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 isvlasov/rageatc-oss --skill creating-briefsgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/creating-briefs)<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/creating-briefs"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/creating-briefs/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/isvlasov/rageatc-oss/creating-briefs"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/creating-briefs.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 | $0.00036 | $0.01124 |
| Opus 5 | $0.00018 | $0.00562 |
| Sonnet 5 | $0.00007 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
creating-briefs 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 10d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Briefs
A brief transforms an unstructured request into a bounded, verifiable specification that the executing agent can work from without clarification questions — and that the requester can read and say "yes, this is what I meant". Briefing is orchestrator-owned: it depends on the full conversation context, so write the brief yourself rather than delegating it.
Skip when the task is trivial, already well-specified, or purely exploratory with undefined outcomes.
Principles
- Outcomes, not solutions — define WHAT to achieve, let the executor determine HOW. Prescribe method only when a real constraint requires it.
- Context is never assumed — the executor hasn't read the conversation, previous work, or project history. If background matters, state it in the brief.
- Fit for purpose AND audience — name who will use the deliverable; it shapes requirements and tone.
Workflow
1. Clarify the request
Extract: core intent (the outcome behind the literal words), purpose (WHY it matters — without it the executor can do technically correct work that serves the wrong goal), scope boundaries, audience, and any assumptions you're making. If critical information is missing, ask targeted questions — don't guess.
2. Identify applicable standards
The 1–3 skills or guides that govern quality for this artefact type: writing-skills for skills, conducting-research for research, style guides for documents. Multiple standards can apply to one brief.
3. Extract requirements
The core step — it creates the shared quality expectations that the executor works to and the critic reviews against. From each standard, select the 5–12 requirements that apply to this task (not all of them), rephrase for clarity if needed, and structure as verifiable checkboxes grouped by source standard. Vague aspirations ("must be good quality") are not requirements.
4. Set constraints
3–6 scope limits: format, length, dependencies, explicit exclusions. More than that suggests the scope itself is unclear.
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.
- 10d ago First seen · 107 lines · 36 tokens per session scan A 02ca1508c953
creating-briefs is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,124 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
design-method
Use when starting any design task — resolves register, sets the 3 dials, locks Gate 0, and routes to the right move and target skill.
design-webapp
Use when building or extending a dashboard, SaaS screen, or any authenticated app surface — use design-web instead for a marketing site.
design-web
Use when building or revising a marketing/landing/campaign page, register brand locked at Gate 0 — use design-webapp for app screens instead.
react-tanstack-router
Use when implementing routing in a React app (NOT Next.js) with TanStack Router — file-based routes, loaders, search params.
git-flow
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
fusecore
Use when creating modules, understanding FuseCore structure, or implementing features in a FuseCore modular-monolith Laravel project.