Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/datathings/marketplacenpx agentmods add skills/datathings/marketplace/greycatWrote 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/datathings/marketplace/greycat)<a href="https://agentmods.dev/skills/datathings/marketplace/greycat"><img src="https://agentmods.dev/badge/skills/datathings/marketplace/greycat/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/datathings/marketplace/greycat"><img src="https://agentmods.dev/badge/skills/datathings/marketplace/greycat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Privilege Escalation · line 80 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Prompt Injection · line 223 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 225 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00105 | $0.06617 |
| Opus 5 | $0.00053 | $0.03308 |
| Sonnet 5 | $0.00021 | $0.01323 |
| Haiku 4.5 | $0.00011 | $0.00662 |
Grade A, and why
greycat 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 8d 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 — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GreyCat
GreyCat is one language and one runtime in one binary. A project lives in a directory rooted at project.gcl. The greycat binary compiles it, runs it, serves it as an HTTP server, manages users, and stores its state in gcdata/. There is no separate database, queue, or web server.
.gcl source files are organized into projects with a single entrypoint named project.gcl, whose @library / @include pragmas (which must appear in that file only) form the closure of analyzed modules. Compiled and run by the greycat runtime; statically analyzed by greycat lint and formatted by greycat fmt.
Beyond the required std, GreyCat publishes optional domain libraries (Kafka, MQTT, OPC UA, SSH/FTP, PostgreSQL, LLM inference, linear algebra, full-text search, OpenStreetMap, and more). Before hand-rolling a domain integration, check the catalog in reference/libraries.md for one that already fits, then pull it in with an @library pragma and greycat install.
Anti-hallucination rule
GreyCat is not Java, Rust, Kotlin, Python, or TypeScript. It has its own conventions and a small grammar. Before writing GCL by analogy to another language, check reference/idioms.md — most "obvious" guesses are wrong (no new, no ternary, no switch, no import, private ≠ "hidden", -> ≠ ., etc.).
When uncertain about a construct: read lib/std/*.gcl for real examples, then run greycat run against a minimal project.gcl. The runtime is the oracle.
When to read which file
This file covers the 80% you need across language and tooling. Drill into a reference file when the task touches its area:
Language:
- reference/syntax.md — Complete grammar reference: every statement, every expression form, operator precedence, literals (string substitution, time
'…', typed-suffix numbers). - reference/types.md — Type system in depth: nullability, narrowing, generic invariance, casting, inheritance,
is/as. - reference/stdlib.md — Built-in types by category (collections, node types, time/duration/geo, IO, Url, S3, Crypto). Method signatures.
- reference/annotations.md — Every annotation (
@expose,@permission,@reserved,@volatile,@format,@test,@tag) and every modifier (private,static,abstract,native). Doc-comment tags like@param. - reference/idioms.md — Idiomatic patterns and common pitfalls (no ternary, no
void, no::new(),functionslot semantics,privatesemantics, generic invariance).
What ships with it
13 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.
- reference/annotations.md 14 KB
- reference/cli.md 24 KB
- reference/idioms.md 20 KB
- reference/lang.md 12 KB
- reference/libraries.md 5.8 KB
- reference/project.md 9.7 KB
- reference/runtime.md 20 KB
- reference/stdlib.md 23 KB
- reference/syntax.md 15 KB
- reference/types.md 13 KB
- reference/webapp-tests.md 6.4 KB
- reference/webapp.md 30 KB
- reference/workflow.md 13 KB
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.
- 8d ago First seen · 487 lines · 105 tokens per session scan A b2412411e923
greycat is a skill published in the GitHub repository datathings/marketplace (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 105 tokens to every session and 6,617 once invoked, about $0.0005 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 2026-08-30.
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…