capability-audit

A local MCP server for Laravel Artisan, the command-line tool used to manage Laravel PHP applications.

In plain words
What is it for?
Use it when a project needs this locally configured Laravel Artisan MCP server, but the supplied information does not specify which tasks it supports.
Why use it?
The input only identifies the server and how it is launched; it does not describe the specific operations it provides.

Skill for Claude CodeCodex

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 skills/codeinfinity1/stram/capability-audit
Any agent
npx skills add CodeInfinity1/Stram --skill capability-audit
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 634 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 $0.00049 $0.00634
Opus 5 $0.00024 $0.00317
Sonnet 5 $0.00010 $0.00127
Haiku 4.5 $0.00005 $0.00063

Measured yesterday against content hash 00306fb450b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capability-audit 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 yesterday.

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/agent-core/capability-audit/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capability Audit

Purpose

Give the user and model an evidence-backed map of what the assistant can actually do now. This skill adapts external reference agent audit patterns to Stram's capability surface and plugin catalogs.

When To Use

Use before large architecture changes, after adding tools/skills/plugins, when debugging "is this wired?", or when choosing the next integration batch.

Inputs And Evidence

  • capability_surface records.
  • Tool catalog and descriptions.
  • Workspace skill catalog and memory skills.
  • Per-skill capability audit matrix.
  • Plugin and channel catalogs.
  • Provider readiness for OpenAI, Groq, Ollama, voice, browser, and OS tools.
  • Recent smoke test artifacts.

Tool Map

  • capability_surface
  • tool_search
  • tool_describe
  • agent_skill_catalog
  • agent_skill_capability_audit
  • plugin_catalog
  • channel_catalog
  • voice_provider_status
  • external_integrations_status
  • system_status

Workflow

  1. Gather the current capability surface with records included when useful.
  2. Run agent_skill_capability_audit when the question includes skill completeness, prompt-only skills, live readiness, or smoke coverage.
  3. Count tools, skills, channels, providers, plugins, and notable missing surfaces.
  4. Verify readiness for local services and cloud providers before claiming availability.
  5. Compare current capabilities to the user's requested architecture or shortlist.
  6. Identify gaps as missing, partially wired, untested, blocked by credentials, or blocked by policy.
  7. Recommend the next implementation batch with verification steps.

Safety

  • Do not claim a provider is usable because config exists; use status or smoke evidence.
  • Do not treat catalog declarations as direct execution support.
  • Keep external secrets redacted.

Native Implementation Boundaries

  • Use capability_surface, tool_search, tool_describe, catalogs, and status tools as authoritative current-state inputs.
  • Use agent_skill_capability_audit for skill implementation status; do not classify skills from informal names or reference repos.
  • Report live readiness separately from native local support when credentials, CLIs, local models, or network access are unavailable.

Read the full file on GitHub · 79 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. yesterday First seen · 79 lines · 49 tokens per session scan A 00306fb450b6

Subscribe to this mod's changes

capability-audit is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 49 tokens to every session and 634 once invoked, about $0.0002 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.