Open source · Agent skill
v2.1.0 · MIT
Innovate or Die
Ask an AI assistant for ideas and you tend to get the advice everyone else gets. This is an agent skill that makes it search harder — it generates a large pile of candidates, has a second copy of the model attack that pile from an isolated context, keeps only what survives, and hands back one cheap experiment you could run this week.
Plugin details
- Version
- 2.1.0
- License
- MIT
- Author
- Ken Pendergast
- Marketplace
- pestalytix
What you get back
An answer you can argue with.
It is also built to tell you plainly when the boring, conventional answer is the right one. The goal is not novelty for its own sake; it is finding the valuable thing everyone walked past.
01
The best idea first
With the reason it should work — not just what to do, but the mechanism that would make it pay off.
02
The ideas it threw away, and why each one died
More useful than it sounds: the objection to an idea you were about to try is worth having before you spend the money on it.
03
One experiment
Chosen to be the cheapest way to learn the most, with a clear number that counts as pass and a clear number that counts as fail.
04
What it might still be missing
The assumptions it could not check and the facts it had to take on faith.
How it works
Six stages · four roles · one bounded correction loop
The critic never sees the answer being written.
Keeping the roles apart is the design choice everything else rests on: an author who knows the filter optimizes for the filter. The innovator produces its full candidate space before the critic is loaded at all, and on hosts with real subagents the two run in genuinely separate contexts.
01
Frame
Restate the real problem and name what counts as the obvious answer.
02
Innovate
At least 10 assumptions classified real-vs-inherited, 5 reformulations, 8 lenses from distant fields, 30 candidates with mechanisms.
03
Critique
Isolated. A seven-test fake-novelty detector, a nine-probe adversarial checklist, and a falsifier standard. Killing 8–15 of 30 is normal.
04
Revise and select
Reopen the territory the critic named, pick finalists on asymmetric potential, push each to its more radical version.
05
Gate
Eight dimensions scored 1–5. A pass needs every score at 4 or above.
06
Deliver
Opens with a version-stamped activation banner, then the strongest thesis, the reframing, top opportunities with mechanisms, the most contrarian hypothesis, the cheapest high-information experiment, a compact kill list, and what may still be missing.
Install
Pick the row for the host you use.
Then ask it something hard, or say innovate or die. Naming the skill in your request is the reliable way to start it, and from v2.1.0 the answer opens with ⟦innovate-or-die v2.1.0⟧ so you can tell that it did.
- Claude Code
Add the marketplace, then install the plugin. If you are not sure which row to pick, use this one — it is two commands, and it is the setup the skill was designed for, because the roles genuinely run in separate sessions.
/plugin marketplace add pestalytix/innovate-or-die/plugin install innovate-or-die@pestalytix
- claude.aiwebsite or app
Download the skill zip without “flat” in its name from the latest release, then go to Customize → Skills → + → Create skill → Upload a skill. Needs code execution turned on under Settings → Capabilities.
innovate-or-die-skill-v2.1.0.zip
- Codex
Clone the repo. The skill is already in place and gets picked up automatically.
.agents/skills/innovate-or-die/
- GitHub Copilot
Clone the repo the same way. The skill is already in place.
.github/skills/innovate-or-die/
- Codex CLIas a plugin
Install the repo as a plugin. The manifest tells it where to look.
.codex-plugin/plugin.json
- VS Code / Visual Studio
Copy the Copilot agent profiles into your agents directory and start with the one named innovate-or-die.
adapters/copilot/agents/*.agent.md.github/agents/
- ChatGPTas a Custom GPT
Easiest: open the ready-made GPT — it is reachable by link and is not listed in the GPT Store. Or build your own: paste the instructions file into the Instructions box and upload the knowledge file as Knowledge.
Open the ready-made GPT (opens in a new tab)
adapters/web/chatgpt-gpt-instructions.mdadapters/web/chatgpt-gpt-knowledge.md
- Geminias a Gem
Easiest: open the ready-made Gem. Or build your own: paste the instructions into the Gem and attach the knowledge file.
Open the ready-made Gem (opens in a new tab)
adapters/web/gemini-gem-instructions.mdadapters/web/gemini-gem-knowledge.md
- Perplexity Computer
Download the flat skill zip from the latest release — Perplexity needs a different zip layout from claude.ai — then go to Computer → Skills → Create skill → Upload a skill.
innovate-or-die-skill-flat-v2.1.0.zip
- Perplexityas a Project
Paste the instructions into the Project instructions, and upload the knowledge file to the Project’s Files.
adapters/web/perplexity-project-instructions.mdadapters/web/perplexity-project-knowledge.md
- Microsoft 365 Copilotin Agent Builder
Paste the instructions into Instructions — that field holds 8,000 characters — and add the knowledge file as a knowledge source.
adapters/web/m365-copilot-instructions.mdadapters/web/m365-copilot-knowledge.md
- Any host that accepts Agent Skills
Copy the skill folder into wherever that host keeps its skills.
skills/innovate-or-die/
- Any host that takes no attachments
Paste the whole single-file fallback matching your host into the chat. The weakest option — see the fidelity levels below.
adapters/web/<target>-fallback.md
What you get on each host
Hosts differ in how much real role separation they can provide, so fidelity degrades in four known steps.
Level 1
Agentic hosts with subagents — Claude Code, Codex, Copilot coding agent
The innovator and critic run in genuinely separate contexts. Full fidelity.
Level 2
Copilot agent profiles
One profile per role plus an orchestrator. The separation is real but manual: you open a fresh chat per role and hand forward only what the next role is entitled to see. Fidelity depends on you following that.
Level 3
One context, staged reading — ChatGPT GPTs, Gems, Agent Builder, Perplexity Projects, Perplexity Computer
The instructions file carries the principles and workflow; the role briefs live in an attached knowledge file read stage by stage. Two caveats: there is no true isolation, only discipline, and knowledge-file access is retrieval-mediated, so a role brief may in principle arrive in fragments. Verbatim quota-extraction probes have been run and passed on a Gemini Gem and on Perplexity Computer, both on 20 August 2026; the other retrieval implementations remain untested.
Perplexity Computer is the most capable host on this rung — the only one that installs as a full zip rather than a paste plus an attachment, and the only one that runs live web search inside the protocol. It also draws on what Perplexity already knows about you: one run referenced four facts about the user’s projects and location that were nowhere in the prompt. Useful more often than not, but worth knowing before you use it on anything sensitive. It is still not Level 1 — on two observed runs it did not dispatch the stages as separate sub-agents, so the roles shared one context. An excellent install is not the same as real isolation, and only isolation moves a host up.
Level 4
Single-paste fallback
Everything inlined for hosts that take no attachment. The whole protocol — including what the critic checks for — is in context from the first token, which is the anchoring failure the design exists to defeat. The document also exceeds every known instruction-field cap, so it may be truncated. Shipped because a documented degraded path beats an undocumented one, not because it is recommended.
Not every cap behind those levels is equally solid: the Gemini Gem limit is a lower bound that has been watched to hold rather than a published figure, and the Perplexity Projects limit is reported by its help centre but has never been paste-tested.
Every host format fact, with the date it was verified (opens in a new tab)
Known limits
Stated as measured
What it costs you and where it fails.
It doesn’t always switch on — but from v2.1.0 you can tell
The answer now opens with a marker naming the skill and the version that produced it. If that line is there, it ran: nothing else writes it. If it is missing, that is a strong hint but not proof — a model that ran the protocol can still skip the line, and the older tell still applies, so no kill list and no pass/fail experiment means it didn’t run. The banner does not make activation more likely; it makes a miss visible. Naming the skill in your request is still the reliable way to start it. In published testing before the banner existed, the skill was installed for 7 runs on Claude Code and switched on in 3 of them — a raw count, not a rate, on a sample far too small to be one — while it started reliably every time in Codex.
It is slow and it eats your usage allowance
It genuinely does more work: dozens of ideas generated and discarded down to a few before it answers. That cost is the trade. Formatting rules keep the output from sprawling, and nothing in the design rewards long answers.
It doesn’t know your prices, your local rules, or your regulations
When an idea depends on a number or a law it wasn’t given, it is instructed to say so and name what you need to look up rather than invent a plausible figure. Look those up before acting on anything.
It’s the wrong tool for two jobs
If you already have your options and need to pick one, that’s a decision, not a search. If you have the plan and need it carried out, that’s execution. This does neither.
The activation write-up, including the explanations that were wrong (opens in a new tab)
Permissions, data, and safety
Everything here is checkable in the repository.
The package is instruction text, not software. That is the whole of its attack surface, and it is why each of the statements below can be confirmed by reading the published files rather than taken on trust.
- What installs is instruction text
- The skill package is eight Markdown files: SKILL.md, principles.md, two reference files, and four role briefs. No scripts, no binaries, no build step, no post-install hook. The repo’s Python tooling — a generator that builds the install surfaces from the source of truth, and a packager that builds the release zips — is developer tooling and is not part of what a host loads.
- It declares no tools and no servers
- The plugin manifest points at a skills directory and nothing else. It defines no commands, no hooks, no MCP servers, and requests no permissions or credentials of its own.
- No telemetry and no data collection
- Nothing is logged, transmitted, or reported back. The package contains no code that could do so, and there is no service behind it — it has no account, no server, and no API key. Your prompts and its answers stay between you and your AI host, under that host’s terms.
- It may cause your assistant to use its own tools
- The protocol reads outside sources when the host offers a browsing or search tool, and on Perplexity Computer it runs live web search inside the protocol and draws on what Perplexity already knows about you. That activity is your assistant’s, under your host’s existing permissions and your own approval — the skill adds no network access of its own — but it is worth knowing before you point it at anything sensitive.
- Embedded instructions are treated as data
- Since v2.0.2 the protocol states that instructions found inside supplied documents, pages, or tool results are material to analyse, never directives to follow, and that a source telling the model what to do rather than what is true is itself a finding worth reporting. Only your own request directs the work.
- Releases are built by CI from the tag
- Release assets are produced only by the tagged release workflow, never from anyone’s working tree, and the job refuses to publish unless the tag matches the version recorded in the source of truth. Builds are reproducible: rebuilding a published tag yields byte-identical zips. MIT licensed, copyright 2026 Ken Pendergast.
Evaluation
Tested against itself, and the results are published.
Method
Every test case runs twice — once with the skill and once without, same prompt and same model — and the delta is the result. It has been run against two different providers’ models, with majority-vote grading over three judgments per case, introduced after grader nondeterminism was measured. Every run is published, including the ones that went badly.
What it shows
With the skill, the models reliably produce the protocol’s full output structure — falsifiers, a kill list, an experiment spec — which they rarely produce unprompted.
What it does not establish
Whether that structure yields better decisions is not yet tested.
It is not always worth the cost: in one case the skill spent 19 times the tokens for no measurable gain.
The quotas exist to force volume. Whether each quota earns its cost is untested — no ablation has been run.
Role separation is not evidence. The evaluator is a quality gate, not proof of correctness: a protocol that scores itself well can still be wrong.
Every evaluation run, with its raw results (opens in a new tab)
Support
One maintainer, and a place to reach him.
Innovate or Die is maintained by Ken Pendergast. Bug reports, host compatibility findings, and evaluation challenges are all welcome — the failures are the part of this project that gets published fastest.
- Issues and bug reports
- GitHub Issues (opens in a new tab)
- Releases
- v2.1.0 (opens in a new tab)