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/nicolasmelo1/logion/with-references-and-scriptsnpx skills add nicolasmelo1/logion --skill with-references-and-scriptsgit clone --depth 1 https://github.com/nicolasmelo1/logionWrote 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/nicolasmelo1/logion/with-references-and-scripts)<a href="https://agentmods.dev/skills/nicolasmelo1/logion/with-references-and-scripts"><img src="https://agentmods.dev/badge/skills/nicolasmelo1/logion/with-references-and-scripts.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 | $0.00056 | $0.00646 |
| Opus 5 | $0.00028 | $0.00323 |
| Sonnet 5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
with-references-and-scripts 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 6d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logion Course With References And Scripts
This example shows the larger shape a real course usually takes: a short SKILL.md for activation, a references/ directory for detailed docs the agent loads on demand, and a scripts/ directory for code the agent runs.
What this course does
When an agent is asked to "say hello and record it," this skill:
- Runs
scripts/say-hello.shto print a greeting. - Writes a timestamped record to
./outputs/hello.loginside the course bundle.
That's it. It's a stand-in for a real skill that runs a tool and produces an artifact.
Structure
with-references-and-scripts/
├── SKILL.md
├── course/
│ └── capabilities.yaml
├── references/
│ └── usage.md # loaded only when the agent needs detail
└── scripts/
└── say-hello.sh # invoked via the terminal tool
When to use this template
Copy this directory when your real course:
- Has a meaningful body that takes ~50-200 lines to explain.
- Bundles one or two helper scripts (Python or shell).
- Needs to write files into a known subdirectory.
If your course also needs outbound HTTP or env vars, use the upcoming with-network-and-secrets/ example as a starting point (or extend this one).
How to invoke
The agent reads this file at activation. To perform the task:
bash scripts/say-hello.sh > outputs/hello.log 2>&1
For detailed parameters, see references/usage.md.
Capability declarations
This course declares:
tools: [file, terminal]— needs to write a file and run a subprocess.filesystem.read: [.]— reads its own bundle.filesystem.write: [./outputs]— writes only underoutputs/.- No network, no env vars.
See course/capabilities.yaml for the exact manifest.
What an author should change when copying
- The
namefield in this frontmatter (must match your directory name). - The
description(be specific about what + when). - The body of this file.
references/usage.mdcontent (or remove the file if you don't need it).scripts/say-hello.sh(or replace with your real script).course/capabilities.yaml— declare only what you actually need.
What ships with it
4 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.
- 6d ago First seen · 76 lines · 56 tokens per session scan A afff553c1fc8
with-references-and-scripts is a skill published in the GitHub repository nicolasmelo1/logion (37 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 646 once invoked, about $0.0003 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
no-mistakes
Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach upstream. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push safely, asks you to do a task and then validate it, or invokes /no-mistakes.
mnemosyne-context
Load this when working on the mnemosyne memory system — its repo, sync server, memory databases, or CI. Covers architecture, the surface/sync data model, dev workflow (tests/ruff/CI matrix), release policy, and known gotchas that are easy to get wrong. Use for any "mnemosyne" dev or devops task, or when a…
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.