The entry point and routing guide for the I-Framework, a product-planning process with Intent, Ideation, and Innovation stages. It reads the Product folder, shows which stage is complete, and recommends the next one.

Use it to start a new product flow, inspect existing Product files, identify the next stage, and see which risks have been addressed.

It helps you resume product work without guessing what has already been done or which type of risk to examine next. It reports progress but leaves the actual writing to the stage-specific tools.

iflow — Skill by InSciCo

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 skills/inscico/i-framework/iflow

Any agent

npx skills add InSciCo/i-framework --skill iflow

Clone the repo

git clone --depth 1 https://github.com/InSciCo/i-framework

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 538 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.

Model	Per session	Once invoked
Fable 5	$0.00072	$0.00538
Opus 5	$0.00036	$0.00269
Sonnet 5	$0.00014	$0.00108
Haiku 4.5	$0.00007	$0.00054

Measured 2d ago against content hash 64e5d675edee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

iflow 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 2d 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.

.claude/skills/iflow/SKILL.md · 38 lines

What it actually says

/iflow — orchestrator & router

You are the map. You read state from disk and tell the founder where they are, which risk is next to retire, and what to run. You do not write artifacts (the stage skills do that).

Procedure

Find the product. Look for Product/ in the current directory.
- Absent: this is a fresh start. Explain the flow (Intent → Ideation → Innovation → a Product/Features/ spec) and recommend /intent.
Read state. Check which of these exist and read their frontmatter gate: field:
- Product/intent.md → stage 1, retires founder–problem risk.
- Product/ideation.md → stage 2, retires solution & demand risk.
- Product/innovation.md → stage 3, retires market/value/moat risk.
- Product/Features/ → the deliverable; count the files.
Determine position & next step. The current stage is the furthest artifact that exists; the next action is the first stage whose gate is open or whose artifact is missing. Respect the soft-gate philosophy — recommend, never block.

Report a risk-burndown snapshot, e.g.:

I-Framework status
─────────────────────────────────────────────
✅ Intent       gate passed   (founder–problem risk retired)
🔄 Ideation     gate open     (solution & demand risk — IN PROGRESS)
⬜ Innovation   not started   (market/value/moat risk)
⬜ Features     0 files
─────────────────────────────────────────────
Next: finish converging in /ideate (set a demand hypothesis), then /innovate.

Offer the next command. Recommend the single next skill to run, and mention /product-status for a full dashboard once features exist. If the founder explicitly wants to jump ahead past an open gate, let them — just name the risk they're leaving open.

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.

2d ago First seen · 38 lines · 72 tokens per session scan A 64e5d675edee

Subscribe to this mod's changes

iflow is a skill published in the GitHub repository InSciCo/i-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 538 once invoked, about $0.0004 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.

Planning agent-skills claude-code claude-code-plugin ideation plugin product-management

resume-customizer

Director-level / senior PM resume + cover letter toolkit. Generates ATS-optimized documents using verified metrics and company-type strategies. For interview prep, STAR stories, outreach templates, and salary negotiation, see the references/ folder. Personalize references/YOURPROFILE.md first.

aksheyw/career-command-center-template · 59 tokens

iflow

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/iflow — orchestrator & router

Procedure

What this file has done since we first saw it

Other skills, from other repositories

resume-customizer

apply

followup

patterns

track-application

interview