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 AdamBien/airails --skill system-briefgit clone --depth 1 https://github.com/AdamBien/airailsWrote 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/adambien/airails/system-brief)<a href="https://agentmods.dev/skills/adambien/airails/system-brief"><img src="https://agentmods.dev/badge/skills/adambien/airails/system-brief/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/adambien/airails/system-brief"><img src="https://agentmods.dev/badge/skills/adambien/airails/system-brief.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 | $0.00355 | $0.03501 |
| Opus 5.5 | $0.00142 | $0.01400 |
| Sonnet 5.5 | $0.00071 | $0.00700 |
| Haiku 4.5 | $0.00036 | $0.00350 |
Grade A, and why
system-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 today.
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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce a system brief: one filled template that answers every question /capability-brief
and /sbce new would otherwise ask about the system as a whole — what it is for, who uses it,
which capabilities it consists of and where each one ends. The stakeholder conversation that
usually happens in fragments across the first ten capability interviews is moved here, to the one
moment all stakeholders are present, and its answers are recorded once.
The brief is stack-neutral: why the system exists and which capabilities it needs, never how any capability works or how the system is built. No operations, inputs, screens, types, transports, frameworks, or file names. A capability's inside belongs to its own brief; the stack belongs to the stack skill. A system brief that names either binds the carving to a solution before the capabilities exist.
Two guarantees, one of them yours
- Structural completeness is yours to enforce. Every section filled, every capability one word with one sentence and a named actor, every actor in at least one capability, every shared noun defined once, no overlapping responsibilities left unacknowledged. The checklist below makes this mechanical; do not emit a brief that fails it.
- Semantic completeness is the stakeholders'. Where one capability ends and the next begins, what the system will never do, which capability comes first, what was rejected and why — these are business facts. You cannot invent them; you can only ask until they are answered or honestly parked under
## Open issues. A guessed carving becomes a business component, then a package, then a team boundary that nobody chose.
Invocation modes: new · review
Read the mode and the input from the invocation: /system-brief new "<description>",
/system-brief review <file-or-pasted-text>. With the mode omitted, review when the input is
already a system brief (recognisable by its ## System … ## Open issues sections), else new.
| Mode | When |
|---|---|
new |
a system that does not exist yet, or an existing system with no system brief and no system doc |
review |
an existing system brief to check, or existing text — a pitch, notes, a product requirements document — to complete into a brief |
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.
- today First seen · 118 lines · 355 tokens per session scan A b47d4fa8ec69
system-brief is a skill published in the GitHub repository AdamBien/airails (60 stars, last pushed yesterday), licensed MIT. It adds 355 tokens to every session and 3,501 once invoked, about $0.0014 per session on Opus 5.5. 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 2026-10-29.
Other skills, from other repositories
iterate-prd
Only use when the user explicitly invokes this skill by name.
feature-requirements
Turn the ticket into requirements and CUJs, and stop with a split proposal when it is too big.
orchestrate
Toolbox for driving HumanLayer from the CLI - log in, pick a host, launch tasks in their own worktrees, launch sessions, list tasks and their PRs, and copy, move, or upload task artifacts.
jira-release
Assemble a release from a batch of Jira issues — one release branch, pull request, preview and tracking issue per repository — and, when a person says to ship it, merge it and move the cards on. Insert into the prompt of a run started on a batch of issues.
github-operations
GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…