iteration-cap

A setting for the maximum number of revision attempts in Second Pass, a review step for drafts.

In plain words
What is it for?
Use it to choose the allowed number of review attempts, from one or more, while retaining the other Second Pass settings.
Why use it?
It limits how long the review-and-revision cycle can continue, helping control time and token use.

Command

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 commands/hubwizard/second-pass/iteration-cap
Clone the repo
git clone --depth 1 https://github.com/HubWizard/second-pass
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 471 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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00471
Opus 5 $0.00015 $0.00235
Sonnet 5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 2d ago against content hash 1b52a9a08277, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

iteration-cap 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.

commands/iteration-cap.md · 42 lines

What it actually says

Set Second Pass iteration cap

The user wants to set the Second Pass iteration cap to: $ARGUMENTS

Perform these steps:

  1. Validate the argument. It must be a positive integer (1 or greater). Reject: empty, non-numeric, zero, negative, decimal, multiple tokens. If invalid, respond with:

    Invalid cap. Usage: /second-pass:iteration-cap <positive integer>
    

    and stop.

  2. Warn on extreme values (do not block, just warn in the confirmation message):

    • Cap of 1 means no iteration — one grading pass, ship whatever comes back.
    • Cap above 5 means heavy token cost per non-measurable output. Note this in the confirmation.
  3. Ensure the config directory exists: ~/.claude/second-pass/. Create it if missing.

  4. Read existing config at ~/.claude/second-pass/config.json if it exists. If it does not exist, start from defaults:

    {"passing_grade": "B", "iteration_cap": 3}
    
  5. Update the iteration_cap field to the parsed integer. Preserve all other fields (e.g., passing_grade) unchanged.

  6. Write the updated config back to ~/.claude/second-pass/config.json as valid JSON (pretty-printed, 2-space indent).

  7. Confirm to the user in a single line:

    Second Pass iteration cap set to <N>. After <N> attempts, the best graded output ships with the grade attached.
    

    If cap == 1, append: Note: cap of 1 disables iteration — one grading pass, then ship. If cap > 5, append: Note: high cap may use significant tokens per non-measurable output.

Do not ask the user questions. Do not list the rubric. Do not explain what Second Pass is. This is a config change — be terse and done.

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.

  1. 2d ago First seen · 42 lines · 29 tokens per session scan A 1b52a9a08277

Subscribe to this mod's changes

iteration-cap is a command published in the GitHub repository HubWizard/second-pass (2 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 471 once invoked, about $0.0001 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.