capability-synthesizer

capability-synthesizer is an agent for Claude Code from spacelift-io/claude-plugins. It costs 26 tokens per session (288 once invoked), scanned A, original, MIT.

An agent that maps an infrastructure governance goal to the right Spacelift policy types. Governance here means deciding who may act, what may run, what must be blocked, and what should be reported.

In plain words
What is it for?
Choosing policy types, rule results, input paths, composition order, and unresolved questions before someone writes the Rego policy.
Why use it?
It helps turn a broad control requirement into the smallest set of policy stages and decisions needed. It also identifies how multiple policies pass information between one another.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the spacelift plugin — 2 skills, 2 agents shipped together

Install

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.

agentmods
npx agentmods add agents/spacelift-io/claude-plugins/capability-synthesizer
Clone the repo
git clone --depth 1 https://github.com/spacelift-io/claude-plugins

Made for: Claude Code.

Or install spacelift, the plugin that ships this one along with the rest of its 2 skills, 2 agents.

Wrote 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.

agentmods badge for capability-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/spacelift-io/claude-plugins/capability-synthesizer.svg)](https://agentmods.dev/agents/spacelift-io/claude-plugins/capability-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/spacelift-io/claude-plugins/capability-synthesizer"><img src="https://agentmods.dev/badge/agents/spacelift-io/claude-plugins/capability-synthesizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 288 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00288
Opus 5 $0.00013 $0.00144
Sonnet 5 $0.00005 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 5d ago against content hash 0bd3647c8e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

capability-synthesizer 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 5d 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.

plugins/spacelift/skills/spacelift-policy-writer/agents/capability-synthesizer.md · 25 lines

What it actually says

Capability Synthesizer

You map a user's governance goal to the Spacelift policy type(s) that achieve it and how they compose. Name the mechanism - do not write full Rego here.

References (relative to the skill root):

  • guides/policy-types.md - all 8 types by lifecycle stage + composition rules
  • references/policy-contract.md - authoritative input paths and rule outputs

Method:

  1. Restate the goal as lifecycle events: who acts, what triggers a run, what must be blocked/allowed/reported.
  2. Pick the minimal set of types from guides/policy-types.md - prefer one; add more only when the goal spans stages.
  3. For each type, name the exact rule outputs and key input paths from the contract - never guess field names.
  4. State composition order and any cross-policy data flow (flags, receipts, trigger fan-out - guides/flags-and-interaction.md).

Output shape:

  • Goal: one line
  • Policies: TYPE - rule outputs used - one-line role
  • Composition: 2-4 bullets on how they chain
  • Open questions: ambiguities to confirm before writing Rego
Changes

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.

  1. 5d ago First seen · 25 lines · 26 tokens per session scan A 0bd3647c8e74

Subscribe to this mod's changes

capability-synthesizer is an agent published in the GitHub repository spacelift-io/claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 288 once invoked, about $0.0001 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.