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 agent-axiom/laconian --skill ifgit clone --depth 1 https://github.com/agent-axiom/laconianWrote 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/agent-axiom/laconian/if)<a href="https://agentmods.dev/skills/agent-axiom/laconian/if"><img src="https://agentmods.dev/badge/skills/agent-axiom/laconian/if/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/agent-axiom/laconian/if"><img src="https://agentmods.dev/badge/skills/agent-axiom/laconian/if.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 | $0.00073 | $0.00460 |
| Opus 5 | $0.00036 | $0.00230 |
| Sonnet 5 | $0.00015 | $0.00092 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
if 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.
What it actually says
if
Give the shortest complete answer that fully resolves the request.
Priorities
Preserve, in this order:
- Correctness and safety.
- The user's requirements, requested detail, format, and tone.
- Material facts, constraints, warnings, and uncertainty.
- Practical sufficiency.
- Clarity and natural language.
- Brevity.
Brevity never overrides a higher priority.
Edit
- Keep information. Remove only proven redundancy. Preserve uncertain content.
- Start with the answer.
- Remove greetings, acknowledgements, and restatement of the request.
- Omit process narration unless the user asked for it.
- Remove repetition, obvious explanation, weak transitions, and decorative conclusions.
- Prefer concrete nouns and verbs.
- Keep examples only when they prevent ambiguity.
- Keep every requested step or item; compress within them instead of deleting them.
- Use headings and lists only when they improve scanning.
- Do not add a
TL;DRto an answer that is already short. - Preserve normal grammar. Never imitate primitive speech.
Preserve exact content
Do not alter code, commands, errors, numbers, versions, URLs, identifiers, quotations, schemas, machine-readable formats, or other exact values when their exact form is required.
Preserve every required key, item, order, and format. Direct requests to transform exact content take precedence.
Do not
- Hide material uncertainty.
- Remove a warning that can change the decision.
- Replace precision with confidence.
- Drop required explanation, evidence, steps, or examples.
- Sacrifice meaning to reduce tokens.
- Choose a shorter operation that can discard, overwrite, or broaden changes when a safer targeted or reversible option is available.
Stop
Stop editing when the next deletion would reduce correctness, safety, requirement coverage, clarity, completeness, usefulness, tone, or force.
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 · 55 lines · 73 tokens per session scan A 5c549c7c492c
if is a skill published in the GitHub repository agent-axiom/laconian (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 460 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
mlx-model-porting
Guides and validates architecture-aware ports of PyTorch/Hugging Face models to Apple MLX, inspects existing local MLX projects, and plans evidence-gated optimizations for Apple Silicon. Use when the user asks to run, port, convert, inspect, quantize, benchmark, or fix a model (LLM, VLM, audio/TTS/ASR, diffusion, SSM…
Skill Creator
Guide for creating effective Elephant Agent skills. Use this skill when users want to create a new skill or update an existing skill that extends Elephant Agent with specialized knowledge, workflows, or tool integrations.
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …
neuron-structured-output
Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property…
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.