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-searchgit 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-search)<a href="https://agentmods.dev/skills/pachca/openapi/pachca-search"><img src="https://agentmods.dev/badge/skills/pachca/openapi/pachca-search/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-search"><img src="https://agentmods.dev/badge/skills/pachca/openapi/pachca-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 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 MCP Rug Pull · line 22 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 24 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 29 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 31 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 39 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 45 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00313 | $0.04587 |
| Opus 5.5 | $0.00125 | $0.01835 |
| Sonnet 5.5 | $0.00063 | $0.00917 |
| Haiku 4.5 | $0.00031 | $0.00459 |
Grade A, and why
pachca-search 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 5d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pachca: finding and summarizing
Pachca has search for messages, chats and employees, plus plain feeds for chats, threads and reminders. Each one covers a different slice of the workspace. Most wrong answers come from using the wrong one, reading only the first page, or taking the wrong id of a thread.
When to use
- Find where something was discussed, who said it, where someone was mentioned, a chat by name, an employee by name, title or department.
- Retell a thread or a chat, or build a digest of channels and threads for a period. Explain the problem a thread reports, or list the remarks made in a thread and check each against the code.
- Pull decisions, open questions and action items out of a discussion, and create reminders from them. Set a reminder for yourself or a colleague. List someone's reminders.
- "Remind me tomorrow at 9:00": a reminder with that
due_at. Pachca notifies its assignees at that time. - Find who is in a group of employees (a tag) or in a chat.
- List the messages in your «Важное». Marking a message is pachca-messaging.
Not here: posting the result or replying, pinning, reacting to or editing a message (finding it on the way included), and messages sent later at a set time (pachca-messaging), watching a thread and replying as new messages come (pachca-watch-thread), changing tags, employees or chat members (pachca-admin), a bot that lives in threads (pachca-ai-agent), token, scopes and 429 handling in code (pachca-api).
You see what the token owner sees
Every search and feed answers as the token owner. An employee's token sees
that employee's chats. A bot token works the same way: it finds and lists
public conversations and channels (pachca_search_chats,
pachca_list_chats with availability=public) and reads their feeds
without joining, while message search and pachca_list_threads cover only
the chats and threads the bot was added to. A multi-guest sees only the
chats they were added to: no public chat they have not joined, not even
its feed.
What ships with it
3 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.
- 5d ago Changed · +2 lines 315c3aaa41bf
- 9d ago Changed · +13 lines a356347c711d
- 13d ago Changed 45ca97f38d1f
- 15d ago Changed · +4 lines · +8 tokens per session b98efb16b9c2
- 18d ago Changed · +18 tokens per session 6e386e57b921
- 20d ago Changed · +159 lines · +117 tokens per session 26fdbaec1f85
- 1mo ago Changed 8b61badcceff
- 2mo ago First seen · 97 lines · 170 tokens per session scan A 80358daa33cf
pachca-search is a skill published in the GitHub repository pachca/openapi (11 stars, last pushed yesterday), licensed MIT. It adds 313 tokens to every session and 4,587 once invoked, about $0.0013 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 2026-08-31.
pachca-search compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pachca-searchpachca/openapi | Skill | 11 | yesterday | MIT | A | 313 | 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 |