Borrowing it
Nothing to install: this file belongs to nickmisasi/planner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nickmisasi/planner/main/.claude/skills/iterate/SKILL.mdgit clone --depth 1 https://github.com/nickmisasi/plannerWrote 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/nickmisasi/planner/iterate)<a href="https://agentmods.dev/skills/nickmisasi/planner/iterate"><img src="https://agentmods.dev/badge/skills/nickmisasi/planner/iterate/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/nickmisasi/planner/iterate"><img src="https://agentmods.dev/badge/skills/nickmisasi/planner/iterate.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 | $0.00040 | $0.01490 |
| Opus 5.5 | $0.00016 | $0.00596 |
| Sonnet 5.5 | $0.00008 | $0.00298 |
| Haiku 4.5 | $0.00004 | $0.00149 |
Grade A, and why
iterate 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 2mo 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enter the structured iteration/refinement loop for an idea's spec. This is the core planning workflow that drives specs from draft to ready-for-implementation.
Instructions
When the user invokes /iterate, follow these steps:
1. Ensure Context is Loaded
If you haven't already loaded the current idea's files, read them now:
spec.mdassumptions.mdresearch.mdsession.mdMILESTONES.md(if it exists — provides context from prior milestones that may inform assumptions)
If no idea is currently active, trigger the /continue skill first to select one.
2. Extract Assumptions
Read through spec.md carefully and identify every assumption being made. Assumptions include:
- Technical assumptions (e.g., "the API supports pagination")
- User behavior assumptions (e.g., "users will authenticate via SSO")
- Architectural assumptions (e.g., "this can be a plugin, not a core change")
- Scope assumptions (e.g., "we only need to support PostgreSQL")
- Dependency assumptions (e.g., "the upstream library supports Go 1.21")
- Performance assumptions (e.g., "this query will return in <100ms")
- Integration assumptions (e.g., "the webhook payload includes user ID")
3. Score and Present
For each assumption, assign an honest confidence score from 1-10:
- 1-3: We're guessing. This needs validation before proceeding.
- 4-6: Reasonable assumption but unverified. Should be confirmed.
- 7-8: Well-supported by research or experience. Minor risk.
- 9-10: Verified fact or trivially true.
Present to the user:
## Spec Summary
<2-3 sentence summary of the spec>
## Phases
<List each phase/milestone from the spec with a brief description>
## Assumptions & Confidence
Overall Confidence: X/10
| # | Assumption | Confidence | Notes |
|---|-----------|------------|-------|
| 1 | ... | X/10 | ... |
| 2 | ... | X/10 | ... |
### Highest Risk (Lowest Confidence)
- Assumption #N (X/10): <why this is risky>
- Assumption #M (X/10): <why this is risky>
### Recommended Next Actions
1. <what would raise confidence the most>
2. <next best action>
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.
- 2mo ago First seen · 134 lines · 40 tokens per session scan A 121b470b680d
iterate is a skill published in the GitHub repository nickmisasi/planner (5 stars, last pushed 6mo ago), licensed MIT. It adds 40 tokens to every session and 1,490 once invoked, about $0.0002 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 2026-08-31.
iterate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| iteratenickmisasi/planner | Skill | 5 | 6mo ago | MIT | A | 40 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |