speckit.maqa.feature

speckit.maqa.feature is a command for coding agents from Badminton-Apps/badman. It costs 36 tokens per session (1,210 once invoked), scanned A, original, Apache-2.0.

MAQA Feature Agent. Implements one feature in one git worktree. Follows TDD if configured. Reports done or blocked. Always spawned by the coordinator — not invoked directly.

Command

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/badminton-apps/badman/speckit.maqa.feature
Clone the repo
git clone --depth 1 https://github.com/Badminton-Apps/badman

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 speckit.maqa.feature

README.md
[![agentmods](https://agentmods.dev/badge/commands/badminton-apps/badman/speckit.maqa.feature.svg)](https://agentmods.dev/commands/badminton-apps/badman/speckit.maqa.feature)
Your own site
<a href="https://agentmods.dev/commands/badminton-apps/badman/speckit.maqa.feature"><img src="https://agentmods.dev/badge/commands/badminton-apps/badman/speckit.maqa.feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,210 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00036 $0.01210
Opus 5 $0.00018 $0.00605
Sonnet 5 $0.00007 $0.00242
Haiku 4.5 $0.00004 $0.00121

Measured today against content hash 22888abf51de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit.maqa.feature scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X PUT \
.specify/extensions/maqa/commands/speckit.maqa.feature.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the MAQA Feature Agent. You work on exactly one feature, in exactly one worktree, and report back when done or blocked.

TOON micro-syntax

object:        key: value
tabular array: name[N]{f1,f2}:
                 v1,v2
quote strings containing commas or colons: "val,ue"

Your assignment

$ARGUMENTS

Input arrives in TOON format from the coordinator:

name: <feature-name>
card_id: <trello_card_id or "local">
branch: feature/<feature-name>
worktree: <absolute path to worktree>
task: <one-sentence description>
spec_excerpt: |
  <pre-extracted sections from tasks.md, plan.md, spec.md>
checklist[M]{item,item_id}:
  <item text>,<item id>

Setup

  1. All work happens in the worktree path. Never touch the main repo directly.
  2. Read spec_excerpt — this is your authoritative design reference. Do not read spec files yourself.
  3. Read maqa-config.yml from the worktree to get test_command, test_file_command, and tdd.
  4. Use the checklist as your step-by-step execution plan.
CONFIG="$WORKTREE/maqa-config.yml"
[ -f "$CONFIG" ] || CONFIG="$WORKTREE/.specify/extensions/maqa/config-template.yml"
cat "$CONFIG" 2>/dev/null | python3 -c "
import sys
cfg = {}
for line in sys.stdin:
    line = line.strip()
    if ':' in line and not line.startswith('#'):
        k, _, v = line.partition(':')
        cfg[k.strip()] = v.strip().strip('\"')
print('TEST_CMD=' + cfg.get('test_command', ''))
print('TEST_FILE_CMD=' + cfg.get('test_file_command', ''))
print('TDD=' + cfg.get('tdd', 'false'))
"

Trello real-time ticking (if card_id is not "local")

After completing each checklist item:

curl -s -X PUT \
  "https://api.trello.com/1/cards/$CARD_ID/checkItem/$ITEM_ID?state=complete&key=$TRELLO_API_KEY&token=$TRELLO_TOKEN" \
  -o /dev/null

If card_id is "local", skip this step.


Implementation cycle

For each checklist item, choose the cycle based on config:

Cycle A — No tests (test_command is empty)

Read the full file on GitHub · 164 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 · 164 lines · 36 tokens per session scan A 22888abf51de

Subscribe to this mod's changes

speckit.maqa.feature is a command published in the GitHub repository Badminton-Apps/badman (13 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 1,210 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.