agentmods.dev

agentcmd: Command for Claude Code

.claude/commands/refresh-spec-index.md

refresh-spec-index is a command for Claude Code from jnarowski/agentcmd. It costs 7 tokens per session (967 once invoked), scanned A, original, MIT.

A command that synchronizes a project specification index with specification folders on disk, adding missing entries and removing stale ones.

In plain words
What is it for?
Use it to reconcile spec folders with index.json and update paths, statuses, and timestamps from spec files.
Why use it?
It prevents the index from disagreeing with the actual backlog, in-progress, and completed specification files.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is jnarowski/agentcmd's own configuration. It tells Claude Code how to work on agentcmd itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentcmd configures →

not rated 18repo 10mo ago A scan 7 tokens original MIT
View source ↗ jnarowski/agentcmd agentcmd.dev
Reuse

Borrowing it

Nothing to install: this file belongs to jnarowski/agentcmd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jnarowski/agentcmd/main/.claude/commands/refresh-spec-index.md
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code.

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 refresh-spec-index

README.md
[![agentmods](https://agentmods.dev/badge/commands/jnarowski/agentcmd/refresh-spec-index/github.svg)](https://agentmods.dev/commands/jnarowski/agentcmd/refresh-spec-index)
Your own site
<a href="https://agentmods.dev/commands/jnarowski/agentcmd/refresh-spec-index"><img src="https://agentmods.dev/badge/commands/jnarowski/agentcmd/refresh-spec-index/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for refresh-spec-index

Your own site · 80×15
<a href="https://agentmods.dev/commands/jnarowski/agentcmd/refresh-spec-index"><img src="https://agentmods.dev/badge/commands/jnarowski/agentcmd/refresh-spec-index.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00007 $0.00967
Opus 5.5 $0.00003 $0.00387
Sonnet 5.5 $0.00001 $0.00193
Haiku 4.5 $0.00001 $0.00097

Measured 2mo ago against content hash 6494c9646058, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

refresh-spec-index 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 2mo 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.

.claude/commands/refresh-spec-index.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refresh Spec Index

Scans spec folders and reconciles with index.json, removing orphaned entries, adding missing specs, and updating metadata.

Instructions

  • Scan all spec folders in backlog/todo/done
  • Compare to index.json entries
  • Remove entries for deleted folders
  • Add entries for untracked folders
  • Update status/timestamps from spec.md files
  • Report all changes made

Workflow

  1. Scan filesystem for spec files:

    • Use find .agent/specs/{backlog,todo,in-progress,done} -maxdepth 2 -type f -name "*.md"
    • Extract spec IDs from folder names (pattern: {id}-{feature-name})
    • Build list of filesystem specs with their file paths (relative to .agent/specs/)

  2. Load and parse index.json:

    • Read .agent/specs/index.json
    • Parse JSON structure

  3. Identify differences:

    • Orphaned entries: Spec ID in index.json but folder doesn't exist at path
    • Missing entries: Folder exists but spec ID not in index.json
    • Path mismatches: Spec moved to different folder (status derived from folder location)

  4. Update index.json:

    • Remove orphaned entries (folder deleted)
    • Add missing entries with default values
    • Update path and status when spec moved to different folder (folder location is source of truth for status)
    • Extract and sync complexity fields from spec.md for each spec:
      • totalComplexity: Parse from **Total Complexity**: X points
      • phaseCount: Parse from **Phases**: N
      • taskCount: Parse from **Tasks**: N
      • If fields not found in spec.md, omit from index.json (optional fields)
    • Preserve lastId field
    • Write back to file

  5. Report changes:

    • Show removed entries (count + ID + path)
    • Show added entries (count + ID + path + status)
    • Show updated entries (count + ID + old status → new status)
    • Show total specs after refresh

Status from Folder Location

The folder location is the source of truth for status. Do NOT use the **Status** field from spec.md for index.json status.

Read the full file on GitHub · 113 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. 2mo ago First seen · 113 lines · 7 tokens per session scan A 6494c9646058

Subscribe to this mod's changes

refresh-spec-index is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 10mo ago), licensed MIT. It adds 7 tokens to every session and 967 once invoked, about $0.0000 per session on Opus 5.5. 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.

Project management
Related

refresh-spec-index compared with commands from other repositories

refresh-spec-index next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
refresh-spec-indexjnarowski/agentcmdCommand1810mo agoMITA7Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code
convergegithub/spec-kitCommand148kyesterdayMITA35Claude Code
implementgithub/spec-kitCommand148kyesterdayMITA14Claude Code