sync-skills-spec

sync-skills-spec is a skill for Claude Code, Codex from phil65/agentpool. It costs 24 tokens per session (548 once invoked), scanned C, original, MIT.

A maintenance task that compares this project's agent skills code with the official Agent Skills Specification, which defines how skills are described, validated and turned into prompts.

In plain words
What is it for?
Use it when updating the Skill data model, frontmatter parsing, validation, prompt generation, or related skill-management code.
Why use it?
It helps reveal when the local implementation has missing fields, outdated validation rules or differences from the published standard.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/phil65/agentpool/sync-skills-spec
Any agent
npx skills add phil65/agentpool --skill sync-skills-spec
Clone the repo
git clone --depth 1 https://github.com/phil65/agentpool

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sync-skills-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/phil65/agentpool/sync-skills-spec.svg)](https://agentmods.dev/skills/phil65/agentpool/sync-skills-spec)
Your own site
<a href="https://agentmods.dev/skills/phil65/agentpool/sync-skills-spec"><img src="https://agentmods.dev/badge/skills/phil65/agentpool/sync-skills-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 548 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00548
Opus 5 $0.00012 $0.00274
Sonnet 5 $0.00005 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 4d ago against content hash 051e59f1b43e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

sync-skills-spec scanned grade C with 1 finding 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$tmp"
.agents/skills/sync-skills-spec/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Skills Spec

Keep src/agentpool/skills/ aligned with the official Agent Skills Spec.

Steps

  1. Clone the reference repo into a temporary directory:

    tmp=$(mktemp -d)
    git clone --depth 1 https://github.com/agentskills/agentskills "$tmp/agentskills"
    
  2. Read the spec and reference implementation:

    • $tmp/agentskills/spec/ — the formal specification documents
    • $tmp/agentskills/implementations/ — reference implementations (especially Python)
    • Focus on the SkillProperties model, frontmatter fields, validation rules, and prompt generation
  3. Compare with our implementation:

    • src/agentpool/skills/skill.py — our Skill Pydantic model, validators, parse_frontmatter(), to_prompt()
    • src/agentpool/skills/registry.py — discovery and registration (our extension, not part of the spec)
    • src/agentpool/skills/manager.py — pool-wide management (our extension)
    • Check for missing fields, changed validation rules, new spec requirements
  4. Apply updates to our code:

    • Add any new frontmatter fields to the Skill model
    • Update validators to match spec changes (name format, length limits, allowed fields)
    • Update to_prompt() if the recommended XML format changed
    • Do NOT replace our registry/manager — those are agentpool-specific extensions
  5. Update the synced commit hash in src/agentpool/skills/skill.py:

    • Get the current HEAD of the cloned repo: git -C "$tmp/agentskills" rev-parse HEAD
    • Update the SPEC_SYNCED_COMMIT constant to the new hash
    • This tracks which version of the spec we last synced against
  6. Clean up:

    rm -rf "$tmp"
    

Key differences from upstream

Our implementation extends the spec with:

  • Async discovery via fsspec/UPath (supports GitHub, S3, etc.)
  • Registry pattern (SkillsRegistry extending BaseRegistry)
  • Pool-wide management (SkillsManager with async context manager)
  • YAML parsing via yamling (not strictyaml)

Read the full file on GitHub · 54 lines

Changes

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.

  1. 4d ago First seen · 54 lines · 24 tokens per session scan C 051e59f1b43e

Subscribe to this mod's changes

sync-skills-spec is a skill published in the GitHub repository phil65/agentpool (186 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 548 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

braindb

Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.

dimknaf/braindb · 36 tokens

braindb-agent

Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.

dimknaf/braindb · 40 tokens

braindb-custom-profile

How to author a BrainDB custom profile — prompt add/replace fragments and an optional keyless ingestor — that shapes wiki naming/structure and feeds a custom ingestion source, with zero effect on defaults when inactive.

dimknaf/braindb · 49 tokens

complete-partial-pr

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.

pydantic/pydantic-ai · 55 tokens

edgeone skill scanner

Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…

Tencent/AI-Infra-Guard · 148 tokens

adding-a-provider-api-feature

Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. Use when wiring a provider feature through the library — it enforces reasoning from the existing cross-provider abstraction before designing…

pydantic/pydantic-ai · 97 tokens