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.
git clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/iterate-plan)<a href="https://agentmods.dev/commands/yonatangross/orchestkit/iterate-plan"><img src="https://agentmods.dev/badge/commands/yonatangross/orchestkit/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/yonatangross/orchestkit/iterate-plan"><img src="https://agentmods.dev/badge/commands/yonatangross/orchestkit/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 | $0.00054 | $0.00654 |
| Opus 5.5 | $0.00022 | $0.00262 |
| Sonnet 5.5 | $0.00011 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00065 |
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 today.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-generated from skills/iterate-plan/SKILL.md
Source: https://github.com/yonatangross/orchestkit
iterate-plan
Revise one plan file. The body is rewritten; the comment block is kept byte for byte, because the
review record must outlive every revision. Layout: the create-plan skill's
references/artifact-layout.md.
Steps
-
Read the plan in full, then the rest of its task directory in NN order (research, earlier plans). List the open comments:
node "skills/iterate-plan/scripts/artifact.mjs" list --file <plan> --open -
Check each comment against the code before acting on it. Open the files it names. A comment can be wrong; if so, say so in a reply instead of changing the plan.
-
Write the revised body to a scratch file: start from the current body (everything between the front matter and
<!-- ork:comments -->), apply the changes, keep the phase structure. Do not copy the comment block into it; the script refuses a body that carries one. -
Write it back through the script, which bumps
revision, refreshesshaandupdated, and keeps the comments:node "skills/iterate-plan/scripts/artifact.mjs" iterate --file <plan> --body /tmp/plan-body.md # prints <plan> revision N -
Answer each comment you addressed with a reply saying what changed. Resolve only when the reviewer asked you to, or when the comment is a factual fix you made:
node "skills/iterate-plan/scripts/artifact.mjs" reply --file <plan> --id c1 --author Claude --text "Phase 1 now names src/x.ts:40." node "skills/iterate-plan/scripts/artifact.mjs" resolve --file <plan> --id c2 --author Claude --text "Rollback step added to phase 2." -
Reply with the path, the new revision and which comments are still open. Do not implement.
Rules
- Never edit the plan file with Write or Edit: one stray write can drop the comment block.
- Never delete or rewrite a comment, even a wrong one. Reply to it.
- Iterating an approved plan moves it back to
in-review; it needs a new approval.
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.
- today First seen · 61 lines · 54 tokens per session scan A 11591627062b
iterate-plan is a command published in the GitHub repository yonatangross/orchestkit (298 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 654 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 2026-10-27.
Other commands, from other repositories
gc
On-demand code-drift / entropy scan (garbage collection) via a fresh-context drift-analyst subagent. Checks changed/active code against golden-rules.md + generic drift heuristics (dead code, duplication, doc-drift) and reports findings with an evidence path. Read-only — recommends, never auto-refactors. Not git gc.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.
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.