agentmods.dev

spec

A command that creates a written goal specification and implementation plan before coding begins. The specification records the intended result, how to test it, what not to change, and when to stop.

In plain words
What is it for?
It is for creating PROMPT.md and IMPLEMENTATION_PLAN.md from the user's request before implementation starts.
Why use it?
It reduces the risk that an agent keeps writing code while gradually solving a different problem than the one requested.

Command for Claude Code

753 +2 1mo ago A scan 20 tokens original MIT
View the source file Archive228/loopkit
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/archive228/loopkit/spec
Clone the repo
git clone --depth 1 https://github.com/Archive228/loopkit

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 453 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 $0.00020 $0.00453
Opus 5 $0.00010 $0.00227
Sonnet 5 $0.00004 $0.00091
Haiku 4.5 $0.00002 $0.00045

Measured yesterday against content hash 954065a80621, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.claude/commands/spec.md · 34 lines

What it actually says

/spec — write the goal spec before you act

Without an external contract, the agent drifts after ~3 iterations and the failure looks like progress (code written, tests pass, wrong goal solved).

Steps

  1. If PROMPT.md exists and --force was NOT passed, stop and print:

    PROMPT.md already exists. Re-run with /spec --force to overwrite, or edit the file directly.

  2. Load the spec-first skill by reading skills/spec-first/SKILL.md (repo layout) or .claude/skills/spec-first/SKILL.md (installed layout).
  3. Write PROMPT.md from templates/PROMPT.md, filling in from the user's latest turn:
    • Goal — one sentence, user-observable outcome.
    • Done when — concrete, testable conditions. Include the exact command that must go green.
    • Never touch — files and areas off-limits.
    • Stop if — abort conditions (scope creep, passing test starts failing, more than N files change outside scope).
  4. Write IMPLEMENTATION_PLAN.md from templates/IMPLEMENTATION_PLAN.md with STATUS: not-started on line 1 (the exact string run.sh greps for).
  5. Print both file paths and STOP. Do not implement in the same turn.

Refuse if

  • The user's request is too vague to write "Done when" concretely. Ask 1–3 clarifying questions and stop.
  • The task is a one-line refactor or a typo fix. /spec is for tasks with more than 2 steps.

Never

  • Skip PROMPT.md because the task "seems small".
  • Edit PROMPT.md after acting to match what you shipped. That is drift, not spec.
  • Start writing code in the same turn as /spec. The user reviews first.
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 · 34 lines · 20 tokens per session scan A 954065a80621

Subscribe to this mod's changes

spec is a command published in the GitHub repository Archive228/loopkit (753 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 453 once invoked, about $0.0001 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.

Data and AIPlanning
Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens