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.
git clone --depth 1 https://github.com/kunalsuri/ai-fication-kitWrote 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.
[](https://agentmods.dev/commands/kunalsuri/ai-fication-kit/perform-feature-add-simulation)<a href="https://agentmods.dev/commands/kunalsuri/ai-fication-kit/perform-feature-add-simulation"><img src="https://agentmods.dev/badge/commands/kunalsuri/ai-fication-kit/perform-feature-add-simulation/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.
<a href="https://agentmods.dev/commands/kunalsuri/ai-fication-kit/perform-feature-add-simulation"><img src="https://agentmods.dev/badge/commands/kunalsuri/ai-fication-kit/perform-feature-add-simulation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00277 |
| Opus 5.5 | $0.00009 | $0.00111 |
| Sonnet 5.5 | $0.00005 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
perform-feature-add-simulation 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 28d 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.
What it actually says
Simulate adding the feature the user names — WITHOUT writing a single line of code. This is a pre-flight check of both the plan and the knowledge layer.
Phases to walk (score each: smooth / friction / blocked)
- Locate — can MODULE_MAP + FEATURE_MAP/CATALOG identify the target modules without crawling? Name them.
- Plan — draft the touch list per layer; note Stability of every file you'd
change. Any
frozenor?file ⇒ blocked pending human approval. - Verify — which suites would prove it works; do they exist and are commands confirmed?
- Knowledge update — which ai/ files would need updating after the change?
Output
A friction report in chat (and, if asked, saved to ai/analysis/audit-reports/): per-phase score with the specific missing knowledge that caused friction, total estimated context cost, and a go / no-go recommendation. Knowledge gaps found here are the cheapest bugs you will ever fix — file each as an audit TODO.
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.
- 28d ago First seen · 24 lines · 23 tokens per session scan A d4b2324f603b
perform-feature-add-simulation is a command published in the GitHub repository kunalsuri/ai-fication-kit (3 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 277 once invoked, about $0.0001 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 2026-09-18.
Other commands, from other repositories
terse
Switch reply compression level — /terse [lite|full|ultra|off]. Complements RTK (input savings) with output-side savings.
start
Start a session — load context + memory and brief yourself on current state.
update
Mid-session checkpoint — save progress without ending the session.
motion
Motion work is applied within whatever component/section/page workflow is already running. If motion is the entire ask with nothing else changing, this command's steps above are sufficient on their own.
typography
This command is a lookup + decision, not a multi-step build — it doesn't need its own workflow file. If the request grows into "and now build the page using this type system," hand off to page or redesign.
cluster-instincts
Group related instincts by tag overlap and batch-promote qualifying clusters to skills. Usage - /mindforge:cluster-instincts [--dry-run] [--min-cluster 3] [--min-confidence 0.7].