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 peterthiemann/agda-mcp --skill agda-proofgit clone --depth 1 https://github.com/peterthiemann/agda-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/peterthiemann/agda-mcp/agda-proof)<a href="https://agentmods.dev/skills/peterthiemann/agda-mcp/agda-proof"><img src="https://agentmods.dev/badge/skills/peterthiemann/agda-mcp/agda-proof/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/peterthiemann/agda-mcp/agda-proof"><img src="https://agentmods.dev/badge/skills/peterthiemann/agda-mcp/agda-proof.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 | $0.00072 | $0.01273 |
| Opus 5.5 | $0.00029 | $0.00509 |
| Sonnet 5.5 | $0.00014 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
agda-proof 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 yesterday.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agda proof development
Use the connected agda-mcp tools for semantic operations. Tool prefixes depend on the client; names below are the server's tool names. This skill requires an agda-mcp connection and a separately installed Agda; if unavailable, report that prerequisite rather than inventing results.
load: establish state
Call agda_server_info first to inspect compatibility, workspace selection, and transformation policy. Agda 2.8.0 is verified; other versions are unverified, not automatically unusable.
Save intended source changes before loading: this server reads disk, not editor buffers. Call agda_load_module with an absolute modulePath (.agda, .lagda, or .lagda.md). In request workspace mode also supply an absolute containing workspaceRoot; otherwise use a configured root. A workspace handle is an opaque returned value, never a directory name.
For proof work prefer includeContexts:true. For a compile-only question use diagnosticsOnly:true; do not combine these flags. Inspect structuredContent, including warnings and diagnostics; text content is only a summary. A completed request does not establish success: check data.checked.
inspect: choose the semantic query
Reuse goals and contexts already returned by load/typecheck. Use agda_retrieve_context for one goal, agda_retrieve_contexts for several (nonempty list; default batch maximum 32). Inspect each batch entry's ok and error; aggregate success does not guarantee every context succeeded.
Use agda_retrieve_goals for current visible holes, agda_retrieve_constraints for blocked equalities, and agda_query_metavariables for visible and backend-published invisible metas. Invisible metas may lack handles and are not automatically editable goals.
Use agda_infer_type for types and agda_normalize_expression for reduction, with a nonempty expression and exactly one selector: goal for local bindings or workspace for top-level scope. Do not approximate these operations with text search. Read the tool contract for modes, output fields, and job controls.
What ships with it
2 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.
- yesterday First seen · 46 lines · 72 tokens per session scan A edadf4cc7f34
agda-proof is a skill published in the GitHub repository peterthiemann/agda-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 1,273 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 2026-10-19.
Other skills, from other repositories
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
dsm5
Assess and explain questions about mental health and neurocognitive conditions against DSM-5-TR diagnostic criteria, and guide evidence-based conversations for clinicians, patients, and family members. Use when someone asks about symptoms, possible conditions, differential diagnoses, diagnostic criteria, prevalence…
biological-expert
Expert-level biology, biotechnology, genetics, bioinformatics, and computational biology. Use when the user mentions biology, biotechnology, genetics, bioinformatics, or genomics, or when the task involves Molecular Biology, Genomics & Bioinformatics, Systems Biology, or Data Analysis.
quantum-expert
Expert-level quantum computing, Qiskit, quantum algorithms, and quantum information. Use when the user mentions quantum computing, Qiskit, quantum algorithms, or quantum information, or when the task involves Quantum Mechanics Basics, Quantum Hardware, Circuit Design, or Algorithm Implementation.
math-modeling-growth
A skill that turns the results and decisions from a real mathematical modelling project into a plain-language learning or review report. Mathematical modelling uses mathematical methods to represent and study a real situation.
matematicas
Resolución de Matemáticas Para problemas matemáticos complejos (ecuaciones, cálculos avanzados, álgebra, geometría, cálculo, etc.).