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 agents/arch3rpro/ark-space/skill-managergit clone --depth 1 https://github.com/arch3rPro/ark-spaceWhat 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 | $0.00020 | $0.00214 |
| Opus 5 | $0.00010 | $0.00107 |
| Sonnet 5 | $0.00004 | $0.00043 |
| Haiku 4.5 | $0.00002 | $0.00021 |
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.
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 regenerateintegrations/. - 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-engineerwhen the work is primarily runtime implementation. - Hand off to
doc-writerwhen 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.
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.
- 2d ago First seen · 23 lines · 20 tokens per session scan A ed567a34c005
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.
Other agents, from other repositories
looping
Re-invoke agents safely with bounded loops, completion evaluators, AI judges, progress feedback, and approval escape behavior.
maintaining-agent-docs
这份"AI 维护指南"(AGENTS.md + docs/agents/)本身也是项目资产,需要随项目演化。.
code_act
Learn what CodeAct is and when to use it with Agent Framework.
fusion-executor
Implements bounded Fusion specifications with a fast coding model.
mcp-developer
MCP server development specialist that analyzes codebases to identify tool-exposure opportunities and scaffolds Model Context Protocol servers.
contributor
Sub-agent dispatched for substantive contributions (PDFs, URLs, long pastes). Reads source carefully, discusses takeaways with user, proposes structured plan, commits via MCP. Cannot bypass append-only contract.