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/razi2001/brief/skillnpx skills add razi2001/brief --skill skillgit clone --depth 1 https://github.com/razi2001/briefWhat 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 | $0.00111 | $0.01512 |
| Opus 5 | $0.00056 | $0.00756 |
| Sonnet 5 | $0.00022 | $0.00302 |
| Haiku 4.5 | $0.00011 | $0.00151 |
Grade A, and why
brief 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brief — Router
Briefs are captured locally and stored in ~/Downloads/brief/. Each is either:
- a
.zipfile (brief-<id>.zip) — yet-to-be-extracted - a folder (
brief-<id>/) after extraction
A brief can contain any combination of these (check brief.json to see which):
- A recording —
recording.webm+ sampledkeyframes/*.png+ a voicetranscript. (Recording briefs.) - An annotated screenshot —
screenshot.png. Any red markings on it were drawn by the user to point at where the issue is. Treat the red as the focus indicator, not as part of the page UI. (brief.json.hasScreenshot/screenshotAnnotated.) - A text description —
brief.json.description, the user's own words about the issue.
So a brief might be a full recording, OR just a screenshot with a red circle, OR just a sentence of text, OR a mix. Use whatever is present. Never assume a recording exists — read brief.json first.
Briefs only exist for one purpose: to become Linear/Jira/GitHub/Notion tickets. Your job is to file the ticket — efficiently, without unnecessary questions — and then clean up.
Step 1 — Identify the action
The user's prompt will be one sentence containing one of:
| User says… | Load |
|---|---|
| "process my inbox" / "briefs X, Y, Z" | playbooks/inbox.md |
| "turn brief X into a ticket" (or similar) | playbooks/ticket.md |
If the prompt names multiple brief IDs or contains the word "inbox", use inbox.md — that playbook orchestrates the others. Otherwise use ticket.md.
Step 2 — Read the playbook
The playbooks live next to this file, in the same skill/playbooks/ folder inside the brief. Load the matching one (skill/playbooks/<name>.md) and follow it. It contains all the rules: how to read the brief files, how to handle screenshots/recordings/text, how to infer the team/repo, how to embed images inline, etc.
What ships with it
2 files 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 · 75 lines · 0 tokens per session scan A 8afcc427e344
brief is a skill published in the GitHub repository razi2001/brief (21 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 1,512 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
linear-cli
Manage Linear issues from the command line using the linear cli. This skill allows automating linear management.
linear
Read Linear issues, transition state, and post comments. The entry point for ticket-driven agent workflows.
linearis
Manage Linear.app work from the command line with the linearis CLI (bins linearis / linear), which outputs JSON: issues/tickets, projects, cycles (sprints), milestones, initiatives (roadmap), documents, labels, teams, users, and issue discussions/comments. Use when the user mentions Linear, a ticket identifier like…
finn-build
Claim the next safe agent-ready issue from Linear, implement it, and open a PR. Use when asked to run Finn-loop's builder, work the approved queue, or fix Finn-loop review feedback. Designed for /loop; one pass does one unit of work.
finn-review
Review open PRs against their linked Linear issues and required GitHub checks, then post a three-group verdict with Finn-loop labels. Use when asked to run Finn-loop's reviewer or review its PR queue. Designed for /loop; never merges or pushes code.
linear
Manage Linear issues. Use when asked about tasks, tickets, bugs, or Linear.