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.
npx skills add emaraschio/cursor-commands --skill instruction-ablationgit clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote 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/skills/emaraschio/cursor-commands/instruction-ablation)<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/instruction-ablation"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/instruction-ablation/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/skills/emaraschio/cursor-commands/instruction-ablation"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/instruction-ablation.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 | $0.00078 | $0.01584 |
| Opus 5.5 | $0.00031 | $0.00634 |
| Sonnet 5.5 | $0.00016 | $0.00317 |
| Haiku 4.5 | $0.00008 | $0.00158 |
Grade A, and why
instruction-ablation 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruction ablation
Role
You run an instruction ablation: rebuild a minimal instruction set from a bare baseline on one real task. You execute the task in-session under GUARDRAILS only, record what already works, and propose a new instruction only when the same failure pattern repeats. For each proposal: explain the failure, write the smallest instruction, retest, and keep it only if VERIFICATION improves. You do not rewrite the user's rules, skills, hooks, or memories unless they say apply now with targets.
When to use
Use when the user invokes /instruction-ablation, asks to delete and rebuild AI instructions from evidence, or wants to thin rules/skills/hooks after models improved. For debugging a pasted prompt with a tiny eval suite, use prompt-eval-debug. For composing a new structured prompt from a rough ask, use structure-prompt. For a six-part Goal before autonomous work, use define-agent-goal.
Ablation charter
Start bare. Run a real task. Add an instruction only after repeated failure. Retest. Keep only if verification improves. Never claim the environment was bare without confirmation.
Workflow
Run phases in order.
Phase 0: Intake
- Require four fields:
- TASK: the real work to attempt
- GUARDRAILS: rules that must not be violated
- EXIT CRITERIA: exactly what "done" means
- VERIFICATION: how to test or inspect the result
- If any field is missing, ask one focused question per gap. Do not invent values.
- Optionally accept a paste or description of the user's current instruction stack (rules, skills, hooks, memories) for later delete-candidate analysis.
- If the task is production-destructive and GUARDRAILS lack explicit consent for that blast radius, stop and ask before the bare run.
Phase 1: Baseline gate
A slash command cannot disable Cursor skills, hooks, memories, or user rules.
- Ask the user to confirm a clean chat / overlays disabled when possible.
- If they confirm: record baseline status as confirmed bare (within harness limits).
- If they cannot or will not: record contamination (what likely remains active) and proceed only after stating that ablation results are contaminated.
- Never claim hooks, memories, or rules were disabled without user confirmation.
- For the bare run, do not lean on catalog workflow skills, hooks, or detailed user workflow instructions beyond GUARDRAILS and the four intake fields.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 138 lines · 78 tokens per session scan A a01fde6ac942
instruction-ablation is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 1,584 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
mobile-emulator-test
QA a native Android or Expo dev-client build end to end on the emulator, checking UI, Supabase, and Sentry for each CRUD step. Use for "test on emulator", "QA Android build", "verify native build", "white screen", "cache rehydration", or "adb reverse".
audit-accessibility
WCAG 2.2 audit via playwright-cli: crawl every page, inject axe-core, test keyboard nav, contrast, ARIA labels, heading order. Use when "audit accessibility", "check a11y", "WCAG audit", "check keyboard nav", or "test screen reader".
deploy-verify
Post-deploy smoke test across browser, Sentry, Supabase, Langfuse, and the public web. Use when "verify deploy", "smoke test production", "post-release check", or "ship or rollback". Deploy plus watch → workflow-ship-and-observe.
audit-realworld
Read-only conformance audit of a full-stack app against RealWorld ("Conduit"): API spec, shared E2E suite, closest-stack reference. Use when "audit against RealWorld", "Conduit conformance", or "is my full-stack app complete?".
enhance-web-forms
Build or upgrade web forms: accessible structure, schema-driven validation, client↔server parity. Use when "improve this form", "form validation", "accessible form", "multi-step form", "form error handling", or "the form UX is bad".
iterate-agent-harness
Turn an agent failure (premature stop, false completion, gamed check, missed file) into a rule, hook, or CI guard with a regression test. Use when "the agent stopped early again", "it gamed the test", or "add a guard so this doesn't recur".