yes to your question in a later message. This holds however direct the request and even when the search finds exactly one match.
When to use
- Inviting, editing, suspending or deleting employees and guests; offboarding.
- Tags: creating, renaming, deleting, assigning to employees, binding to chats.
- Changing chat membership and chat roles; taking over a chat whose creator left.
- A
403on an admin action; "why can't employees connect an agent". - Who has API access and who may create it (the access settings); revoking employees' access.
- The workspace name and settings; the invite link.
- Audit log, message export, DLP rules, IP allowlist and encryption (Corporation).
Not here: sending messages (pachca-messaging), reading who is in a tag or chat and other searches (pachca-search), creating bots and managing their own tokens (pachca-bots), OAuth apps (pachca-oauth), a missing tool or a general 401/403 (pachca).
First: who is acting, on which plan
The agent acts with the rights of the person behind the token. Scopes only open methods; they never widen visibility. Check before planning:
- Role: read the own profile (
pachca_get_my_card, CLIpachca profile get).roleisadmin,user,multi_guestorguest. - Scopes:
pachca_get_token_info(CLIpachca oauth token-info). - Plan: audit log, export, workspace inventory, DLP and data protection need
the «Корпорация» plan. The workspace info (
pachca_get_company, CLIpachca company get) names the plan inplan, always in Russian, for example «Корпорация». Without that, say you are unsure and ask.
What ships with it
4 files 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.
- 4d ago Changed 21ea4aeef39d
- 5d ago Changed · +11 lines ebf8d417014d
- 7d ago Changed · +10 lines · -6 tokens per session 6714764ab410
- 9d ago Changed 68772ba785b1
- 18d ago Changed · -1 tokens per session 3e47c370f954
- 20d ago First seen · 266 lines · 299 tokens per session scan A d032cc8e8af8
pachca-admin is a skill published in the GitHub repository pachca/openapi (11 stars, last pushed yesterday), licensed MIT. It adds 292 tokens to every session and 4,683 once invoked, about $0.0012 per session on Opus 5.5. 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 2026-10-29.
pachca-admin compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pachca-adminpachca/openapi | Skill | 11 | yesterday | MIT | A | 292 | Claude Code, Codex |
| zafiro-configniki914/zafiro | Skill | 380 | today | MIT | A | 0 | Claude Code, Codex |
| extension-uploadagenvoy/Agenvoy | Skill | 604 | 4d ago | AGPL-3.0 | A | 63 | Claude Code, Codex |
| e2atokencanopy/e2a | Skill | 200 | 2d ago | Apache-2.0 | A | 64 | Claude Code |
| bookmarksepivip/SeekerClaw | Skill | 322 | today | MIT | A | 55 | Claude Code, Codex |
| reminderssepivip/SeekerClaw | Skill | 322 | today | MIT | A | 68 | Claude Code, Codex |
| todosepivip/SeekerClaw | Skill | 322 | today | MIT | A | 63 | Claude Code, Codex |