import-spec

import-spec is a command for coding agents from ai-sdlc-framework/ai-sdlc. It costs 48 tokens per session (758 once invoked), scanned A, original, Apache-2.0.

A command that imports a Spec Kit feature's tasks.md file into an AI software-development backlog. Spec Kit is a format for planning a software feature, and the file lists its work items.

In plain words
What is it for?
Use it to add every task from a feature plan to the backlog, while detecting missing or unfamiliar task-file formats.
Why use it?
It turns planned work into separate backlog tasks and keeps each task linked to the original planning document.

Command

Part of the ai-sdlc plugin — 1 skill, 16 commands, 9 agents shipped together

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/ai-sdlc-framework/ai-sdlc/import-spec
Clone the repo
git clone --depth 1 https://github.com/ai-sdlc-framework/ai-sdlc

Or install ai-sdlc, the plugin that ships this one along with the rest of its 1 skill, 16 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 import-spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/ai-sdlc-framework/ai-sdlc/import-spec.svg)](https://agentmods.dev/commands/ai-sdlc-framework/ai-sdlc/import-spec)
Your own site
<a href="https://agentmods.dev/commands/ai-sdlc-framework/ai-sdlc/import-spec"><img src="https://agentmods.dev/badge/commands/ai-sdlc-framework/ai-sdlc/import-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 758 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 $0.00048 $0.00758
Opus 5 $0.00024 $0.00379
Sonnet 5 $0.00010 $0.00152
Haiku 4.5 $0.00005 $0.00076

Measured 3d ago against content hash b3753b0bd1b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

import-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 3d 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.

ai-sdlc-plugin/commands/import-spec.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Import a spec-kit feature into the AI-SDLC backlog. The spec-kit tasks.md at --from <path> is parsed; one backlog task is created per upstream task entry, each carrying a specRef: frontmatter block pointing back to the upstream artifact.

Per RFC-0036 OQ-1 + OQ-11 (resolved 2026-05-16)

  • tasks.md only. No fallback to spec.md. Missing tasks.mdDecision: incomplete-spec-detected is opened in the Decision Catalog and a clarification task is filed back in the backlog asking the operator to run /speckit.tasks upstream and re-run the import.
  • Auto-detect schema; refuse unknown. Unrecognised tasks.md layout → Decision: upstream-schema-unknown is opened + an upgrade-framework task is filed asking for parser support.

Phase scope (Phase 4 of RFC-0036)

  • ✓ CLI + slash command
  • specRef: back-references on every generated task
  • ✗ DoR at import time (Phase 5 / AISDLC-330)
  • ✗ Reconcile / drift handling (Phase 6 / AISDLC-331)

Usage

node pipeline-cli/bin/cli-import-spec.mjs --from .specify/specs/<feature>/

$ARGUMENTS is the path. Accepts either the feature directory (containing tasks.md) or the tasks.md file directly.

ARGS="${ARGUMENTS:-}"
if [[ -z "$ARGS" ]]; then
  echo "Usage: /ai-sdlc import-spec --from <path-to-spec-kit-feature>"
  exit 1
fi

# Pass the operator's args straight through. `--from` is the only required
# flag; `--work-dir` defaults to cwd; `--format` defaults to text.
node pipeline-cli/bin/cli-import-spec.mjs $ARGS

Output

  • Imported: one line per task written, formatted as IMP-N (upstream T-NNN) → <path>.
  • Incomplete spec: the Decision id (DEC-NNNN) + path of the clarification task created in backlog/tasks/.
  • Unknown schema: same, but the clarification task asks for parser support rather than an upstream re-run.

In all three cases the CLI exits 0 — the failure modes are explicitly non-blocking per RFC-0035 G0. The operator's next triage pass sees the Decision + clarification task and decides next steps.

Read the full file on GitHub · 69 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. 3d ago First seen · 69 lines · 48 tokens per session scan A b3753b0bd1b5

Subscribe to this mod's changes

import-spec is a command published in the GitHub repository ai-sdlc-framework/ai-sdlc (92 stars, last pushed 10d ago), licensed Apache-2.0. It adds 48 tokens to every session and 758 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 2026-08-30.