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 Handigraphs/handigraphs-stats-api-mcp --skill research-handigraphs-filtersgit clone --depth 1 https://github.com/Handigraphs/handigraphs-stats-api-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/handigraphs/handigraphs-stats-api-mcp/research-handigraphs-filters)<a href="https://agentmods.dev/skills/handigraphs/handigraphs-stats-api-mcp/research-handigraphs-filters"><img src="https://agentmods.dev/badge/skills/handigraphs/handigraphs-stats-api-mcp/research-handigraphs-filters/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/handigraphs/handigraphs-stats-api-mcp/research-handigraphs-filters"><img src="https://agentmods.dev/badge/skills/handigraphs/handigraphs-stats-api-mcp/research-handigraphs-filters.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 | $0.00064 | $0.01871 |
| Opus 5.5 | $0.00026 | $0.00748 |
| Sonnet 5.5 | $0.00013 | $0.00374 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
research-handigraphs-filters 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Handigraphs filters
Connection
This plugin connects to the hosted Handigraphs MCP server at
https://mcp.handigraphs.com/mcp, available to eligible Handigraphs All Access members.
Use only this plugin's handigraphs-stats-hosted connection;
never silently switch connections, identities or local credentials following
an OAuth failure.
Sign in through the client's browser OAuth flow as the intended Handigraphs account. Never ask for, accept or repeat an API key, website JWT, access/refresh token or service secret in chat, tool arguments, headers or configuration. No local key setup helpers are included. The client discovers public registration and authorization metadata; do not ask users to register a confidential client.
stats:read is required; filters:write and research:run are independent opt-in
consent choices. A connection grants only approved scopes and current eligibility,
Terms, rollout and worker policy still apply. For 401 or revoked/expired consent,
use the client's reconnect/login flow. For missing scopes, explain the denial;
the owner can revoke the app at /account/api and reconnect with explicit consent.
Never approve broader scopes automatically. A lapsed account can still inspect
and revoke connections. Do not fall back to an API key or another account to
bypass policy, quotas, errors or an unavailable worker. Switching to local is a
separate user choice; the existing local installation and keys remain supported.
Shared business workflow
Use the Handigraphs MCP tools for native website filters and Angles research. The targets are MLB batters/starters and NHL skaters/goalies. Tools also work without this skill; the API remains authoritative for ownership, validity and limits.
Resolve the task and permission
- An explicit request to research and create/save authorizes a new filter and paired Angles idea once a supported candidate is selected. Research alone does not authorize saving. Get explicit user confirmation before replacing an existing filter or idea; read its current revision first. A permission, tool annotation, or model-written confirmation flag is not user confirmation.
- For “run my filter,” resolve the owned item with
list_saved_filtersandget_saved_filter, disambiguating duplicate names only when necessary. Preserve its exact rule and revision.run_filtermeans today's Eastern slate; a historical test usesstart_filter_research. Do not repeat research merely to rerun a saved filter. Saving/running never starts Performance tracking or bets.
What ships with it
1 file 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 · -3 lines f2a81e773325
- 9d ago Changed · +24 lines a76ed7367a7e
- 12d ago First seen · 119 lines · 64 tokens per session scan A 8dfafb418fda
research-handigraphs-filters is a skill published in the GitHub repository Handigraphs/handigraphs-stats-api-mcp (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,871 once invoked, about $0.0003 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 2026-10-18.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
dcc-blender-assembly-pitfalls
Read this BEFORE writing any Blender geometry code through MCP, whenever you are about to (1) create or size mesh primitives - bpy.ops.mesh.primitivecubeadd, primitivecylinderadd, primitiveuvsphereadd, primitiveconeadd - or set scale / dimensions on a part; (2) orient a part with rotationeuler or rotationquaternion…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
color-theory
Use when constructing a reusable palette for a visual system: choose a harmony, assign semantic roles and light/dark token values, account for brand and cultural meaning plus color-vision deficiency, and ensure interaction states never rely on hue alone. Not for measuring an existing interface against an accessibility…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
quantum-algorithms
A routing workflow for choosing an open-source quantum-computing algorithm and loading the matching local workflow. Quantum computing uses circuits and quantum states to represent and process information.