add-spec

Add implementation spec to existing PRD folder.

Command for Claude Code

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 commands/jnarowski/agentcmd/add-spec
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,925 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00008 $0.01925
Opus 5 $0.00004 $0.00962
Sonnet 5 $0.00002 $0.00385
Haiku 4.5 $0.00001 $0.00193

Measured today against content hash 4f595e490482, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-spec 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.

.claude/commands/cmd/add-spec.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Spec to Existing Folder

Adds an implementation spec (feature/bug/issue) to an existing spec folder that contains a PRD. Routes to the appropriate generate command with context.

Variables

  • $param1: $1 (required) - 10-digit spec ID of existing folder (e.g., 2511131522)

Instructions

  • IMPORTANT: This is a ROUTER command - it does NOT generate specs itself
  • IMPORTANT: Read the appropriate generate command instructions and follow them exactly
  • This command adds a spec to a folder that already has a PRD (or empty folder)
  • Auto-detects spec type from conversation context (feature/bug/issue)
  • References existing PRD content if available for better accuracy
  • Routes to: generate-feature-spec, generate-bug-spec, or generate-issue-spec

Workflow

  1. Validate Spec ID:

    • Verify $param1 is a 10-digit number matching format YYMMDDHHmm
    • If invalid format: Show error and exit
    • Example valid: 2511131522
    • Example invalid: 123 (too short), abc (not numeric)
  2. Read Index and Verify Folder:

    • Read .agent/specs/index.json
    • Look up entry with key matching $param1
    • If not found: Show error listing available spec IDs and exit
    • Extract folder path from entry
    • Verify folder exists at .agent/specs/{folder}
    • If folder doesn't exist: Show error and exit
  3. Check for Existing Spec:

    • Check if entry has path field in index.json
    • If path field exists and points to spec.md: Show error "Spec already exists at {path}" and exit
    • This prevents overwriting existing specs
  4. Read Existing PRD (if present):

    • Check if prd.md exists in folder
    • If exists: Read prd.md content to use as additional context
    • If not: Continue without PRD context
  5. Detect Spec Type:

    • Analyze conversation history and PRD content (if available)
    • Determine if this is a:
      • feature: New functionality, enhancement, or major change
      • bug: Fixing broken behavior, errors, or unexpected results
      • issue: Small task, minor fix, or simple change

Read the full file on GitHub · 208 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 First seen · 208 lines · 8 tokens per session scan A 4f595e490482

Subscribe to this mod's changes

add-spec is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 8 tokens to every session and 1,925 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 2026-09-01.