agentmods.dev

capability-discovery

capability-discovery is a skill for Claude Code from synaptiai/synapti-marketplace. It costs 77 tokens per session (1,078 once invoked), scanned A, original, Apache-2.0.

A scan of the project and environment to find available agents, skills, commands, quality checks, and code-intelligence tools.

In plain words
What is it for?
Use it when starting implementation, creating or reviewing pull requests, or responding to review feedback.
Why use it?
It prevents an agent from assuming that a tool exists or overlooking a useful way to inspect or verify the work.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the flow plugin — 32 skills, 21 commands, 9 agents shipped together

not rated 6repo changed today A scan 77 tokens original Apache-2.0

Good fit Use it when starting implementation, creating or reviewing pull requests, or responding to review feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synaptiai/synapti-marketplace/capability-discovery
View source ↗ synaptiai/synapti-marketplace
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/synapti-marketplace --skill capability-discovery
Clone the repo
git clone --depth 1 https://github.com/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 32 skills, 21 commands, 9 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-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/capability-discovery/github.svg)](https://agentmods.dev/skills/synaptiai/synapti-marketplace/capability-discovery)
Your own site
<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/capability-discovery"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/capability-discovery/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.

agentmods 80×15 button for capability-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/capability-discovery"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/capability-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,078 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 $0.00077 $0.01078
Opus 5 $0.00039 $0.00539
Sonnet 5 $0.00015 $0.00216
Haiku 4.5 $0.00008 $0.00108

Measured today against content hash 5a7ec1980cc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

capability-discovery 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.

plugins/flow/skills/capability-discovery/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capability Discovery

Contract

Iron law: discover before assuming — never hardcode tool availability; scan the environment first. Invoked once per command run, before any quality or verification phase: /flow:start Phase 1, /flow:pr pre-flight, /flow:address before verification, /flow:resolve step 1c, /flow:setup Phase 1, /flow:design and /flow:brainstorm EXPLORE, and the test-runner agent. Returns the six-section markdown report below (Agents Available, Skills Available, Quality Commands, Tech Stack, Verification Capabilities, LSP Capabilities). The calling command stores the output for later phases and does not re-invoke it within the same run. Permitted skips: the markdown-only early exit (no tech-stack file and no quality commands in CLAUDE.md) and LSP probing when lsp.enabled is false.

Detection Order

Steps 1-5 are independent — run them simultaneously with parallel tool calls.

  1. Agents: Glob ".claude/agents/*.md" (project) and "plugins/*/agents/*.md" (plugin); parse source, name (filename without .md), description (frontmatter).

  2. Skills: Glob ".claude/skills/*/SKILL.md" and "plugins/*/skills/*/SKILL.md"; parse source, name (parent directory), description.

  3. Commands: Glob ".claude/commands/*.md" and "plugins/*/commands/*.md"; parse source, name, description.

  4. Quality commands from CLAUDE.md — .claude/CLAUDE.md first, then CLAUDE.md:

    grep -E "(npm|pnpm|yarn|bun|ruff|pytest|go |cargo |make )" "$CLAUDE_MD"

  5. Tech stack by indicator file: package.json → node, tsconfig.json → typescript, pyproject.toml → python, Gemfile → ruby, go.mod → go, Cargo.toml → rust, Makefile → makefile.

Early exit — markdown-only: no tech-stack file AND no quality commands in CLAUDE.md → report Quality Commands "No code-related quality commands applicable", Tech Stack "Markdown-only project", skip Step 6.

  1. Verification capabilities: ls verify.sh scripts/verify* playwright.config.* cypress.config.* 2>/dev/null.
  2. LSP capabilities: pre-check lsp.enabled (default true; if false, report every feature Disabled). Probe documentSymbol, hover, goToDefinition, findReferences, goToImplementation against one representative source file for the detected stack, each bounded by lsp.timeout (default 5000 ms); infer diagnostics Available when documentSymbol succeeds. Procedure and result rules: references/lsp-capability-probes.md.

Read the full file on GitHub · 74 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. today Changed · -85 lines 5a7ec1980cc9
  2. 7d ago First seen · 159 lines · 77 tokens per session scan A 0035aae82ca0

Subscribe to this mod's changes

capability-discovery is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 1,078 once invoked, about $0.0004 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 2026-09-03.

Building agentsagentic-design-patternsagentic-developmentagentic-workflowai-developer-toolsai-firstclaude-code-plugin
Related

Other skills, from other repositories

create-or-update-concepts

Scan and analyze the project codebase to create or update concept files in agents-context/concepts/ (organized by domains/, source/, shared/) and update the README index and Load-When Cheatsheet.

CaptainMe-AI/lead-dev-os · 46 tokens

step2-scope-tasks

Break a specification into ordered task groups with explicit context-awareness directives.

CaptainMe-AI/lead-dev-os · 20 tokens

step1-write-spec

Gather requirements through structured Q&A, then formalize into a specification document.

CaptainMe-AI/lead-dev-os · 20 tokens

create-pr

Creates a GitHub Pull Request on the current branch with a description focused on WHAT changed (not HOW). Uses emojis in the title and description. Use when the user asks to create a PR, open a pull request, or submit changes for review. Triggers on mentions of PR, pull request, merge request, or code review.

CaptainMe-AI/lead-dev-os · 70 tokens

step4-archive-spec

Archive a completed spec — moves it to specs-archived and blocks agent access.

CaptainMe-AI/lead-dev-os · 23 tokens

plan-product

Define product mission, vision, target users, and technology stack.

CaptainMe-AI/lead-dev-os · 16 tokens