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/host-platform-rulesgit 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 | $0.01003 |
| Opus 5 | $0.00000 | $0.00502 |
| Sonnet 5 | $0.00000 | $0.00201 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
host-platform-rules 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 yesterday.
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.
Host platform rules ({{HOST_PLATFORM_RULES}})
For operators running AgentsCommander. What the per-platform {{HOST_PLATFORM_RULES}} block is, where it renders, and how to customize it by editing a plain file — without code changes or a release.
What it is
{{HOST_PLATFORM_RULES}} is the 8th mandatory placeholder of the global default agent template (template version 5), rendered immediately after {{CLI_CONTEXT}} in every materialized agent context. Its content is selected by the session's execution platform:
| Host OS | Rendered block |
|---|---|
| Windows | The Git Bash CLI-routing rule (single source of truth; the {{INTER_AGENT_MESSAGING}} section only carries a pointer to it) |
| Linux / macOS | A minimal note that no platform-specific shell routing rules apply |
| Container (transport api) session | Nothing — no block, no file read |
The block is mandatory: a preserved personalized template that lacks the token receives the current block through the append fallback, exactly like {{AGENT_REPOS}}.
Where it renders
- Global template (
Context.AgentsCommander.md/AGENTS.md/CLAUDE.mdmaterializations): between## CLI executableand## Session credentials. - Root Agent runtime prologue: as its 10th code-owned block, between the CLI context and session credentials blocks. The root role template (
Context.root-agent.md) is never rendered through the placeholder machinery; the root gets the block from the prologue. - Coordinator sessions: through the global render — no coordinator-template change is needed and none exists (the block must not be added to
Context.coordinator.md, or it would duplicate). - Container sessions: never.
The platform files
Each platform's block content is configurable by editing a per-platform file in the project .ac root:
| File | Platform |
|---|---|
.ac/Context.platform.windows.md |
Windows host sessions |
.ac/Context.platform.linux.md |
Linux host sessions |
.ac/Context.platform.macos.md |
macOS host sessions |
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.
- yesterday First seen · 57 lines · 0 tokens per session scan A 3de692653d74
host-platform-rules 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 1,003 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).