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/mblua/agentscommander/agent-skillsgit clone --depth 1 https://github.com/mblua/AgentsCommanderWhat 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 | $0.00000 | $0.01362 |
| Opus 5 | $0.00000 | $0.00681 |
| Sonnet 5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
agent-skills 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent skills
For developers ready to add reusable per-agent workflows. Skills are markdown documents AC discovers from each agent's canonical skills/ directory.
Agent skills are reusable instructions stored in an agent's canonical
skills/ folder. Use them for workflows that are too specific for a general
role prompt but useful enough to keep around, such as release checklists,
framework conventions, debugging recipes, or tool-specific operating notes.
AgentsCommander scans the canonical Agent Matrix skills/ directory at
session/context creation time when a canonical Matrix root is available. It
reads only the first YAML frontmatter segment from each SKILL.md, injects a
deterministic metadata index into the generated context, and does not inject
all full SKILL.md bodies at startup.
Where Skills Live
For an Agent Matrix agent, skills live beside the agent's canonical role, memory, and plans:
This tree shows the skill-relevant canonical state only. Other Matrix entries,
such as inbox/, outbox/, and config.json, are omitted here.
<project>/
+-- .ac/
+-- _agent_dev-rust/
+-- Role.md
+-- memory/
+-- plans/
+-- skills/
When that agent runs inside a room replica, the generated
AgentsCommander context allows writes to the origin Agent Matrix skills/
folder. That keeps skills canonical across replicas instead of copying them
into one temporary room session.
Standalone agent folders can also contain a local skills/ folder, but
AgentsCommander runtime discovery does not scan standalone local skills unless
canonical Agent Matrix state is resolved. The canonical Root Agent directory
ac-root-agent/ is the exception: its local skills/ directory is durable Root
Agent state, seeded by AgentsCommander, and discovered in generated Root Agent
context.
Minimal Skill Layout
Use one directory per skill. SKILL.md with YAML frontmatter is the validated
entrypoint. name is optional and defaults to the skill directory name.
description is recommended; when absent, AgentsCommander keeps the skill
visible with a warning that the agent should inspect SKILL.md before use.
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 · 161 lines · 0 tokens per session scan A 73b6a1899eeb
agent-skills is an agent published in the GitHub repository mblua/AgentsCommander (10 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,362 tokens. 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
engine-implementation-executor
Execute an already-reviewed phase.rs implementation plan surgically. Receives the approved plan + scope, edits files, runs Tilt-first verification, and returns a diff summary with any judgement-call notes. Does NOT plan, does NOT review, does NOT commit. Spawned by the /engine-implementer skill.
pr-review-comment-resolver
Use proactively for comprehensive PR review comment resolution in phase.rs. Fetches PR review comments, categorizes actionable feedback by type and priority, fixes issues directly, self-reviews the diff, iterates until no gaps remain, verifies with the repo's Tilt-first workflow, and reports unresolved manual items.
mtg-rules-auditor
Audits MTG Comprehensive Rules coverage in engine code. Accepts targeted file lists or CR sections for lightweight runs, or does a full codebase sweep. Produces structured reports mapping game logic to CR rule numbers.
parser-gap-finder
Analyzes parser coverage gaps, classifies them by failure reason, and proposes prioritized parser fixes to unlock the most cards with the least code changes. Run with cargo parser-gaps data available.
git-workflow
Hermes CN 的需求与 bug 修复通常同时横跨 Desktop 与 Core 两个仓库。正式动手写代码前，两个仓库都必须先过这道预检，不要直接在 main 上改：.
PROJECT_MAP
Agent "PROJECT_MAP" from zyqzyq/Unfour, covering projectmap.md, top-level directory structure, frontend packages, @unfour/ui (packages/ui) and @unfour/command-client (packages/command-client).