Borrowing it
Nothing to install: this file belongs to DIGI-UW/OpenELIS-Global-2. 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/DIGI-UW/OpenELIS-Global-2/develop/.specify/oe/commands/iterate-plan.mdgit clone --depth 1 https://github.com/DIGI-UW/OpenELIS-Global-2Wrote 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/commands/digi-uw/openelis-global-2/iterate-plan)<a href="https://agentmods.dev/commands/digi-uw/openelis-global-2/iterate-plan"><img src="https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/iterate-plan/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/commands/digi-uw/openelis-global-2/iterate-plan"><img src="https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/iterate-plan.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 | $0.00000 | $0.02213 |
| Opus 5 | $0.00000 | $0.01107 |
| Sonnet 5 | $0.00000 | $0.00443 |
| Haiku 4.5 | $0.00000 | $0.00221 |
Grade A, and why
iterate-plan 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 9d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iterate Plan
When the user invokes /iterate-plan (optionally with arguments), perform an
evidence-based plan iteration that evaluates the existing plan against
current signals, identifies stale sections, and produces an updated plan.
This command runs in plan mode (read-only except the plan file). It is the proper way to update a plan between iterations — it prevents anchoring bias, context drift, and silent carry-forward of stale decisions.
User Input
$ARGUMENTS
Support these patterns:
/iterate-plan→ Full freshness evaluation + rewrite of current plan/iterate-plan --zero-based→ Ignore existing plan entirely; derive fresh from goals + principles + current state, then diff against old plan/iterate-plan --checkpoint→ Quick freshness check only; report stale sections without rewriting/iterate-plan "focus on X"→ Iterate with a specific focus area or user-provided direction
Why This Command Exists
LLM anchoring bias research (Nguyen et al., 2024) shows that stronger models exhibit MORE consistent anchoring to initial plan content, not less. Plans presented as authoritative context are treated as ground truth. Chain-of-thought, reflection prompts, and "ignore the anchor" instructions all fail to mitigate this. The only effective strategy is dual-anchor prompting — explicitly presenting competing perspectives (old plan vs. new feedback vs. principles) and forcing evaluation between them.
Without structured iteration, plans drift toward:
- Append-only accumulation: New sections added, stale sections preserved
- Sunk-cost anchoring: Effort already spent on a section makes it feel valid
- Legacy carry-forward: Decisions from iteration N survive to iteration N+5 without re-evaluation, pulling implementation toward outdated designs
Signal Hierarchy (non-negotiable)
When signals conflict, higher-ranked signals ALWAYS win. The plan file is the LOWEST authority — it must justify its continued existence against all higher signals.
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.
- 9d ago First seen · 234 lines · 0 tokens per session scan A f89267349df3
iterate-plan is a command published in the GitHub repository DIGI-UW/OpenELIS-Global-2 (251 stars, last pushed today), licensed MPL-2.0. It costs nothing until one of its globs matches a file; then it loads 2,213 tokens. 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.