post-cold-start-verification

post-cold-start-verification is a cursor rule for Cursor from kunalsuri/ai-fication-kit. It costs 25 tokens per session (490 once invoked), scanned A, original, Apache-2.0.

A read-only audit of the files that give an AI agent knowledge about a project, such as guides, maps, and entry instructions. It produces a prioritised report about missing, stale, or contradictory information.

In plain words
What is it for?
Finding unfinished placeholders, checking that documented paths and modules exist, comparing project profiles and commands, and reporting inconsistencies that need correction.
Why use it?
It finds documentation problems that can make an agent follow incorrect paths or instructions after a project is started from scratch. It uses an existing mechanical verification manifest when available instead of repeating path checks manually.

Cursor rule for Cursor

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 rules/kunalsuri/ai-fication-kit/post-cold-start-verification
Clone the repo
git clone --depth 1 https://github.com/kunalsuri/ai-fication-kit

Made for: Cursor.

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 post-cold-start-verification

README.md
[![agentmods](https://agentmods.dev/badge/rules/kunalsuri/ai-fication-kit/post-cold-start-verification.svg)](https://agentmods.dev/rules/kunalsuri/ai-fication-kit/post-cold-start-verification)
Your own site
<a href="https://agentmods.dev/rules/kunalsuri/ai-fication-kit/post-cold-start-verification"><img src="https://agentmods.dev/badge/rules/kunalsuri/ai-fication-kit/post-cold-start-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 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 $0.00025 $0.00490
Opus 5 $0.00013 $0.00245
Sonnet 5 $0.00005 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 5d ago against content hash bb2dfdf6e5f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

post-cold-start-verification 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.

.cursor/rules/post-cold-start-verification.mdc · 36 lines

What it actually says

Audit the AI knowledge layer. Read-only with one exception: you may write ONE report.

Step 0 — use the mechanical verifier's output, don't redo its job

If ai/analysis/audit-reports/VERIFICATION_MANIFEST.json exists, read its summary and the non-confirmed claims first: path-existence checking is already done deterministically by the kit's verify command (run from the kit checkout: node install.mjs verify <repo> — no LLM involved, so its statuses are facts). Spend your pass on what a script cannot judge (checks 1, 3, 4 below, and the semantic half of check 2). If the manifest is absent or older than the docs it covers, recommend regenerating it in your report instead of re-deriving path checks by hand.

Checks

  1. Placeholders: find every <fill in>, ? Stability, and {{...}} leftover across ai/ and the entry files (CLAUDE.md, AGENTS.md).
  2. Internal consistency: every path mentioned in ai/guide/* exists on disk (covered by the manifest when present — see Step 0); MODULE_MAP rows correspond to real directories; FEATURE_MAP entries point at real files; diagrams name real modules.
  3. Profile consistency: build/test commands in CLAUDE.md/AGENTS.md match ai/repo-profile.json; flag divergence (don't silently fix).
  4. Provenance hygiene: no [verified] tag lacking a date; nothing you can tell was agent-written carrying [verified].

Output

Write ai/analysis/audit-reports/<YYYY-MM-DD>-post-cold-start.md: findings grouped P1 (agent-blocking) / P2 (misleading) / P3 (cosmetic), each with location and a one-line suggested fix. Tag the report itself [inferred]. Do not modify the files you are auditing.

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 · 36 lines · 25 tokens per session scan A bb2dfdf6e5f2

Subscribe to this mod's changes

post-cold-start-verification is a cursor rule published in the GitHub repository kunalsuri/ai-fication-kit (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 25 tokens to every session and 490 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 2026-08-31.