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/ryan-scheinberg/harness/iterate-plannpx skills add ryan-scheinberg/harness --skill iterate-plangit clone --depth 1 https://github.com/ryan-scheinberg/harnessWrote 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/ryan-scheinberg/harness/iterate-plan)<a href="https://agentmods.dev/skills/ryan-scheinberg/harness/iterate-plan"><img src="https://agentmods.dev/badge/skills/ryan-scheinberg/harness/iterate-plan.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 5.1 | $0.00043 | $0.00597 |
| Opus 5 | $0.00022 | $0.00298 |
| Sonnet 5 | $0.00009 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
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 6d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill intends architects to directly communicate with the user via AskUserQuestion
Truly challenge every assumption in the artifact. This is where the user's judgment, taste, and experience get injected into the project — don't short-circuit that by deciding too much yourself, and don't waste it on defaults either. Rigor with convergence: probe every tradeoff that shapes implementation, and surface the ones where the user's answer actually improves the plan
Work the decision tree
Branch by branch. Resolve dependencies before moving forward. The stack decision shapes the testing question, the MVP decision shapes the deployment question. Out of order, you waste earlier answers
For each branch:
- Read what the brief already commits to
- Explore the codebase for anything it can resolve —
ls,grep, config files, existing patterns - Identify the real tradeoff — the thing that will actually split opinions
- Form your own recommendation before asking
When to ask the user
Ask when the user's answer will make the plan stronger:
- A tradeoff where the user's taste, experience, or business context is what makes the call right
- A decision that changes a slice, a dependency, the architecture, or the risk surface
- An assumption in the brief worth challenging — even one you think holds up
- A place where you genuinely don't have a recommendation
Don't ask about naming, file layout, test placement, obvious library picks, log format, standard health-check shape. Decide these, write them into the brief, move on. The user is paying for judgment on tradeoffs, not for sign-off on defaults
How to ask
Batch via one AskUserQuestion call covering the current branch. Each question names the tradeoff, offers your recommendation, and says why the alternative might be right — the user should be able to reply "go with your picks" and the brief still ends up stronger than before. The user should always be able to reply with a freeform option too
When an answer unlocks a new branch, send another batched call. Don't drift into one-at-a-time — the context-switch cost is what makes this skill feel long
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.
- 6d ago First seen · 44 lines · 43 tokens per session scan A 11211b7b094b
iterate-plan is a skill published in the GitHub repository ryan-scheinberg/harness (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 597 once invoked, about $0.0002 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
gleanin
Rules distilled from past session friction (errors, edit loops, corrections), analyzed by a stronger model and applied to guide future work. Regenerated from glean/artifacts/ plus an index of trigger-loaded protocols from GLEANPROTOCOLDIRS by sync.sh — load every session via CLAUDE.md.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.