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 agentmods add skills/inscico/i-framework/innovatenpx skills add InSciCo/i-framework --skill innovategit clone --depth 1 https://github.com/InSciCo/i-frameworkWrote 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/inscico/i-framework/innovate)<a href="https://agentmods.dev/skills/inscico/i-framework/innovate"><img src="https://agentmods.dev/badge/skills/inscico/i-framework/innovate.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01052 |
| Opus 5 | $0.00032 | $0.00526 |
| Sonnet 5 | $0.00013 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
innovate 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 4d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/innovate — Stage 3: define why we win, then spec the features
This is the payoff stage. You retire market, value & moat risk by forcing a clear UVP, then you decompose the bet into the feature set that is the deliverable. Run as a guided interview, one question at a time.
Procedure
1. Load context & check the gate (soft)
Read Product/intent.md and Product/ideation.md. If ideation.md has gate: open, warn ("you haven't settled a validated bet yet — proceed anyway?") but don't block. If ideation.md is missing, suggest /ideate first.
2. Interview for differentiation
Ask, one at a time, challenging thin answers:
- The secret: what do you believe or know that competitors don't?
- Why 10x, not 10%: on which dimension are you an order of magnitude better — painkiller, not vitamin?
- The moat: what stops a fast follower copying you? Does the advantage compound (data, network, switching costs, brand)?
- Validation: what's the cheapest evidence the value is real (willingness-to-pay, retention, "very disappointed" signal)?
3. Write Product/innovation.md
Use the structure from the plugin's templates/innovation.md. You MUST enumerate the UVP elements as an id'd list (UVP-1, UVP-2…) — every innovation feature's contributes_to references one of these ids, so a prose-only UVP silently breaks tracing. Capture the unique insight, why-10x, moat, and validation plan.
3b. (Optional) Ground the UVP in competitor research
Offer to run /compete now. If the founder accepts — or Product/competition.md already exists — use the comparison matrix as evidence for the next steps: a capability that's table-stakes across the matrix becomes implementation; a whitespace capability that maps to a UVP id becomes innovation. If they decline, proceed on judgment. /compete writes Product/competition.md; it's optional and never blocks.
4. Decompose the bet into features
Enumerate every capability the MVP needs to deliver the UVP, plus the table-stakes needed for a usable product. Aim for completeness, not minimalism, at this step — /classify and priority will separate signal from noise.
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.
- 4d ago First seen · 47 lines · 64 tokens per session scan A b4876736e35b
innovate is a skill published in the GitHub repository InSciCo/i-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,052 once invoked, about $0.0003 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.
Other skills, from other repositories
product-brainstorming
Brainstorm product ideas, explore problem spaces, and challenge assumptions as a thinking partner. Use when exploring an opportunity, generating solutions, or stress-testing an idea before converging on a direction.
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…
ask-codex
Consult OpenAI Codex for investigation, debugging, or code review. Use when user explicitly asks to "ask codex", "check with codex", "codex review", or as a last resort when stuck after 4+ failed attempts at debugging, investigation, or bug fix and completely out of ideas. Codex is slow (2-5 min), so only escalate…
new
Use when user asks to create a release, cut a release, or publish a version. Auto-detects GitHub vs GitLab vs Gitea, calculates semantic version, generates release notes from PRs/MRs or commits, shows preview for confirmation before publishing.
clarify
This skill should be used when user appears confused, frustrated, or shows misalignment between expectations and reality. Triggers on phrases like "I don't understand", "this doesn't make sense", "confused", "wait, shouldn't it...", "why is this happening", "I thought X did Y", contradictory statements, or frustration…