sync-check

A command that compares a project's requirements documents with its actual code. It looks for missing requirements, code that breaks the written rules, and code that the documents do not describe.

In plain words
What is it for?
Use it for periodic requirements-to-code audits after running /spec-build, the separate command that checks whether the requirements documents agree with one another. It records draft issues in OPEN-ISSUES.md but does not change the code.
Why use it?
It exposes differences between what the project says it should do and what it really does. This helps teams decide whether to change the code or update the requirements.

Command for Claude Code

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/washingtonwei/project-pulse/sync-check
Clone the repo
git clone --depth 1 https://github.com/Washingtonwei/project-pulse

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,145 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 $0.00000 $0.03145
Opus 5 $0.00000 $0.01572
Sonnet 5 $0.00000 $0.00629
Haiku 4.5 $0.00000 $0.00314

Measured 2d ago against content hash 7fdabb73fddc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-check 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 2d 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/sync-check.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sync-check — Spec ↔ Code conformance audit

Detect drift between the requirements docs and the actual codebase — where built code diverges from the spec, where the spec is unimplemented, and where code exists that no spec describes. This is the periodic companion to /spec-build.

/spec-build vs /sync-check — two different jobs, don't conflate them:

  • /spec-build = do the docs agree with each other? Intra-doc consistency (anchors, slugs, FR/BR refs, UC↔traceability). Mechanical, deterministic, cheap, auto-fixes. Run it freely after doc edits.
  • /sync-check (this) = do the docs agree with the code? Spec↔code conformance. Mostly semantic (read code, judge whether a rule is enforced), expensive, somewhat non-deterministic, and report-mostly — every finding needs a human fix-code-vs-amend-doc decision, so it never edits code and never "auto-fixes" a divergence. Its only write is appending draft OI-n items to docs/requirements/OPEN-ISSUES.md.

Run /spec-build first (or assume it passes) — /sync-check relies on the docs being internally consistent and the traceability matrix being current. This command reuses, does not duplicate, /spec-build's UC↔traceability coverage check.


Arguments / scope

/sync-check [scope] where scope is one of:

  • (none)changed-since-last-run (default). Read the last-audit baseline marker in OPEN-ISSUES.md (see Phase 0), git diff <baseline>..HEAD --stat to find changed backend//frontend//docs/ paths, and scope the semantic Phase B to the BRs/UCs/areas those touch. Phase A (mechanical) always runs in full — it's cheap.
  • --full → exhaustive: every BR, every UC main-flow + extensions, every endpoint and enum. Expensive; this is the deliberate 4-pass audit. Use after large changes or on a schedule.
  • <area> (e.g. EVA, DOC, ram/document, BR-deletion-integrity) → scope to one UC-area, package, or a set of BRs.

Default to changed-since-last-run; drift only appears where code or specs changed, so this is both cheaper and higher-signal. State the chosen scope at the start of the run.

Read the full file on GitHub · 94 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. 2d ago First seen · 94 lines · 0 tokens per session scan A 7fdabb73fddc

Subscribe to this mod's changes

sync-check is a command published in the GitHub repository Washingtonwei/project-pulse (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,145 tokens. 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 2026-08-31.