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 agntcy/dir-mcp --skill search-agentsgit clone --depth 1 https://github.com/agntcy/dir-mcpWrote 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/agntcy/dir-mcp/search-agents)<a href="https://agentmods.dev/skills/agntcy/dir-mcp/search-agents"><img src="https://agentmods.dev/badge/skills/agntcy/dir-mcp/search-agents/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/agntcy/dir-mcp/search-agents"><img src="https://agentmods.dev/badge/skills/agntcy/dir-mcp/search-agents.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 | $0.00035 | $0.01328 |
| Opus 5 | $0.00017 | $0.00664 |
| Sonnet 5 | $0.00007 | $0.00266 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
search-agents 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search and Discover Agents
Use this skill to find AI agents and MCP servers in the AGNTCY Agent Directory, inspect their records, and verify their authenticity.
Search the Directory
Use agntcy_dir_search_local to find agents. All parameters are optional and combinable:
By capability (skill):
Call agntcy_dir_search_local with skill_names=["*python*", "*data-analysis*"]
By name pattern:
Call agntcy_dir_search_local with names=["my-agent*"], versions=["v1.*"]
By domain:
Call agntcy_dir_search_local with domain_names=["*finance*"]
By locator type (e.g. Docker images only):
Call agntcy_dir_search_local with locators=["docker-image:*"]
Paginated:
Call agntcy_dir_search_local with limit=20, offset=40
Wildcard patterns: * matches any sequence, ? matches one character, [abc] matches a set.
Multiple filters within a call are combined with OR logic.
The search returns record_cids — content identifiers you can use to fetch the full record.
Fetch a Record
agntcy_dir_pull_record returns the entire record inline. Populated records routinely exceed 50KB — well past the tool-result token limit — get truncated to a saved file, and burn a large chunk of context reading that file back in even when only a few fields are needed. Only use agntcy_dir_pull_record directly for a quick check when you expect a small record (e.g. one you just created and know is minimal). For anything else — browsing search results, inspecting third-party records, or pulling more than one — pull with the bundled dirctl binary and filter with jq before any of it reaches the model.
1. Invoke dirctl through the dir-mcp npm package — never system-wide
Never run a bare dirctl or search PATH/the filesystem for it. Use the @agntcy/dir-mcp npm package's own bundled binary — the same package .mcp.json already runs via npx -y @agntcy/dir-mcp — via its second bin entry:
npx -y --package=@agntcy/dir-mcp dirctl <subcommand and flags>
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 · +25 lines · +7 tokens per session 9aa9cce7c123
- 8d ago First seen · 85 lines · 28 tokens per session scan A 7c2efc0e916a
search-agents is a skill published in the GitHub repository agntcy/dir-mcp (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 1,328 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…