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 commands/art9mid/arc-skill/arc-featuregit clone --depth 1 https://github.com/art9mid/arc-skillWhat 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 | $0.00094 | $0.01149 |
| Opus 5 | $0.00047 | $0.00575 |
| Sonnet 5 | $0.00019 | $0.00230 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
arc-feature 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 112 lines · 94 tokens per session scan A 191bec8c48c8
arc-feature is a command published in the GitHub repository art9mid/arc-skill (7 stars, last pushed 4mo ago), with no licence file. It adds 94 tokens to every session and 1,149 once invoked, about $0.0005 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 commands, from other repositories
review-code
Read ALL memory bank code rules + best practices, check the files that changed, and APPLY fixes so they adhere. The active counterpart to /scan (which is read-only). Use after an AI session, before commit, to make changed files compliant.
rules
Command "rules" from chohra-med/expo_boilerplate, covering invocation, what a "rules-boundary" directory is, the five sections (one owner agent each), generate (the "create them if they don't exist" path) and resolve (what each agent reads).
init
Command "init" from chohra-med/expo_boilerplate, covering command: init — spec-driven bootstrap, invocation, step 1 — capture intent (the interview, one message), step 2 — scaffold (copy from templates/, fill the {{...}}) and step 4 — write the first spec from the goal.
generate-agents
Command "generate-agents" from chohra-med/expo_boilerplate, covering invocation, how it works, the concern each agent gets (one per agent), rules for the injected block (every agent) and idempotent + the loop.
learn
Command "learn" from chohra-med/expo_boilerplate, covering command: learn — the learning loop (feedback → rules), when to run it, invocation, the loop (6 steps) and 1 — capture.
tickets
Command "tickets" from chohra-med/expo_boilerplate, covering invocation, source a — a ticket mcp (linear / github issues / jira / …), source b — an inline plan (no ticket system), then: build and hard rules.