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 Cloudgeni-ai/opengeni --skill skill-managementgit clone --depth 1 https://github.com/Cloudgeni-ai/opengeniWrote 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/cloudgeni-ai/opengeni/skill-management)<a href="https://agentmods.dev/skills/cloudgeni-ai/opengeni/skill-management"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/skill-management/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/cloudgeni-ai/opengeni/skill-management"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/skill-management.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 | $0.00031 | $0.01567 |
| Opus 5.5 | $0.00012 | $0.00627 |
| Sonnet 5.5 | $0.00006 | $0.00313 |
| Haiku 4.5 | $0.00003 | $0.00157 |
Grade A, and why
skill-management 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Skills
A Skill is a folder containing SKILL.md and supporting UTF-8 text files.
Use Skills for reusable procedures and context-specific or personal behavioral
preferences. Use workspace instructions for short always-on rules within their
authorized scope. A request to remember how to behave belongs in one of those
destinations, not Knowledge, even when phrased as "the user prefers concise replies."
Knowledge holds facts and outcomes for retrieval, not standing behavior.
Make the Skill description state when it applies: only that descriptor enters
the prompt index; the agent reads the full instructions with skill_read when
relevant. Do not promise that the full Skill body is always in the prompt.
For mixed requests, keep the short rule in workspace instructions and the detailed
procedure in a Skill. Do not duplicate either as a Knowledge entry.
Read
skill_read works without a sandbox. Omit paths to read SKILL.md; specify
relative paths to read exactly those files. Include SKILL.md explicitly only
when you want it alongside other files. An empty paths list is not a default.
Read supporting files only when needed. Reads return current saved content;
you do not need to pin a version to follow a Skill.
To discover supporting files, call skill_read with listFiles: true and no
paths. This returns only relative paths (at most 1,024) and available revision
identity, never file bodies. Then request only the paths you need. Inventory
cannot be combined with paths and does not require sandbox checkout.
Find and install
Management tools are lazy: discover the relevant tool with tool search before
calling it. Use skill_search to find installed or available Skills and
skill_install to install a chosen source. Installation resolves source bytes
on the server; do not invent a source hash. Search does not install anything.
Installed guidance never grants credentials, tools, or additional permissions.
Keep the same operationId and original arguments when retrying an uncertain
install. A committed install replays before fetching the source again. Updates
must supply the reviewed installation version; do not substitute a newer value
merely to get past a conflict.
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 · 133 lines · 31 tokens per session scan A 2aa83b6a5685
skill-management is a skill published in the GitHub repository Cloudgeni-ai/opengeni (205 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 1,567 once invoked, about $0.0001 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 2026-10-21.
Other skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
effect-v4
Write, review, or upgrade Effect v4 code in the Composio CLI, cli-keyring, and json-schema-to-effect-schema packages, all pinned exactly to [email protected] — Context.Service and explicit layers, Schema.TaggedError and typed recovery, the effect/cli command surface, and the vendored effect source oracle. Use when writing…
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-java-gen
Use when writing Java code with dev.axllm:ax for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-go-flow
Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.