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/backchainai/backchain-plugins/briefnpx skills add backchainai/backchain-plugins --skill briefgit clone --depth 1 https://github.com/backchainai/backchain-pluginsWhat 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 | $0.00165 | $0.04572 |
| Opus 5 | $0.00082 | $0.02286 |
| Sonnet 5 | $0.00033 | $0.00914 |
| Haiku 4.5 | $0.00016 | $0.00457 |
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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brief
Produce an interactive HTML brief as the medium for an intermediate operator-agent discussion. The brief is a single self-contained .html file. Where the artifact has decisions to make, it carries inline controls (radios, checkboxes, sliders, free-text fields). Whether or not it has decisions, it always ends with a sticky "Copy execution prompt" button: the operator reviews the artifact, optionally commits to choices and notes, and pastes a clean execution prompt into a fresh context window where another agent acts on it.
The pattern exists because plans, specs, design explorations, annotated diffs, decision matrices, and navigable reports are spatial information that markdown flattens. HTML preserves dimensionality (side-by-side comparison, collapsible detail, jump links, tabs, swatches, severity tags) and lets the operator interact with the artifact (toggle options, expand sections, scrub a slider) before the next agent runs. The export-button feedback loop is the second half of the pattern: whatever the operator did in the UI returns to the agent as a focused prompt, instead of leaving ambiguity in prose.
When this skill applies
This skill is the default format for any intermediate operator-agent discussion artifact. The pattern's value is spatial layout, interactivity, and the export-button feedback loop into the next prompt. Trigger whenever any of these are true:
- Intermediate discussion document. The artifact is a plan, spec, draft proposal, design exploration, decision matrix, annotated review, recommendation, or report the operator will read carefully and discuss before acting on it.
- Forkable decisions. The work has multiple options that are easier grasped side-by-side than described in prose, and the operator will commit to specific choices.
- Spatial information. The content is structural and markdown would flatten it: design tokens as swatches, diffs with margin notes and severity tags, architecture or call-graph layouts, comparison tables that benefit from interaction.
- Navigable scaffolding. The operator wants collapsible sections, tabs, jump links, or side-by-side comparison rather than linear top-to-bottom reading.
- Follow-on prompt. The next step is a fresh context window, so the artifact must produce a prompt that stands alone.
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 · 227 lines · 165 tokens per session scan A aa00baf160df
brief is a skill published in the GitHub repository backchainai/backchain-plugins (4 stars, last pushed 27d ago), licensed Apache-2.0. It adds 165 tokens to every session and 4,572 once invoked, about $0.0008 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
kayba-stage-3-metrics
Define metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful. Trigger when the user says "run stage 3", "define metrics", "build metrics", "compute baselines", or when invoked by the kayba-pipeline orchestrator. Requires…
kayba-stage-5-action-plan
Triage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations. Trigger when the user says "run stage 5", "make action plan", "triage skills", or when invoked by the kayba-pipeline orchestrator. Requires eval outputs from stages 1-4.
kayba-stage-6-hitl
Human-In-The-Loop gate that presents the action plan with full context, collects an informed approval/modification/rejection decision, and records the outcome. Trigger when the user says "run stage 6", "HITL review", "approve action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md…
kayba-pipeline
End-to-end agent evaluation and improvement pipeline. Takes a traces folder and optional HITL flag, then orchestrates sub-agents through 7 stages — each stage is its own skill invoked by a dedicated sub-agent. Trigger when the user says "run the pipeline", "kayba pipeline", "evaluate and fix", "full eval", "analyze…
kayba-stage-2-domain-context
Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. Trigger when the user says "run stage 2", "gather context", "domain context", or when invoked by the kayba-pipeline orchestrator.
kayba-stage-7-fixer
Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.