specpilot-sync

specpilot-sync is a command for Claude Code from girishr/SpecPilot. It costs 14 tokens per session (196 once invoked), scanned A, original, MIT.

A command that compares project specification files with the actual source tree and package configuration to find documentation drift.

In plain words
What is it for?
Reviewing architecture, requirements, and test documentation, listing concrete mismatches, and proposing file-by-file corrections for approval.
Why use it?
It identifies when specs describe old files, versions, dependencies, commands, or test suites and prevents those discrepancies from being silently ignored.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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/girishr/specpilot/specpilot-sync
Clone the repo
git clone --depth 1 https://github.com/girishr/SpecPilot

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 specpilot-sync

README.md
[![agentmods](https://agentmods.dev/badge/commands/girishr/specpilot/specpilot-sync.svg)](https://agentmods.dev/commands/girishr/specpilot/specpilot-sync)
Your own site
<a href="https://agentmods.dev/commands/girishr/specpilot/specpilot-sync"><img src="https://agentmods.dev/badge/commands/girishr/specpilot/specpilot-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 196 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 5.1 $0.00014 $0.00196
Opus 5 $0.00007 $0.00098
Sonnet 5 $0.00003 $0.00039
Haiku 4.5 $0.00001 $0.00020

Measured 6d ago against content hash 1da5cdd9a0ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

specpilot-sync 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 6d 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/specpilot-sync.md · 13 lines

What it actually says

Find and fix drift between .specs/ and the real project.

  1. Read .specs/architecture/architecture.md, .specs/project/requirements.md, and .specs/quality/tests.md.
  2. Compare their claims against the actual src/ structure and package.json (versions, dependencies, scripts).
  3. List concrete discrepancies: stale version numbers, renamed or removed files/modules still referenced, undocumented modules that exist in src/ but aren't mentioned in the specs, stale command or test-suite lists.
  4. Propose specific per-file edits to close each discrepancy — do not just describe the problem, show the fix.
  5. Wait for the user's confirmation before writing any of the proposed edits.

This is a judgment/comparison task, not a mechanical one — do not attempt to script the diff; read and reason about each file.

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. 6d ago First seen · 13 lines · 14 tokens per session scan A 1da5cdd9a0ec

Subscribe to this mod's changes

specpilot-sync is a command published in the GitHub repository girishr/SpecPilot (37 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 196 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.