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 skills/mblua/agentscommander/role-skill-boundary-auditnpx skills add mblua/AgentsCommander --skill role-skill-boundary-auditgit 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/role-skill-boundary-audit)<a href="https://agentmods.dev/skills/mblua/agentscommander/role-skill-boundary-audit"><img src="https://agentmods.dev/badge/skills/mblua/agentscommander/role-skill-boundary-audit.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00630 |
| Opus 5 | $0.00023 | $0.00315 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
role-skill-boundary-audit 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 4d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
role-skill-boundary-audit
Purpose
Roles define who is responsible.
Skills define how to perform a reusable capability.
Diagnostic by default: recommend, do not rewrite, unless the user or active workflow asked for the refactor.
Conciseness mandate (always)
Write the minimum that changes behavior; roles and skills spend context budget every time they load. This applies to every Role.md and skill you write, recommend, or rewrite.
- Add only what adds value; cut the rest.
- Keep rationale to one line, and only where it guides a judgment the rule itself does not cover.
- No restatement: drop "Why" / "How to apply" / examples that repeat a rule without adding information.
Role.mdis the tightest surface (always loaded). Load-on-demand skills may hold more detail, but still no padding.- When recommending or rewriting, target the smallest, least-verbose change that restores the boundary and preserves operative meaning.
Classification
- Keep in Role: identity, ownership, authority, responsibilities, escalation, durable boundaries for one agent.
- Move to Skill: repeatable workflow, checklist, tool procedure, implementation pattern, domain method.
- Move to Global Policy: must constrain every agent or session regardless of role.
- Move to Workflow Docs: team process, operator/onboarding guide, durable docs humans browse outside startup context.
- Move to Memory: project fact, decision, preference, or status that persists but is not a standing instruction.
- Duplicate / Consolidate: same guidance in multiple places; pick one source of truth.
- Trim / Compress: content is in the right place but bloated; cut to the operative minimum.
- Split Agent: one role owns unrelated accountability surfaces.
- Merge Agent: agents differ mostly by wording or minor task variants.
- Needs Owner Decision: placement touches authority, access, team structure, or policy.
Workflow
- Identify the instruction or proposed change.
- Name current vs proposed location.
- Classify it.
- Check for authority language, reusable procedure, duplicated guidance, agent-boundary drift, and verbosity.
- Recommend the smallest, least-verbose change that restores a clear boundary and preserves meaning.
- Stop at the recommendation if the change would rewrite files or split/merge agents, unless the user asked for the refactor.
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.
- 4d ago First seen · 66 lines · 46 tokens per session scan A af3e86a69e9a
role-skill-boundary-audit is a skill published in the GitHub repository mblua/AgentsCommander (10 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 630 once invoked, about $0.0002 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 skills, from other repositories
qa-cli-mcp-api
Select and run explicitly requested, risk-based QA for Anarlog's CLI, webhooks, stdio MCP, hosted Cloud API, and remote MCP. Test only affected lanes unless comprehensive coverage is requested.
sqlite-schema-design
Design or review schemas for crates/cloudsync using SQLite Sync constraints, not generic SQLite advice. Use when adding synced tables, changing synced columns, or planning CloudSync-safe migrations.
add-plugin
Scaffold a new Tauri plugin in this repository when asked to add or create a plugin under plugins/. Use this for plugin generation and repository integration work, not for editing an existing plugin unless the request is specifically about bringing a freshly generated plugin in line with project conventions.
axum-test-transport
Choose between in-process tower::ServiceExt::oneshot tests and real tokio::net::TcpListener server tests for Axum services in this repository.
new-changelog
Create the next desktop changelog entry when asked to add a changelog file or prepare the next release note under packages/changelog/content. Use this when the task is specifically about determining the next version and creating the markdown entry.
migrate-to-sqlite
Migrate a TinyBase table to SQLite. Use when asked to move a data domain (e.g. templates, vocabs) from the TinyBase store to the app SQLite database.