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 commands/tondevrel/scientific-agent-skills/formatgit clone --depth 1 https://github.com/tondevrel/scientific-agent-skillsWrote 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/commands/tondevrel/scientific-agent-skills/format)<a href="https://agentmods.dev/commands/tondevrel/scientific-agent-skills/format"><img src="https://agentmods.dev/badge/commands/tondevrel/scientific-agent-skills/format.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 | $0.00000 | $0.00552 |
| Opus 5 | $0.00000 | $0.00276 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
FORMAT 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commands/ Format Guide
This folder contains slash commands - user-invocable actions that users explicitly call via /command-name.
File Naming
- Files must be
.md(Markdown) - Filename becomes the command name:
build-agent.md→/build-agent - Use kebab-case:
analyze-data.md,run-experiment.md
File Structure
Each command file has two parts:
1. YAML Frontmatter (Required)
---
description: Brief description shown in command autocomplete
argument-hint: [optional-argument-placeholder]
allowed-tools: [Read, Glob, Grep, Bash, Write, Edit, WebFetch]
---
Fields:
description(Required): One-line description of what the command doesargument-hint(Optional): Placeholder text for expected argumentallowed-tools(Optional): List of tools the command can use
2. Markdown Body
# Command Title
Brief explanation of what this command does.
## Arguments
The user invoked this command with: $ARGUMENTS
## Instructions
Step-by-step guide for the AI when this command is invoked:
1. First, do X
2. Then, do Y
3. Finally, do Z
## Capabilities
- Capability 1
- Capability 2
## Example Usage
\`\`\`
/command-name argument1
/command-name different argument
\`\`\`
Example Command
---
description: Analyze a scientific dataset and generate a report
argument-hint: [path-to-dataset]
allowed-tools: [Read, Glob, Grep, Bash, Write]
---
# Analyze Scientific Data
This command analyzes a dataset and generates a summary report.
## Arguments
The user invoked this command with: $ARGUMENTS
## Instructions
1. Read the skill file at `data-analysis/SKILL.md` for methodology
2. Load the dataset from the provided path
3. Generate statistical summary
4. Create visualization recommendations
5. Output a markdown report
## Example Usage
\`\`\`
/analyze-data ./experiments/results.csv
/analyze-data ./data/measurements.parquet
\`\`\`
Best Practices
- Keep descriptions concise - They appear in autocomplete
- Use $ARGUMENTS - This gets replaced with user's input
- Reference skills - Point to relevant SKILL.md files for detailed guidance
- Provide examples - Show 2-3 typical usage patterns
- Limit scope - One command = one focused action
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 · 102 lines · 0 tokens per session scan A e70a64f6066f
FORMAT is a command published in the GitHub repository tondevrel/scientific-agent-skills (20 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 552 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.