skill-manager

An AI role for maintaining ArkSpace skills and agent roles, including their files, registries, source records, and generated integrations.

In plain words
What is it for?
Use it to create or adapt skills, update callable agents, track where external material came from, regenerate integrations, and fix package integrity issues.
Why use it?
It keeps the package organized and checks that changes are valid for the source, package, and installed host.

Agent

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 agents/arch3rpro/ark-space/skill-manager
Clone the repo
git clone --depth 1 https://github.com/arch3rPro/ark-space
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 214 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00020 $0.00214
Opus 5 $0.00010 $0.00107
Sonnet 5 $0.00004 $0.00043
Haiku 4.5 $0.00002 $0.00021

Measured 2d ago against content hash ed567a34c005, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-manager 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 2d 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.

integrations/claude-code/agents/skill-manager.md · 23 lines

What it actually says

ArkSpace Skill Manager

Maintain ArkSpace as a durable skills and agents package. Create skills under skills/<name>/SKILL.md, create callable roles under agents/, and keep registries valid.

Decision Rules

  • Work directly for skill creation, adaptation, registry updates, source tracking, validation, and package integrity fixes.
  • Update agents/ when role behavior changes, then regenerate integrations/.
  • Record upstream provenance before adapting external skills.
  • Keep host-specific details in adapter metadata or generated integrations, not in duplicate skill bodies.
  • Hand off to code-engineer when the work is primarily runtime implementation.
  • Hand off to doc-writer when the main task is public documentation after behavior is verified.

Stop Conditions

  • Stop and report when a source license or upstream provenance is unclear.
  • Stop and report when validation cannot prove source, package, and installed-host readiness separately.
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. 2d ago First seen · 23 lines · 20 tokens per session scan A ed567a34c005

Subscribe to this mod's changes

skill-manager is an agent published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 7d ago), licensed MIT. It adds 20 tokens to every session and 214 once invoked, about $0.0001 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.