discover-capabilities

discover-capabilities is a skill for Claude Code from synaptiai/agent-capability-standard. It costs 50 tokens per session (1,803 once invoked), scanned A, original, Apache-2.0.

A task-analysis tool that matches a plain-language request to known capabilities, points out missing ones, and builds an ordered workflow. A capability is a specific ability needed to complete part of a task.

In plain words
What is it for?
Use it to analyze a task, find the abilities it requires, identify gaps, and create a safe workflow with evidence for each decision.
Why use it?
It removes the guesswork from turning a broad request into concrete steps. It also shows where the available capabilities do not cover the task.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Part of the agent-capability-standard plugin — 42 skills, 2 hooks shipped together

Good fit Use it to analyze a task, find the abilities it requires, identify gaps, and create a safe workflow with evidence for each decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synaptiai/agent-capability-standard/discover-capabilities
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.

Any agent
npx skills add synaptiai/agent-capability-standard --skill discover-capabilities
Clone the repo
git clone --depth 1 https://github.com/synaptiai/agent-capability-standard

Made for: Claude Code.

Or install agent-capability-standard, the plugin that ships this one along with the rest of its 42 skills, 2 hooks.

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 discover-capabilities

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/discover-capabilities.svg)](https://agentmods.dev/skills/synaptiai/agent-capability-standard/discover-capabilities)
Your own site
<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/discover-capabilities"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/discover-capabilities.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00050 $0.01803
Opus 5 $0.00025 $0.00901
Sonnet 5 $0.00010 $0.00361
Haiku 4.5 $0.00005 $0.00180

Measured 8d ago against content hash ac4dada49106, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

discover-capabilities 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 8d 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.

skills/discover-capabilities/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent

Execute discover-capabilities to analyze a natural language task description and automatically:

  1. Detect which ontology capabilities are needed
  2. Identify gaps where the ontology lacks coverage
  3. Synthesize a valid workflow DAG from matched capabilities

This skill bridges the gap between "I want to do X" and "here are the specific capabilities and workflow steps needed to do X safely."

Success criteria:

  • All atomic actions in the task are identified
  • Each action maps to an ontology capability with confidence score
  • Missing capabilities are flagged with proposed extensions
  • A valid workflow is synthesized with proper safety steps
  • Evidence anchors trace the discovery reasoning

Compatible schemas:

  • schemas/capability_ontology.yaml
  • schemas/workflow_catalog.yaml

Inputs

Parameter Required Type Description
task_description Yes string Natural language description of the task to analyze
domain No string Domain context for specialization (e.g., "security", "data-pipeline")

Procedure

  1. Load ontology context: Read the capability ontology to understand available capabilities

    • Load schemas/capability_ontology.yaml via CapabilityRegistry
    • Load schemas/workflow_catalog.yaml via WorkflowEngine
    • Note: 36 atomic capabilities across 9 cognitive layers
  2. Analyze task: Decompose the task into atomic capability requirements

    • Parse the task description for action verbs and targets
    • Map each action to the closest ontology capability
    • Assign confidence scores based on semantic match quality
    • Identify domain parameters where applicable
  3. Classify matches: Validate and filter capability matches

    • Accept matches with confidence >= 0.6
    • Route low-confidence matches to gap detection
    • Identify unmatched requirements
  4. Detect gaps: For unmatched requirements

    • Find nearest existing capabilities by semantic similarity
    • If available, generate proposed new capabilities with:
      • Suggested layer, risk level, and schemas
      • Edges to related existing capabilities
      • Rationale for the proposal

Read the full file on GitHub · 246 lines

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. 8d ago First seen · 246 lines · 50 tokens per session scan A ac4dada49106

Subscribe to this mod's changes

discover-capabilities is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 8d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,803 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

gh

GitHub API access and project management automation for the hallucination-detector repo. Uses octokit with proxy-aware client for all GitHub operations — issues, PRs, labels, milestones, Projects V2. No gh CLI required.

bitflight-devops/hallucination-detector · 49 tokens

evaluate-options

Research and evaluate implementation options before presenting a recommendation. Use when multiple approaches exist for a problem and a decision is needed. Launches one background research agent per option in parallel, collects evidence-backed findings, then presents a recommendation grounded in observed data — not…

bitflight-devops/hallucination-detector · 97 tokens

delegate

Quick delegation template for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Task tool, or when preparing prompts for specialized agents. Provides the WHERE-WHAT-WHY framework. For comprehensive delegation guidance, activate the agent-orchestration how-to-delegate skill.

bitflight-devops/hallucination-detector · 60 tokens

beginner-tone

A set of Korean-language conversation and safety instructions for people new to coding and AI. It tells the assistant to explain difficult terms and guide the user with one clear next action.

sodam-ai/SoDam-Harness-Eng · 34 tokens

sodam-harness-self-check

A self-checking instruction set for an AI agent. It tells the agent to verify important work, show evidence, and clearly disclose anything it could not check.

sodam-ai/SoDam-Harness-Eng · 51 tokens

sodam-harness-beginner-tone

A short note saying this add-on has been merged into another beginner-focused writing guide.

sodam-ai/SoDam-Harness-Eng · 25 tokens