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/HubWizard/second-passWrote 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/hubwizard/second-pass/confirm-revisions)<a href="https://agentmods.dev/commands/hubwizard/second-pass/confirm-revisions"><img src="https://agentmods.dev/badge/commands/hubwizard/second-pass/confirm-revisions/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/hubwizard/second-pass/confirm-revisions"><img src="https://agentmods.dev/badge/commands/hubwizard/second-pass/confirm-revisions.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 | $0.00039 | $0.00383 |
| Opus 5.5 | $0.00016 | $0.00153 |
| Sonnet 5.5 | $0.00008 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
confirm-revisions 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 1mo 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.
What it actually says
Set Second Pass confirm-revisions flag
The user wants to set confirm_revisions to: $ARGUMENTS
Perform these steps:
-
Validate the argument. Must be
trueorfalse(case-insensitive). Reject anything else with:Invalid value. Usage: /second-pass:confirm-revisions <true|false>and stop.
-
Ensure the config directory exists:
~/.claude/second-pass/. Create it if missing. -
Read existing config at
~/.claude/second-pass/config.jsonif it exists. If it does not exist, start from defaults:{"passing_grade": "B", "iteration_cap": 3, "confirm_revisions": false} -
Update
confirm_revisionsto the parsed boolean. Preserve all other fields unchanged. -
Write the updated config back to
~/.claude/second-pass/config.jsonas valid JSON (pretty-printed, 2-space indent). -
Confirm to the user in a single line:
- If true:
Second Pass confirm-revisions set to true. Revisions are re-judged in a loop (more confidence, more tokens). - If false:
Second Pass confirm-revisions set to false. Revisions ship after one pass (default, cheaper).
- If true:
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.
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.
- 1mo ago First seen · 34 lines · 39 tokens per session scan A 263cd607f3f1
confirm-revisions is a command published in the GitHub repository HubWizard/second-pass (2 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 383 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.
Other commands, from other repositories
review-pr
Review a pull request or the current branch with four specialist agents in parallel (code-reviewer for correctness and security, silent-failure-hunter, test-gap-analyzer, type-design-reviewer), then merge their findings into one severity-ranked review with file:line anchors and no duplicates, optionally posted to the…
review
An adversarial code review that assumes hidden bugs may exist and checks changes for correctness, structure, and security concerns.
check
A combined code-quality review and design-to-implementation consistency check. It reads the changed files once, then evaluates them from both review perspectives.
dual-review
Adversarial dual review — two independent reviewers with no shared context; both must approve before merge.
review-pr
Review a GitHub pull request by number.
review
Review the current diff against the project rules.