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 agentmods add skills/handigraphs/handigraphs-stats-api-mcp/setup-handigraphs-stats-apinpx skills add Handigraphs/handigraphs-stats-api-mcp --skill setup-handigraphs-stats-apigit 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/setup-handigraphs-stats-api)<a href="https://agentmods.dev/skills/handigraphs/handigraphs-stats-api-mcp/setup-handigraphs-stats-api"><img src="https://agentmods.dev/badge/skills/handigraphs/handigraphs-stats-api-mcp/setup-handigraphs-stats-api.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.01036 |
| Opus 5 | $0.00044 | $0.00518 |
| Sonnet 5 | $0.00018 | $0.00207 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
setup-handigraphs-stats-api 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up Handigraphs Stats API
Configure the local plugin without exposing the reveal-once key to the model or conversation.
Security rules
- Never ask the user to paste, type, upload, or repeat the API key in chat.
- Never pass the API key as a shell command argument, tool argument, environment dump, log message, or test fixture.
- Never read or print the current value. Credential checks may return only whether a value is present.
- Direct the user to create or rotate a key at
https://www.handigraphs.com/account/apiwhen they do not already have a copied reveal-once key.
Windows agent-assisted setup
- Resolve the absolute path to the bundled
../../scripts/configure-windows.ps1helper relative to this skill. - Launch that helper through the local shell tool's approval or out-of-sandbox execution path on the first attempt. When the shell tool exposes
sandbox_permissions, set it torequire_escalatedand explain that approval is needed only to open the local masked window on the user's visible desktop. - In that approved call, start a visible Windows PowerShell process with
-NoLogo,-NoProfile,-NonInteractive,-STA,-ExecutionPolicy Bypass,-File <absolute-helper-path>, and a normal window style. Never put the API key in the command, its environment, or any tool argument. - Do not first try the standard Windows sandbox. Codex normally isolates sandboxed commands on a private desktop, so
Start-Processcan report a live process with the expected window title even though the user cannot see it. A sandboxed process or title is not proof that the setup window is visible. - After the approved launch, confirm only that the exact returned helper process remains open and has the
Handigraphs Stats API setupwindow title. Do not inspect its controls, automate the paste, read the saved environment value, or claim that the credential was saved. - Tell the user to finish the steps in the setup window and fully quit and reopen Codex. The already-running MCP process cannot reload a credential saved after it started.
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.
- 5d ago First seen · 47 lines · 89 tokens per session scan A a244cb7ee29d
setup-handigraphs-stats-api is a skill published in the GitHub repository Handigraphs/handigraphs-stats-api-mcp (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,036 once invoked, about $0.0004 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
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
maya-shot-export
Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).
social-scrape
Collect public posts and discussion from X, LinkedIn and Hacker News through a local signed-out browser, then report them in chat or write them to a document. Use when the user wants to scrape, monitor or research specific accounts, topics, hashtags or discussions on social platforms.
knowledge
Unified cross-store knowledge query. Searches MEMORY.md, Thoughtbox knowledge graph, git history, and assumption registry in parallel, returning results with provenance.