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 aksika/abtars --skill skill-authoringgit clone --depth 1 https://github.com/aksika/abtarsWrote 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/aksika/abtars/skill-authoring)<a href="https://agentmods.dev/skills/aksika/abtars/skill-authoring"><img src="https://agentmods.dev/badge/skills/aksika/abtars/skill-authoring.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 | $0.00024 | $0.01535 |
| Opus 5 | $0.00012 | $0.00767 |
| Sonnet 5 | $0.00005 | $0.00307 |
| Haiku 4.5 | $0.00002 | $0.00153 |
Grade B, and why
skill-authoring scanned grade B with 2 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 7d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- After every change, reload and inspect the catalog. Run any scripts or commands needed to verify the changed procedure. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bins: [jq, curl] How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring
Store reusable procedures as skills. Store facts, events, and preferences with memory_store.
Choose the right persistence
Use a skill when the knowledge explains how to do something and is likely to help again, especially when the procedure is multi-step, error-prone, or corrected by the user.
Use memory_store when the knowledge records what is true: a fact, event, decision, or preference. Do not create a skill for one conversation's outcome.
Never put credentials, tokens, private user data, or conversation transcripts in a skill. Declare required environment-variable names, not their values.
Authoring workflow
- Search
~/.abtars/skills/skills_catalog.mdfor an existing skill that already covers the procedure. Improve it instead of creating a duplicate. - Choose a lowercase kebab-case name, 3-64 characters, with no leading or trailing hyphen.
- Write a specific description (1-120 characters) that says what the skill does and when it applies. The catalog uses this text to select skills.
- Keep the body procedural and imperative. Include prerequisites, ordered actions, failure handling, and a concrete verification step only when they add real value.
- Create the skill with
skill_create. Pass only the Markdown body incontent; the tool writes frontmatter. - Run
/skill reload, then confirm the skill appears inskills_catalog.mdwith the expected name and description.
skill_create writes ~/.abtars/skills/self/<skill-name>/SKILL.md. Its body must be 100-50,000 UTF-8 bytes. Prefer a concise body; move substantial supporting material into references/.
Skill shape
<skill-name>/
├── SKILL.md # required: metadata and instructions
├── skill.json # only for a persistent interactive skill
├── scripts/ # optional deterministic helpers
└── references/ # optional detailed guidance
A typical generated file has:
---
name: inspect-service-logs
description: Diagnose a failing service from its logs; use for startup failures and repeated crashes.
tags: [debugging, services]
related: [troubleshooting]
---
# Inspect Service Logs
1. Capture the first error and its surrounding context.
2. Trace it to the component that emitted it.
3. Verify the diagnosis by reproducing the failure or checking runtime state.
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.
- 7d ago First seen · 147 lines · 24 tokens per session scan B ea6805cc6196
skill-authoring is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,535 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
api-caller
Call any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.
calculator
Evaluate mathematical expressions and unit conversions. Handles arithmetic, percentages, exponents, and common unit conversions (temperature, distance, weight). No external dependencies.
task-list
Required for 4+ step requests; add tasks at start and update status after each step.
text-analyzer
Analyze text content and produce statistics including word count, line count, character count, most frequent words, and readability metrics. Works on any plain text input provided inline or from a file path.
memory-enhancement
Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, checking memory health, or verifying code references are still valid. Use when you say "add a citation", "verify this memory's code refs", "check memory health". Do NOT use for searching or creating…