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 mblua/AgentsCommander --skill agency-agents-rolesgit clone --depth 1 https://github.com/mblua/AgentsCommanderWrote 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/mblua/agentscommander/agency-agents-roles)<a href="https://agentmods.dev/skills/mblua/agentscommander/agency-agents-roles"><img src="https://agentmods.dev/badge/skills/mblua/agentscommander/agency-agents-roles/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/mblua/agentscommander/agency-agents-roles"><img src="https://agentmods.dev/badge/skills/mblua/agentscommander/agency-agents-roles.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 | $0.00056 | $0.00526 |
| Opus 5.5 | $0.00022 | $0.00210 |
| Sonnet 5.5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
agency-agents-roles 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.
What it actually says
agency-agents-roles
Mandatory offer before creating a specialist agent
Before you create any new specialist agent (any role-defined create-agent-matrix), you MUST first offer Agency Agents role templates.
Skip the offer ONLY if, in this session, the user already declined Agency templates or explicitly asked for a custom or from-scratch role.
Say what Agency Agents is, from real data only
When you offer, briefly say what Agency Agents is, but state ONLY what real local data supports. Never invent a description or recall one from memory.
- Agency Agents is a collection of tested, shareable role templates published in a source repository. The real source is the
repovalue reported byagency-templates status(and stored in the cache manifest), not a URL you guess. - Describe Agency Agents concretely by its source repo plus the actual templates available (their real names and 1-line descriptions from
agency-templates list); there is no local one-line project description to quote. - If the template cache is absent (status reports it unavailable), say so and offer to fetch it. Ask before downloading or updating, because it writes to the local template cache.
On acceptance, use the CLI
Use the AgentsCommander CLI from AGENTSCOMMANDER_BINARY_PATH:
"<AGENTSCOMMANDER_BINARY_PATH>" agency-templates update --ref main
"<AGENTSCOMMANDER_BINARY_PATH>" agency-templates status --pretty
"<AGENTSCOMMANDER_BINARY_PATH>" agency-templates list --pretty
update refreshes the local cache from the source repo (--ref selects the git ref, default main). status reports whether a cache is present and its repo, ref, and commit. list prints each cached template's real id and 1-line description.
Then present the candidate template(s) and create with create-agent-matrix --role-template <id>. Use only the IDs and descriptions that command returns; never invent template IDs or descriptions.
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 · 34 lines · 56 tokens per session scan A 30431b8b39ba
agency-agents-roles is a skill published in the GitHub repository mblua/AgentsCommander (12 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 526 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history, or import a local recording. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
pake
Package a website or local web build as a desktop app with Pake. Use for packaging, CLI options, icons, bundle identifiers, or WebView proxy setup. Not for unrelated Tauri development or uninstalling apps.
prompt-cache-optimizer
Audit and optimize Pisper system-prompt and tool-schema token overhead while preserving stable prompt-cache prefixes, permissions, and runtime behavior. Invoke only for explicit prompt or tool-context optimization work.
screenshot-studio
Regenerate the Pisper product screenshots under docs/shots/ against the current UI. Starts an isolated dev instance, seeds fictional demo data through the real runtime APIs, captures every referenced page at the exact 2558x1380 asset size, and replaces the files. Use only when the user asks to refresh product…
app-release
Use when the user asks to release a new version, ship a build, or publish a Skill Zoo release. Also use when a tag push results in Homebrew 404 errors or missing artifact failures.
tauri-updater
Use when adding software auto-update to a Tauri 2 desktop app, or when users ask about tauri-plugin-updater integration, app update checking, distinguishing installer vs portable builds for updates, or generating update manifests for GitHub Releases.