autospec.specify

autospec.specify is a command for Claude Code from ariel-frischer/autospec. It costs 9 tokens per session (2,143 once invoked), scanned A, original, MIT.

A command that turns a plain-language feature description into a YAML specification, a structured text file describing the feature, and starts related feature work.

In plain words
What is it for?
Use it with a feature request to create a short feature name, a feature branch and directory, and a YAML description of the requested work.
Why use it?
It gives an informal request a consistent written shape before implementation begins. This makes the intended feature easier to review and use during development.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it with a feature request to create a short feature name, a feature branch and directory, and a YAML description of the requested work.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ariel-frischer/autospec/autospec.specify
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.

Clone the repo
git clone --depth 1 https://github.com/ariel-frischer/autospec

Made for: Claude Code.

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 autospec.specify

README.md
[![agentmods](https://agentmods.dev/badge/commands/ariel-frischer/autospec/autospec.specify/github.svg)](https://agentmods.dev/commands/ariel-frischer/autospec/autospec.specify)
Your own site
<a href="https://agentmods.dev/commands/ariel-frischer/autospec/autospec.specify"><img src="https://agentmods.dev/badge/commands/ariel-frischer/autospec/autospec.specify/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 autospec.specify

Your own site · 80×15
<a href="https://agentmods.dev/commands/ariel-frischer/autospec/autospec.specify"><img src="https://agentmods.dev/badge/commands/ariel-frischer/autospec/autospec.specify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,143 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 $0.00009 $0.02143
Opus 5 $0.00005 $0.01071
Sonnet 5 $0.00002 $0.00429
Haiku 4.5 $0.00001 $0.00214

Measured 9d ago against content hash d5a79be501a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

autospec.specify 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 9d 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.

internal/cli/admin/.claude/commands/autospec.specify.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Outline

The text the user typed after /autospec.specify in the triggering message is the feature description. Assume you always have it available in this conversation even if $ARGUMENTS appears literally below. Do not ask the user to repeat it unless they provided an empty command.

Given that feature description, do this:

  1. Generate a concise short name (2-4 words) for the branch:

    • Analyze the feature description and extract the most meaningful keywords
    • Create a 2-4 word short name that captures the essence of the feature
    • Use action-noun format when possible (e.g., "add-user-auth", "fix-payment-bug")
    • Preserve technical terms and acronyms (OAuth2, API, JWT, etc.)
    • Keep it concise but descriptive enough to understand the feature at a glance
    • Examples:
      • "I want to add user authentication" → "user-auth"
      • "Implement OAuth2 integration for the API" → "oauth2-api-integration"
      • "Create a dashboard for analytics" → "analytics-dashboard"
      • "Fix payment processing timeout bug" → "fix-payment-timeout"
  2. Create feature branch and directory: Run the Go command with your generated short-name:

    autospec new-feature --json --short-name "<short-name>" "$ARGUMENTS"
    

    Parse the JSON output for:

    • BRANCH_NAME: The full branch name (e.g., "008-user-auth")
    • SPEC_FILE: Path to the spec file (ignore - we'll create spec.yaml instead)
    • FEATURE_NUM: The feature number
    • AUTOSPEC_VERSION: The autospec version (for _meta section)
    • CREATED_DATE: ISO 8601 timestamp (for _meta section)

    Set FEATURE_DIR to specs/<BRANCH_NAME>/

  3. Generate spec.yaml: Create the YAML specification file with this exact structure.

    Schema reference: Run autospec artifact spec --schema to see the full schema if unsure.

    # ============ REQUIRED SECTIONS ============
    
    feature:                    # REQUIRED section
      branch: "<branch name from step 2>"      # REQUIRED
      created: "<today's date YYYY-MM-DD>"     # REQUIRED
      status: "Draft"           # REQUIRED enum: Draft|Review|Approved|Completed
      input: "<original user description verbatim>"  # optional
    
    user_stories:               # REQUIRED section (array, at least one item)
      - id: "US-001"            # REQUIRED
        title: "<story title>"  # REQUIRED
        priority: "P1"          # REQUIRED enum: P0|P1|P2|P3 (P0=critical, P1=must-have, P2=should-have, P3=nice-to-have)
        as_a: "<role/actor>"    # REQUIRED
        i_want: "<action/capability>"   # REQUIRED
        so_that: "<benefit/value>"      # REQUIRED
        why_this_priority: "<justification for priority level>"  # optional
        independent_test: "<how this story can be tested in isolation>"  # optional
        acceptance_scenarios:   # optional (but recommended)
          - given: "<precondition/context>"
            when: "<action taken>"
            then: "<expected outcome>"
    
    requirements:               # REQUIRED section
      functional:               # REQUIRED (array)
        - id: "FR-001"
          description: "<MUST/SHOULD/MAY + requirement>"
          acceptance_criteria: "<how to verify this>"
      non_functional:           # optional (array)
        - id: "NFR-001"
          category: "<performance|security|usability|reliability|code_quality>"
          description: "<requirement>"
          measurable_target: "<specific metric>"
    
    # ============ OPTIONAL SECTIONS ============
    
    success_criteria:           # optional
      measurable_outcomes:
        - id: "SC-001"
          description: "<user-focused, measurable outcome>"
          metric: "<how to measure>"
          target: "<specific value or threshold>"
    
    key_entities:               # optional
      - name: "<entity name>"
        description: "<what this entity represents>"
        attributes:
          - "<key attribute 1>"
          - "<key attribute 2>"
    
    edge_cases:                 # optional
      - scenario: "<edge case description>"
        expected_behavior: "<what should happen>"
    
    assumptions:                # optional
      - "<assumption 1>"
      - "<assumption 2>"
    
    constraints:                # optional
      - "<constraint 1>"
      - "<constraint 2>"
    
    out_of_scope:               # optional
      - "<explicitly excluded item 1>"
      - "<explicitly excluded item 2>"
    
    _meta:                      # optional (but recommended)
      version: "1.0.0"
      generator: "autospec"
      generator_version: "<AUTOSPEC_VERSION from step 2>"
      created: "<CREATED_DATE from step 2>"
      artifact_type: "spec"
    

Read the full file on GitHub · 219 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. 9d ago First seen · 219 lines · 9 tokens per session scan A d5a79be501a6

Subscribe to this mod's changes

autospec.specify is a command published in the GitHub repository ariel-frischer/autospec (141 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 2,143 once invoked, about $0.0000 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 2026-08-30.