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 skills/arch3rpro/ark-space/skill-managernpx skills add arch3rPro/ark-space --skill skill-managergit clone --depth 1 https://github.com/arch3rPro/ark-spaceWrote 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/arch3rpro/ark-space/skill-manager)<a href="https://agentmods.dev/skills/arch3rpro/ark-space/skill-manager"><img src="https://agentmods.dev/badge/skills/arch3rpro/ark-space/skill-manager.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 | $0.00035 | $0.00507 |
| Opus 5 | $0.00017 | $0.00253 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Manager
Manage skills as durable package assets, not one-off prompt snippets.
Use this skill when creating a skill, adapting an external skill, recording upstream provenance, assigning a skill to a role, validating the skills package, or preparing a selective upstream update.
Workflow
- Classify the request: create, adapt, mirror, validate, assign role, document, or review upstream changes.
- Check
registry/skills.yaml,registry/sources.yaml, andregistry/roles.yamlbefore editing. - Keep skill bodies under
skills/<skill-name>/SKILL.md. - Record source provenance for every reused or adapted skill.
- Assign each active skill to at least one role unless it is intentionally standalone.
- Run
python3 scripts/validate-skills.pyafter registry, role, manifest, or skill changes.
Sync Modes
| syncMode | Meaning | Update behavior |
|---|---|---|
mirror |
External skill kept close to upstream | Prefer direct sync, preserve upstream behavior, record version or commit when available |
adapted |
External skill changed for this package | Compare upstream changes and merge selectively |
local |
Skill created here | Maintain directly |
reference-only |
Upstream used only as design reference | Do not publish it as a local skill unless explicitly promoted |
Creating a Skill
- Create
skills/<skill-name>/SKILL.md. - Add YAML frontmatter with
nameanddescription. - Keep instructions host-neutral unless the skill is intentionally platform-specific.
- Add the skill to
registry/skills.yaml. - Add or update any needed source in
registry/sources.yaml. - Assign the skill to one or more roles.
- Run validation.
Adapting an External Skill
- Record the upstream in
registry/sources.yaml. - Add the skill with
syncMode: adapted. - Keep a concise note about why it diverges from upstream.
- Preserve license and attribution requirements.
- Review upstream updates manually before merging.
Validation
Run:
python3 scripts/validate-skills.py
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.
- 3d ago First seen · 57 lines · 35 tokens per session scan A 8e1a584e1edd
skill-manager is a skill published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 507 once invoked, about $0.0002 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
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
feature-dev
Feature development workflow. Use when: implementing features, writing code, running dev loop. Not for: understanding code (use code-explore), reviewing code (use codex-code-review). Output: implemented feature + tests + review gate.
doc-refactor
Refactor documents — simplify without losing information, visualize flows with sequenceDiagram.
invest
First-time fork users: run the invest-setup skill first to initialize. The main flow lives in this skill (the AI agent uses the CLI/MCP to view the portfolio / run the committee / replay decision history). The Web GUI has been retired (2026-07) — every capability is exposed via CLI subcommands / MCP tools. The backend…