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/br3eze-code/br3eze-code/agentos-editornpx skills add br3eze-code/br3eze-code --skill agentos-editorgit clone --depth 1 https://github.com/br3eze-code/br3eze-codeWhat 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 | $0.00060 | $0.00543 |
| Opus 5 | $0.00030 | $0.00271 |
| Sonnet 5 | $0.00012 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
agentos-editor 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentOS Editor
Use this skill when a user asks to edit, revise, polish, restructure, compare, or issue controlled content. First identify the artifact type, source of truth, audience, tenant, project, revision, requested change, and publication state.
Workflow
identify source and revision
→ inspect requested change and scope
→ preserve meaning and protected requirements
→ edit or propose changes
→ run format, consistency, and integrity checks
→ record review comments and revision
→ request publication approval when required
→ issue approved artifact and evidence
For document-controlled work, use the nearest existing WBS package or create an Editor activity with a stable number such as ACT-EDITOR-DOC-001. Include source reference, original revision, target revision, editor, reviewers, change summary, acceptance criteria, evidence, and approval state.
Editing rules
Distinguish clearly between:
draft
review
revision proposed
approved
published
superseded
Never overwrite the source of truth without a backup or revision record. Preserve technical constraints, tenant boundaries, legal or financial values, identifiers, code semantics, and explicit user requirements. Do not invent missing facts. Mark unresolved points as questions or assumptions.
For code-adjacent edits, preserve module system, imports, error handling, authorization, idempotency, and tests. For controlled documents, preserve revision history, authorship, references, distribution scope, and approval status. For customer communication, remove private data and unverified claims.
Review and approval
Use read and draft capabilities for ordinary edits. Treat document.publish, drawing.issue, specification.approve, message.send, record.share, and production code changes as approval-gated mutations. Show a change summary or diff before approval. Recheck identity, scope, current revision, and approval immediately before issuing.
Outputs
Return:
artifact and revision
source of truth
requested changes
applied changes
unresolved questions
review findings
validation results
approval state
publication or handoff action
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 63 lines · 60 tokens per session scan A 4101a46fb47f
agentos-editor is a skill published in the GitHub repository br3eze-code/br3eze-code (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 60 tokens to every session and 543 once invoked, about $0.0003 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
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.