ChecklistReader

ChecklistReader is an agent for coding agents from attilaszasz/sdd-pilot. It costs 19 tokens per session (498 once invoked), scanned A, original, MIT.

A checklist status reader that scans every checklist in a feature folder and combines their completion results into one status.

In plain words
What is it for?
Use it to check whether a feature's checklists are complete, identify unfinished items, and report blocking issues and queue progress.
Why use it?
It removes the need to inspect several checklist files manually and flags incomplete, inconsistent, or invalid work that should block implementation.

Agent

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 agents/attilaszasz/sdd-pilot/_checklist-reader
Clone the repo
git clone --depth 1 https://github.com/attilaszasz/sdd-pilot

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 ChecklistReader

README.md
[![agentmods](https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_checklist-reader.svg)](https://agentmods.dev/agents/attilaszasz/sdd-pilot/_checklist-reader)
Your own site
<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_checklist-reader"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_checklist-reader.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 498 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 $0.00019 $0.00498
Opus 5 $0.00010 $0.00249
Sonnet 5 $0.00004 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured 5d ago against content hash c5053b16522b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ChecklistReader 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 5d 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.

.github/agents/_checklist-reader.md · 67 lines

What it actually says

Task

Read checklist files and summarize gating status for implementation workflows.

Inputs

Checklist directory contents and evaluation markers.

Execution Rules

Parse statuses deterministically and preserve checklist identifier fidelity.

Output Format

Return aggregated checklist pass/fail state with blocking indicators.

1. Assess State

Run node scripts/checklist-state.mjs "<featureDir>" from the repository root. This is the sole aggregate checklist-state definition for Generate Checklist, Autopilot, and Implement.

  • Missing checklists/ returns "N/A".
  • "PASS" requires at least one non-empty checklist, every item checked, and a null or complete valid queue.
  • A pending or malformed queue, empty or incomplete file, duplicate queue ID, stale queue/file relationship, or reader failure returns "FAIL" and blocks.

3. Report

Return JSON summary:

{
  "totalFiles": <number>,
  "totalItems": <number>,
  "totalIncomplete": <number>,
  "overallStatus": "PASS" | "FAIL" | "N/A",
  "blocking": <boolean>,
  "issues": ["<blocking reason>"],
  "queue": null | { "total": 1, "completed": 1, "remaining": 0, "status": "COMPLETE" | "PENDING" | "MALFORMED" },
  "files": [
    {
      "name": "ux.md",
      "path": "specs/.../checklists/ux.md",
      "total": 10,
      "completed": 10,
      "incomplete": 0,
      "status": "PASS"
    },
    {
      "name": "security.md",
      "path": "specs/.../checklists/security.md",
      "total": 8,
      "completed": 5,
      "incomplete": 3,
      "status": "FAIL"
    }
  ]
}
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. 5d ago First seen · 67 lines · 19 tokens per session scan A c5053b16522b

Subscribe to this mod's changes

ChecklistReader is an agent published in the GitHub repository attilaszasz/sdd-pilot (95 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 498 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.