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 commands/wangke19/gemini-ai-helpers/bisectgit clone --depth 1 https://github.com/wangke19/gemini-ai-helpersWrote 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/wangke19/gemini-ai-helpers/bisect)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/bisect"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/bisect.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 | $0.00010 | $0.03814 |
| Opus 5 | $0.00005 | $0.01907 |
| Sonnet 5 | $0.00002 | $0.00763 |
| Haiku 4.5 | $0.00001 | $0.00381 |
Grade A, and why
bisect 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 yesterday.
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.
This is a copy
100% identical to bisect — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
git:bisect
Synopsis
/git:bisect # Fully interactive - will ask for all inputs
/git:bisect [good-commit] [bad-commit] # With commit references
Description
The git:bisect command is an interactive git bisect assistant that helps find the exact commit that introduced a specific change (bug, behavior change, feature, performance regression, etc.) using binary search.
What This Command Does:
- Guides you through setup - Validates commits, checks for conflicts
- Presents commits for evaluation - Shows relevant info about each commit
- Learns from your decisions - Detects patterns in your choices
- Can automate - If it understands your criterion, it can evaluate automatically (with your permission)
- Reports the result - Shows the culprit commit with full details
Terminology
Git bisect uses confusing terms. This command uses clearer labels:
| What You See | Git Term | Meaning |
|---|---|---|
| "Change IS in the code" | bad |
The change you're looking for EXISTS in this commit |
| "Change is NOT in the code" | good |
The change you're looking for does NOT exist yet |
Never use "good" or "bad" alone - always explain what they mean in context.
Workflow
1. Provide (or select) reference commits
↓
2. Describe what change you're looking for
↓
3. [If criterion is clear] Confirm understanding → Choose manual/auto
↓
4. Evaluate commits (manually or automatically)
↓
5. Receive final report with culprit commit
↓
6. Clean up (git bisect reset)
Commands During Bisect
At any point during the bisect, you can:
- "show diff" or "more details" - See the full diff for the current commit
- "skip" - Skip a commit that cannot be tested (won't build, etc.)
- "abort" - Cancel the bisect and return to your original branch
- "automate" - Ask to enable automation (if pattern detected)
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.
- yesterday First seen · 514 lines · 10 tokens per session scan A 0ad643f8f209
bisect is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 3,814 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to bisect, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
spec-design
Create comprehensive technical design for a specification.
release-prod
Guide you through promoting stage → production.
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.
modernize-extract-rules
Mine business logic from legacy code into testable, human-readable rule specifications.
mem-search
Full-text search in the memory vault (archives, contexts, histories, index).
a
Quick alias for /analyze.