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 skills add ArcBlock/agent-skills --skill afsgit clone --depth 1 https://github.com/ArcBlock/agent-skillsWrote 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/arcblock/agent-skills/afs)<a href="https://agentmods.dev/skills/arcblock/agent-skills/afs"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/afs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arcblock/agent-skills/afs"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/afs.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00027 | $0.02094 |
| Opus 5.5 | $0.00011 | $0.00838 |
| Sonnet 5.5 | $0.00005 | $0.00419 |
| Haiku 4.5 | $0.00003 | $0.00209 |
Grade A, and why
afs 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 1mo 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARC skill: afs
AFS is the path-addressed world. Prefer MCP (arc skill show mcp) or the
daemon HTTP API (POST /afs on the instance's own port) for live agent
work — both attach to one already-known instance without ambiguity.
arc afs <cmd> is for ad-hoc inspection of a named instance from a
terminal. It never silently picks a world: pass --instance <name> to
attach to a specific instance's daemon, or --standalone for a throwaway
ad-hoc AFS with no daemon and no runtime state. Bare arc afs <cmd> (no
flag) targets the default instance and fails closed — non-zero exit —
if that instance has no daemon running.
Core ops
arc afs ls [path] --instance <name>
arc afs read <path> --instance <name>
arc afs write <path> [content] --instance <name>
arc afs stat <path> --instance <name>
arc afs exec <executable_path> --args '<json-object>' --instance <name>
arc afs search <path> <query> --instance <name>
arc afs explain [topic|path] --instance <name>
Every example above works the same with --standalone instead of
--instance <name> (ad-hoc mode; the first output line reads [standalone]).
arc afs mount is the exception — it is NOT instance-scoped. Its four
subcommands (add / remove / list / validate) only read and write the
.afs-config/config.toml found by walking up from the current directory, and
they reject --instance / -i / --home rather than accept-and-ignore
them. To mount a path into a running instance, use arc attach:
cd <dir-with-.afs-config> && arc afs mount list # edit/inspect the cwd config
arc attach --to ws://localhost:<port> --namespace <ns> --source <dir> # runtime mount
Exec args (critical): pass parameters as one JSON object. Check the
exact shape with arc afs exec --help (per-command help never needs an
instance).
arc afs exec /some/.actions/foo --args '{"key":"value"}' --instance <name>
Do not invent bare key=value after -- unless exec --help documents
it. When in doubt: --args '{...}'.
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.
- 1mo ago First seen · 179 lines · 27 tokens per session scan A 667545e5314d
afs is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 9d ago), licensed MIT. It adds 27 tokens to every session and 2,094 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
atlas-mssql
SQL Server specifics for Atlas (also Azure SQL and MSSQL): login, dev database and URL scope (mode=schema vs mode=database, the database query parameter), compatibility level and collation, system-generated constraint names, clustered index defaults and datetime2 precision in HCL, GO batches and the delimiter…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.