Brief
A filesystem-first, runtime-neutral operating system for agent-assisted work.
npx -y skills add aylee/agent-os --skill briefAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Write or revise a concise project brief or one-pager. Use when the user asks for stakeholder alignment, a proposal, a one-page brief, or an edit to an existing brief artifact.
SKILL.md
1.3 KB, 244 tokens by cl100k_base, as published. Nobody here has run it
Brief
Produce a decision-ready brief, not a transcript of the work that led to it.
- Resolve the owner binder. Read its
BINDER.md, linked active workstream, relevant area context, andlibrary/reference/me.mdwhen voice matters. - Inspect
library/templates/brief.md. Reuse its structure only where each section earns its place. - Establish audience, decision or outcome, evidence, constraints, scope, risks, and next step. Ask only for material facts that cannot be discovered.
- For an existing file, preserve settled facts and edit in place. For a new file, write it inside the owner binder with a descriptive filename.
- Keep execution state in the linked
WORKSTREAM.md; do not duplicate status logs in the brief. - After writing, summarize what changed, unresolved questions, and the artifact path. Do not create a receipt for the document edit.
If the work changes current execution state, update the linked workstream separately and create a receipt only for that workstream revision transition.
Do not invent links, metrics, quotations, or stakeholder positions. Do not commit or publish unless the user separately asks.
What ships with it: 2 files
532 B alongside SKILL.md
agents/
- agent-os.yaml301 B
- openai.yaml231 B
Gives 0 of the 12 instructions most plan spec skills give in 244 tokens
Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07
- Ask one question at a timein 51 of 1099
- Break plans into vertical slicesin 29 of 1099, across 11 files
- Publish issues in dependency orderin 27 of 1099, across 9 files
- Iterate until user approves the breakdownin 25 of 1099, across 7 files
- Explore the repository to understand the codebase statein 24 of 1099, across 7 files
- Use domain glossary vocabularyin 23 of 1099, across 5 files
- Apply correct triage labels to published issuesin 23 of 1099, across 5 files
- Prefer AFK slices over HITLin 22 of 1099, across 7 files
- Write a specification before writing any codein 22 of 1099, across 14 files
- Write failing tests before implementation codein 22 of 1099, across 20 files
- Ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
- Respect existing architecture decision recordsin 20 of 1099, across 5 files
Said here and by no other author read
- Produce a decision-ready brief, not a transcript.
- Resolve and read the owner binder.
- Reuse the brief template structure only where needed.
- Ask only for undiscoverable material facts.
- Preserve settled facts when editing an existing brief.
- Write new briefs inside the owner binder.
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.